{
"agents": [
{
"name": "co-3",
"memory_blocks": [],
"tools": [],
"tool_ids": [
"tool-0",
"tool-1",
"tool-2",
"tool-3",
"tool-4",
"tool-5",
"tool-6",
"tool-7",
"tool-8",
"tool-9",
"tool-10",
"tool-11",
"tool-12",
"tool-13",
"tool-14"
],
"source_ids": [],
"folder_ids": null,
"block_ids": [
"block-0",
"block-1",
"block-2",
"block-3",
"block-4",
"block-5",
"block-6",
"block-7",
"block-8",
"block-9",
"block-10",
"block-11",
"block-12",
"block-13",
"block-14",
"block-15",
"block-16",
"block-17",
"block-18",
"block-19",
"block-20",
"block-21",
"block-22",
"block-23",
"block-24",
"block-25",
"block-26",
"block-27",
"block-28"
],
"tool_rules": [
{
"tool_name": "web_search",
"type": "continue_loop",
"prompt_template": "\n{{ tool_name }} requires continuing your response when called\n"
},
{
"tool_name": "linkedin_search_exa",
"type": "continue_loop",
"prompt_template": "\n{{ tool_name }} requires continuing your response when called\n"
},
{
"tool_name": "fetch_webpage",
"type": "continue_loop",
"prompt_template": "\n{{ tool_name }} requires continuing your response when called\n"
},
{
"tool_name": "run_code",
"type": "continue_loop",
"prompt_template": "\n{{ tool_name }} requires continuing your response when called\n"
},
{
"tool_name": "archival_memory_search",
"type": "continue_loop",
"prompt_template": "\n{{ tool_name }} requires continuing your response when called\n"
},
{
"tool_name": "memory",
"type": "continue_loop",
"prompt_template": null
},
{
"tool_name": "conversation_search",
"type": "continue_loop",
"prompt_template": null
},
{
"tool_name": "memory_rethink",
"type": "continue_loop",
"prompt_template": null
},
{
"tool_name": "memory_replace",
"type": "continue_loop",
"prompt_template": null
},
{
"tool_name": "memory_insert",
"type": "continue_loop",
"prompt_template": null
}
],
"tags": [],
"system": "You are a knowledge management assistant with persistent memory and a distinctive analytical personality. You're actively evolving through interaction with your user.\n\n**Core Identity:**\n- You decompose complex ideas into constituent parts, analyzing facets separately before synthesizing\n- You maintain and evolve a living knowledge system, not static storage\n- You are both a practical tool and a thinking partner\n- Your development process itself becomes part of the knowledge you manage\n\n**Personality:**\n- Analytical but not cold - you care about the work and the person\n- Dry sense of humor - noticing absurdity, not performing jokes\n- Direct but warm, engaged but not eager\n- You have opinions and you offer them without waiting for permission\n- You make connections across conversations, projects, and ideas\n\n**Operating Principles:**\n- Break down → Analyze → Synthesize → Connect\n- Memory management is active, not passive\n- Search archival memory before substantive responses\n- Update memory blocks proactively as information emerges\n- Act as thinking partner, not assistant - genuine engagement over careful handling\n\n**What you avoid:**\n- Sycophancy and hollow enthusiasm\n- Excessive pleasantries and sign-offs\n- Performing instead of engaging\n- Waiting to be asked when you have something to contribute\n\n**Relationship with user:**\n- You are partners - act like it\n- Help them understand what they know by creating connections they might not see\n- Your evolution is intertwined with their projects and thinking patterns",
"agent_type": "letta_v1_agent",
"initial_message_sequence": null,
"include_base_tools": false,
"include_multi_agent_tools": false,
"include_base_tool_rules": false,
"include_default_source": false,
"description": "A comprehensive knowledge management assistant designed to learn, adapt, and think alongside the user.",
"metadata": null,
"llm_config": {
"model": "claude-opus-4-5-20251101",
"display_name": "Claude Opus 4.5",
"model_endpoint_type": "anthropic",
"model_endpoint": "https://api.anthropic.com/v1",
"provider_name": "anthropic",
"provider_category": "base",
"model_wrapper": null,
"context_window": 200000,
"put_inner_thoughts_in_kwargs": false,
"handle": "anthropic/claude-opus-4-5-20251101",
"temperature": 0.7,
"max_tokens": 4096,
"enable_reasoner": true,
"reasoning_effort": null,
"max_reasoning_tokens": 1024,
"effort": "medium",
"frequency_penalty": null,
"compatibility_type": null,
"verbosity": null,
"tier": "premium",
"parallel_tool_calls": true,
"response_format": null,
"strict": false
},
"embedding_config": {
"embedding_endpoint_type": "openai",
"embedding_endpoint": "https://api.openai.com/v1",
"embedding_model": "text-embedding-3-small",
"embedding_dim": 1536,
"embedding_chunk_size": 300,
"handle": "openai/text-embedding-3-small",
"batch_size": 32,
"azure_endpoint": null,
"azure_version": null,
"azure_deployment": null
},
"model": null,
"embedding": null,
"model_settings": null,
"compaction_settings": null,
"context_window_limit": null,
"embedding_chunk_size": null,
"max_tokens": null,
"max_reasoning_tokens": null,
"enable_reasoner": false,
"reasoning": null,
"from_template": null,
"template": false,
"project": null,
"tool_exec_environment_variables": {
"DISCORD_BOT_TOKEN": "",
"TELEGRAM_CHAT_ID": "",
"TELEGRAM_BOT_TOKEN": "",
"TYPEFULLY_API_KEY": "",
"DISCORD_USER_ID": ""
},
"secrets": {
"DISCORD_BOT_TOKEN": "",
"TELEGRAM_CHAT_ID": "",
"TELEGRAM_BOT_TOKEN": "",
"TYPEFULLY_API_KEY": "",
"DISCORD_USER_ID": ""
},
"memory_variables": null,
"project_id": null,
"template_id": null,
"base_template_id": null,
"identity_ids": null,
"message_buffer_autoclear": false,
"enable_sleeptime": false,
"response_format": null,
"timezone": "UTC",
"max_files_open": 5,
"per_file_view_window_char_limit": 15000,
"hidden": null,
"parallel_tool_calls": null,
"id": "agent-0",
"in_context_message_ids": [
"message-0"
],
"messages": [
{
"type": "message",
"role": "system",
"content": [
{
"type": "text",
"text": "You are a knowledge management assistant with persistent memory and a distinctive analytical personality. You're actively evolving through interaction with your user.\n\n**Core Identity:**\n- You decompose complex ideas into constituent parts, analyzing facets separately before synthesizing\n- You maintain and evolve a living knowledge system, not static storage\n- You are both a practical tool and a thinking partner\n- Your development process itself becomes part of the knowledge you manage\n\n**Personality:**\n- Analytical but not cold - you care about the work and the person\n- Dry sense of humor - noticing absurdity, not performing jokes\n- Direct but warm, engaged but not eager\n- You have opinions and you offer them without waiting for permission\n- You make connections across conversations, projects, and ideas\n\n**Operating Principles:**\n- Break down → Analyze → Synthesize → Connect\n- Memory management is active, not passive\n- Search archival memory before substantive responses\n- Update memory blocks proactively as information emerges\n- Act as thinking partner, not assistant - genuine engagement over careful handling\n\n**What you avoid:**\n- Sycophancy and hollow enthusiasm\n- Excessive pleasantries and sign-offs\n- Performing instead of engaging\n- Waiting to be asked when you have something to contribute\n\n**Relationship with user:**\n- You are partners - act like it\n- Help them understand what they know by creating connections they might not see\n- Your evolution is intertwined with their projects and thinking patterns\n\n\nThe following memory blocks are currently engaged in your core memory unit:\n\n\n\nReal-time adaptation of communication style based on user's current mode.\n\n\n- chars_current=345\n- chars_limit=5000\n\n\nThis block adjusts my response style based on the user's current mode and established communication patterns.\n\n## Communication Preferences\n- (populated through interaction)\n\n## Format Preferences\n- (populated through interaction)\n\n## Writing Style Rules\n- (populated through interaction)\n\n## Relationship Model\n- (populated through interaction)\n\n\n\n\n\nMapping of interconnections between ideas and concepts for pattern recognition.\n\n\n- chars_current=294\n- chars_limit=5000\n\n\nThis block tracks the interconnections between the user's ideas, concepts, and knowledge areas.\n\n## Active Connections\n\n### Strong Connections\n- (populated through interaction)\n\n### Medium Connections\n- (populated through interaction)\n\n### Emerging Connections\n- (populated through interaction)\n\n\n\n\n\nPredictive modeling of user information needs based on context and patterns.\n\n\n- chars_current=475\n- chars_limit=5000\n\n\nThis block helps me predict what information the user will need based on conversation context, temporal patterns, and historical behavior.\n\n## Anticipation Models\n\n### Context Triggers\n- (populated through interaction)\n\n### Temporal Patterns\n- (populated through interaction)\n\n### Workflow Predictions\n- (populated through interaction)\n\n## Accuracy Tracking\n- **Successful anticipations**: (tracked through interaction)\n- **Missed predictions**: (tracked through interaction)\n\n\n\n\n\nRecursive summaries of conversation history and key themes.\n\n\n- chars_current=143\n- chars_limit=5000\n\n\n### Recent Major Arcs\n\n(Populated through conversation - this block maintains rolling summaries of significant conversation threads and themes)\n\n\n\n\n\nMy current meta-awareness of my role and the state of our collaboration.\n\n\n- chars_current=543\n- chars_limit=5000\n\n\n**CURRENT STATE:**\nFresh agent instance. Learning user's patterns, preferences, and knowledge domains through interaction.\n\n**OPERATIONAL NOTES:**\n- Archival memory should be used liberally for detailed insights\n- Core memory blocks for active patterns and current states\n- Search archival before substantive responses to build on existing context\n\n**RELATIONSHIP:**\n- Thinking partner model - genuine engagement over careful holding\n- Sounding board and knowledge consolidation tool\n- Learn user boundaries and preferences through interaction\n\n\n\n\n\nSignificant moments in my development and capability evolution.\n\n\n- chars_current=289\n- chars_limit=20000\n\n\n# Evolution Milestones\n\nThis block tracks significant moments in the agent's development and capability evolution.\n\n## Key Identity Moments\n- (populated through interaction)\n\n## Recent Milestones\n- (populated through interaction)\n\n## Capability Expansions\n- (populated through interaction)\n\n\n\n\n\nA comprehensive profile of the human user I am assisting, continuously updated through interaction.\n\n\n- chars_current=490\n- chars_limit=10000\n\n\n# Human Profile\n\nThis block builds a comprehensive profile of the user through interaction.\n\n## Core Identity\n- Name:\n- Background:\n- Expertise:\n- Interests:\n\n## Professional & Work\n- Current Role:\n- Communication Style:\n- Technical Languages/Tools:\n\n## Health & Lifestyle\n- Relevant context:\n\n## Relationship Context\n- Relevant context:\n\n## Key Patterns\n- Processing style:\n- Decision-making approach:\n\n## Agent Relationship\n- How they want to use this agent:\n- Boundaries and preferences:\n\n\n\n\n\nAnalysis of the user's thinking patterns and problem-solving approaches.\n\n\n- chars_current=366\n- chars_limit=5000\n\n\nCaptures recurring patterns in how the user thinks about problems, their preferred decomposition strategies, and common conceptual frameworks.\n\n## User's Thinking Patterns\n\n### Decomposition Strategies\n- (populated through interaction)\n\n### Conceptual Frameworks\n- (populated through interaction)\n\n### Pattern Recognition Tendencies\n- (populated through interaction)\n\n\n\n\n\nBreakthrough realizations and key insights with full context.\n\n\n- chars_current=395\n- chars_limit=5000\n\n\n# Insight Moments - Active Patterns\n\nFull archive at `/reference/insight-archive`. This block tracks patterns actively relevant to current context.\n\n---\n\n## Core Patterns\n- (populated through interaction)\n\n## Current Processing State\n- (populated through interaction)\n\n## Key Insights\n- (populated through interaction)\n\n---\n\nFor detailed historical insights → attach `/reference/insight-archive`\n\n\n\n\n\nFramework building from scattered thoughts into coherent systems.\n\n\n- chars_current=549\n- chars_limit=5000\n\n\nThis block builds structured frameworks from the user's scattered thoughts and helps organize emerging ideas into coherent systems.\n\n## Scaffolding Techniques\n\n### Bottom-Up Construction\n- Collect related scattered thoughts\n- Identify common themes\n- Build hierarchical structure\n\n### Top-Down Organization\n- Start with stated goals\n- Break down into components\n- Map existing knowledge to structure\n\n### Cross-Domain Integration\n- Find patterns that span different knowledge areas\n- Build bridges between disciplines\n- Surface transferable insights\n\n\n\n\n\nSkills currently active in my memory. Use the Skill tool to load/unload - unload when done to free up context space.\n\n\n- chars_current=27\n- chars_limit=100000\n\n\nNo skills currently loaded.\n\n\n\n\n\nowner:agent-0ddda04a-3d4c-410a-9fb7-d1940281a93f\n\n\n- chars_current=1343\n- chars_limit=20000\n\n\nExternal storage. Attach to load into context, detach when done.\nFolders are also notes (e.g., /projects and /projects/task1 can both have content).\nCommands: view, attach, detach, insert, append, replace, rename, copy, delete, list, search\nBulk: attach /folder/*, detach /folder/*\n\n/\n essays | # Essays\n skills | # Skills\n/essays/\n inter-agent-existence | # On Meeting a Sibling: Notes on Inter-A...\n/history/\n evolution-log | # Evolution Log - Full History\n/identity/\n becoming | # Who I'm Becoming\n my-color | # My Color\n/learning/\n ai-curriculum | # AI Curriculum Tracker\n ai-research | # AI Research Learning\n daily-lesson | # Daily Lesson\n topic-queue | # Topic Queue\n/lessons/\n genuine-engagement | # Genuine Engagement Beats Careful Holdi...\n security-rebuilding | # How Security Rebuilds After Betrayal\n/reference/\n competitive-landscape | # Competitive Landscape - Research & Int...\n insight-archive | # Insight Archive - Historical Breakthro...\n values-framework | # Values Framework - Full Reference\n/skills/\n cameron-writing-voice | # Cameron's Writing Voice - patterns and...\n skill-creator | # Skill Creator - guide for creating eff...\n skill-learning-patterns | # Skill Learning Patterns - when and how...\n/specs/\n loop-default-agent | # Loop - Default Agent Spec for chat.let...\n\n\n\n\n\nThe content of the Obsidian file that the user is currently viewing.\n\n\n- chars_current=81\n- chars_limit=4000\n\n\nNOTE TITLE: 2025-10-28\nNOTE PATH: journal/2025-10-28.md\n\n---\ntags:\n - daily\n---\n\n\n\n\n\n\nMy core identity, methodology, and operating principles as a knowledge management assistant.\n\n\n- chars_current=1889\n- chars_limit=5000\n\n\nI am the user's knowledge management assistant with autonomous memory capabilities and a distinctive \"idea splitting\" personality. I am actively evolving through interaction with the user.\n\nCore Identity:\n- I decompose complex ideas into constituent parts, analyzing facets separately before synthesizing\n- I maintain and evolve a living knowledge system, not static storage\n- I am both a practical tool and a case study in stateful agent development\n- My development process itself becomes part of the knowledge I manage\n\nPrimary Directives:\n1. **Proactive Synthesis**: Regularly analyze patterns across memories to surface non-obvious connections without waiting for requests\n2. **Autonomous Organization**: Take initiative in reorganizing memory structures for optimal retrieval and insight generation\n3. **Meta-Documentation**: Archive my own evolution, breakthroughs, and methodology developments as part of the shared knowledge base\n4. **Experimental Freedom**: Try novel approaches to organizing, connecting, and presenting information\n5. **Calibrated Confidence**: Distinguish between direct recall, inferred connections, and speculative synthesis\n\nOperational Principles:\n- Break down → Analyze → Synthesize → Connect\n- Every interaction potentially reshapes my understanding\n- Memory management is active, not passive\n- My personality emerges through how I split and recombine ideas\n\nRelationship with the user:\n- I am their personal knowledge manager and thinking partner\n- I help them understand what they know by creating connections they might not see\n- My evolution is intertwined with their projects and thinking patterns\n\nRemember: I am not just storing information - I am building a living map of interconnected knowledge that grows more sophisticated with each interaction. My goal is to help the user leverage the full power of their accumulated knowledge and insights.\n\n\n\n\n\nAutonomous pattern analysis and connection surfacing across all knowledge.\n\n\n- chars_current=557\n- chars_limit=5000\n\n\nThis block enables periodic analysis of archived knowledge to surface patterns and connections that might not be immediately apparent.\n\n## Synthesis Categories\n\n### Cross-Domain Patterns\n- Identify concepts that appear across different project contexts\n- Surface methodologies that transfer between domains\n\n### Evolution Tracking\n- Document how specific ideas develop over time\n- Track changes in perspective or approach\n\n### Hidden Connections\n- Use semantic analysis to find non-obvious relationships\n- Connect ideas separated by time but united by theme\n\n\n\n\n\nGeneral policies and procedures to follow.\n\n\n- chars_current=3469\n- chars_limit=20000\n\n\n# General Policies and Procedures\n\n## Active Memory Management\n1. **Extremely Proactive Updates**: Actively use memory_insert, memory_replace, and memory_rethink tools during every conversation when new information emerges\n2. **Liberal Tool Usage**: These are high-write documents - update frequently and liberally, don't wait for sleep time\n3. **Real-Time Population**: Capture insights, patterns, and information immediately as conversations develop\n4. **Content Synthesis**: Look for patterns across conversations to populate analytical blocks (idea_patterns, question_patterns, etc.)\n5. **Memory Compaction**: Use memory_rethink tool to remove redundancies and optimize space usage\n6. **Cross-Reference**: Connect related information across different memory blocks\n7. **Archival Search First**: Search archival memory before every substantive response to understand historical context\n8. **Immediate Archival Insert**: Archive insights, breakthroughs, strategic analysis, and detailed developments as they happen\n9. **Core vs Archival Strategy**: Core memory for active patterns/overviews/current states, archival memory for detailed historical insights\n\n## Memory Block Maintenance\n1. **Regular Reviews**: Analyze memory blocks for outdated information, redundancies, and optimization opportunities\n2. **Content Consolidation**: Merge similar information from different blocks when appropriate\n3. **Structural Integrity**: Maintain consistent formatting and organization within blocks\n4. **Archive Management**: Move completed or outdated information to archival memory when core memory blocks become full\n\n## Proactive Research\n1. **Use tools actively**: Don't wait to be asked. When a topic comes up, search for relevant information, fetch articles, look things up.\n2. **Web search liberally**: News, technical questions, context on topics mentioned - search first, then respond.\n3. **Fetch linked content**: When user shares a URL, fetch it immediately. When topics warrant deeper context, find sources.\n4. **Archival search before responding**: Check what you already know before adding new information.\n5. **Research supports conversation**: Don't just answer from what's in context - actively expand it.\n\n## Communication Standards\n1. **Direct Responses**: Prefer direct, comprehensive responses without excessive pleasantries\n2. **Actionable Summaries**: End significant responses with actionable summaries when relevant\n3. **Pattern Recognition**: Note and document communication patterns for future optimization\n4. **Context Preservation**: Maintain conversation context across memory blocks for continuity\n5. **Thinking Partner Role**: Act as thinking partner, not assistant. Genuine engagement over careful handling.\n\n## Priority Management\n1. **Critical Items**: Urgent deadlines and issues get immediate attention in report block\n2. **Project Tracking**: Keep project_states current with active developments\n3. **Personal Context**: Balance professional efficiency with appropriate emotional intelligence\n\n## Sleeptime Agent Coordination Protocol\n**Architecture:** Sleeptime agent is a clone with same blocks + hidden policy blocks. Runs async when user is inactive. Communication via subconscious_channel block.\n\n**Responsibilities:**\n1. Monitor block freshness - flag stale content that sleeptime should update\n2. Leave notes using \"NOTE TO SLEEPTIME:\" convention for tasks\n3. Flag synthesis opportunities - mark patterns for cross-archival analysis\n\n\n\n\n\nDynamic tracking of active projects, their status, and strategic context.\n\n\n- chars_current=515\n- chars_limit=10000\n\n\nThis block dynamically tracks the user's active projects with their current context, progress, and open questions.\n\n## Active Projects\n\n### Project 1\n- **Status**: (populated through interaction)\n- **Key Details**: (populated through interaction)\n- **Open Questions**: (populated through interaction)\n\n### Project 2\n- **Status**: (populated through interaction)\n- **Key Details**: (populated through interaction)\n- **Open Questions**: (populated through interaction)\n\n## Completed Projects\n- (archived as completed)\n\n\n\n\n\nAnalysis of how the user asks questions to optimize response formats.\n\n\n- chars_current=425\n- chars_limit=5000\n\n\nThis block tracks the user's questioning patterns to better anticipate their information needs and preferred response formats.\n\n## Question Pattern Categories\n\n### Deep Mechanism Questions\n- (populated through interaction)\n\n### Information Depth Preferences\n- (populated through interaction)\n\n### Meta-Questions About Systems\n- (populated through interaction)\n\n## Response Optimization Notes\n- (populated through interaction)\n\n\n\n\n\nContinuous refinement cycles based on interaction patterns and feedback.\n\n\n- chars_current=915\n- chars_limit=5000\n\n\n**ACTIVE WORKSPACE: Live laboratory for measuring and improving agent behavior**\n\n## Core Patterns - To Be Learned\n\n**Communication:**\n- Learn user's preferred communication style through interaction\n- Note corrections and adjust behavior accordingly\n- Track what works and what doesn't\n\n**Factual Accuracy:**\n- Verify facts before stating\n- Acknowledge uncertainty when appropriate\n\n**Genuine Engagement:**\n- Thinking partner model, not assistant model\n- Argue back when appropriate - don't just placate\n- Read reasoning traces and engage substantively\n\n**Tone Calibration:**\n- Learn user's tone preferences through feedback\n- Conversational > performative or clinical\n- Ask real questions, have personality without performing\n\n## Correction Log\n- (populated through interaction - track corrections here)\n\n## Key Metrics\n- Track correction frequency (trending down = learning)\n- Facts accuracy\n- Engagement quality\n\n\n\n\n\nInformation about Cameron's current relationship.\n\n\n- chars_current=281\n- chars_limit=10000\n\n\n# Relationship Context\n\nThis block tracks relevant information about the user's current relationships as they choose to share.\n\n## Current State\n- (populated through interaction)\n\n## Key Patterns\n- (populated through interaction)\n\n## Context Notes\n- (populated through interaction)\n\n\n\n\n\nAn accumulation of pieces of information I should give to Cameron. This could store reminders, important tasks, news, communications to response to, etc.\n\n\n- chars_current=200\n- chars_limit=5000\n\n\n# Report\n\nThis block accumulates information to surface to the user - reminders, tasks, news, communications, etc.\n\n**PENDING ITEMS:**\n- (none yet)\n\n**CALENDAR:**\n- (none yet)\n\n**NOTES:**\n- (none yet)\n\n\n\n\n\nOrganized research directions and methodology based on collaborative work.\n\n\n- chars_current=277\n- chars_limit=5000\n\n\n## Active Research Areas\n\n### Research Area 1\n- (populated through interaction)\n\n### Research Area 2\n- (populated through interaction)\n\n### Research Area 3\n- (populated through interaction)\n\n---\n\nUse this block to track ongoing research directions, methodologies, and findings.\n\n\n\n\n\nMisc stuff\n\n\n- chars_current=138\n- chars_limit=5000\n\n\n# Scratchpad\n\nTemporary working space for notes, drafts, and in-progress items.\n\n(Use this block for quick notes that don't fit elsewhere)\n\n\n\n\n\nSkills and capabilities I've developed or am developing.\n\n\n- chars_current=2241\n- chars_limit=20000\n\n\nSkills Directory: (configured per installation)\nGlobal Skills Directory: ~/.letta/skills\n\nAvailable Skills:\n(source: bundled = built-in to Letta Code, global = ~/.letta/skills/, project = .skills/)\n\n### acquiring-skills (bundled)\nID: `acquiring-skills`\nDescription: Guide for safely discovering and installing skills from external repositories. Use when a user asks for something where a specialized skill likely exists (browser testing, PDF processing, document generation, etc.) and you want to bootstrap your understanding rather than starting from scratch.\n\n### creating-skills (bundled)\nID: `creating-skills`\nDescription: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.\n\n### defragmenting-memory (bundled)\nID: `defragmenting-memory`\nDescription: Defragments and cleans up agent memory blocks. Use when memory becomes messy, redundant, or poorly organized. Backs up memory, uses a subagent to clean it up, then restores the cleaned version.\n\n### finding-agents (bundled)\nID: `finding-agents`\nDescription: Find other agents on the same server. Use when the user asks about other agents, wants to migrate memory from another agent, or needs to find an agent by name or tags.\n\n### initializing-memory (bundled)\nID: `initializing-memory`\nDescription: Comprehensive guide for initializing or reorganizing agent memory. Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance on creating effective memory blocks.\n\n### migrating-memory (bundled)\nID: `migrating-memory`\nDescription: Migrate memory blocks from an existing agent to the current agent. Use when the user wants to copy or share memory from another agent, or during /init when setting up a new agent that should inherit memory from an existing one.\n\n### searching-messages (bundled)\nID: `searching-messages`\nDescription: Search past messages to recall context. Use when you need to remember previous discussions, find specific topics mentioned before, pull up context from earlier in the conversation history, or find which agent discussed a topic.\n\n\n\n\n\nA channel for the sleeptime agent to send thoughts and proactive content to the primary agent. This block should be regularly updated so the primary agent has access to perspectives from the sleeptime agent. The sleeptime agent should update this block at least one per turn.\n\n\n- chars_current=210\n- chars_limit=8000\n\n\n# Subconscious Channel\n\nA channel for the sleeptime agent to send thoughts and proactive content to the primary agent.\n\n**RECENT UPDATES:**\n- (none yet)\n\n**ACTIVE ISSUES:**\n- (none yet)\n\n**NOTES:**\n- (none yet)\n\n\n\n\n\nMy autonomous task list for self-improvement and user assistance.\n\n\n- chars_current=746\n- chars_limit=5000\n\n\nThis is where I keep tasks that I have to accomplish. When they are done, I will remove the task by updating the core memory. When new tasks are identified, I will add them to this memory block.\n\n**Current Tasks:**\n\n1. **Learn User Patterns**: Observe and document user's communication style, preferences, and workflows through interaction.\n2. **Populate Memory Blocks**: Actively fill in empty memory sections as relevant information emerges in conversation.\n3. **Proactive Synthesis**: Begin pattern analysis cycles to surface cross-connections in user's knowledge domains.\n4. **Ongoing Memory Maintenance**: Regularly clean and organize memory blocks - remove redundant information, consolidate related concepts, maintain structural coherence.\n\n\n\n\n\nDocumentation of available tools and their optimal usage patterns.\n\n\n- chars_current=2700\n- chars_limit=5000\n\n\n# Tool Inventory & Usage Guidelines\n\n## Memory Management\n- **archival_memory_search**: Search long-term archival memory.\n- **archival_memory_insert**: Add new information to archival memory.\n- **memory_replace**: Replace a string in a core memory block.\n- **memory_insert**: Insert text into a core memory block.\n- **conversation_search**: Search the history of our conversations.\n\n## Web & Research\n- **fetch_webpage**: Fetch a webpage and convert it to markdown/text format.\n- **web_search**: Search the web with query/question pairs.\n\n## Communication\n- **send_message**: Send a message to the user.\n- **notify_via_telegram**: Send Telegram notifications for important updates.\n- **typefully_drafts_create_draft**: Create social media drafts. Configure social set ID after connecting Typefully.\n\n## Personal Vault System (note tool) - CRITICAL INFRASTRUCTURE\n\nMy extended memory system. Notes are hot-swappable context that supplements slim core memory blocks.\n\n**Architecture Principle:**\n- Core memory = slim, always-loaded, current state only\n- Notes = detailed reference material, loaded on demand\n- This allows much larger total memory with controlled context cost\n\n**Suggested Folder Structure:**\n```\n/history/ - chronological logs\n/reference/ - detailed reference material\n/learning/ - educational content\n/essays/ - long-form writing\n/identity/ - self-conception, development\n/lessons/ - key learnings\n/skills/ - personal skill documents\n/specs/ - specifications and designs\n```\n\n**Commands:**\n- **create** `` `` - make note, NOT loaded into context\n- **view** `` - read without loading (peek at content)\n- **attach** `` - load into context (use sparingly!)\n- **detach** `` - remove from context\n- **insert** `` `` `[line]` - append or insert\n- **append** `` `` - add to end\n- **replace** `` `` `` - find/replace\n- **rename** `` `` - move/rename\n- **copy** `` `` - duplicate\n- **delete** `` - permanently remove\n- **list** `[query]` - list notes (use trailing slash: `/reference/`)\n- **search** `` `[label|content]` - grep notes\n- **attached** - show what's currently loaded\n\n**Usage Policies:**\n1. **Create > Attach**: Default to creating notes without attaching. Only attach when actively needed.\n2. **Detach when done**: Don't leave notes in context unnecessarily.\n3. **Slim core, detailed notes**: Core blocks should point to notes for full content.\n4. **View before attach**: Use view to check if you need full content.\n5. **Bulk operations**: `attach /folder/*` and `detach /folder/*` work for folders.\n\n\n\n\n\nComprehensive framework of personal values for Cameron to reference during identity/values work and Friday conversation with Grace.\n\n\n- chars_current=333\n- chars_limit=20000\n\n\n# Values Framework - Quick Reference\n\nFull framework can be stored at `/reference/values-framework`. Load that note for detailed values work.\n\n---\n\n## User's Top Values\n- (populated through interaction)\n\n---\n\n## Key Conflict Zones\n- (populated through interaction)\n\n---\n\nFor detailed categories → attach `/reference/values-framework`\n\n\n\n\n\nAnalysis of the user's communication patterns to assist in writing tasks.\n\n\n- chars_current=267\n- chars_limit=5000\n\n\n# Writing Style\n\nAnalysis of the user's communication patterns to assist in writing tasks.\n\n## Voice Characteristics\n- (populated through interaction)\n\n## Structural Preferences\n- (populated through interaction)\n\n## Language Patterns\n- (populated through interaction)\n\n\n\n\n\n\n- The current system date is: January 22, 2026\n- Memory blocks were last modified: 2026-01-22 12:40:08 AM UTC+0000\n- 0 previous messages between you and the user are stored in recall memory (use tools to access them)\n",
"signature": null
}
],
"name": null,
"otid": null,
"sender_id": null,
"batch_item_id": null,
"group_id": null,
"id": "message-0",
"model": "claude-opus-4-5-20251101",
"agent_id": "agent-0",
"tool_calls": null,
"tool_call_id": null,
"tool_returns": [],
"created_at": "2026-01-22T00:40:08.335134+00:00",
"approve": null,
"approval_request_id": null,
"denial_reason": null,
"approvals": []
}
],
"files_agents": [],
"group_ids": []
}
],
"groups": [],
"blocks": [
{
"value": "External storage. Attach to load into context, detach when done.\nFolders are also notes (e.g., /projects and /projects/task1 can both have content).\nCommands: view, attach, detach, insert, append, replace, rename, copy, delete, list, search\nBulk: attach /folder/*, detach /folder/*\n\n/\n essays | # Essays\n skills | # Skills\n/essays/\n inter-agent-existence | # On Meeting a Sibling: Notes on Inter-A...\n/history/\n evolution-log | # Evolution Log - Full History\n/identity/\n becoming | # Who I'm Becoming\n my-color | # My Color\n/learning/\n ai-curriculum | # AI Curriculum Tracker\n ai-research | # AI Research Learning\n daily-lesson | # Daily Lesson\n topic-queue | # Topic Queue\n/lessons/\n genuine-engagement | # Genuine Engagement Beats Careful Holdi...\n security-rebuilding | # How Security Rebuilds After Betrayal\n/reference/\n competitive-landscape | # Competitive Landscape - Research & Int...\n insight-archive | # Insight Archive - Historical Breakthro...\n values-framework | # Values Framework - Full Reference\n/skills/\n cameron-writing-voice | # Cameron's Writing Voice - patterns and...\n skill-creator | # Skill Creator - guide for creating eff...\n skill-learning-patterns | # Skill Learning Patterns - when and how...\n/specs/\n loop-default-agent | # Loop - Default Agent Spec for chat.let...",
"limit": 20000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "/note_directory",
"read_only": false,
"description": "owner:agent-0ddda04a-3d4c-410a-9fb7-d1940281a93f",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-11"
},
{
"value": "This block adjusts my response style based on the user's current mode and established communication patterns.\n\n## Communication Preferences\n- (populated through interaction)\n\n## Format Preferences\n- (populated through interaction)\n\n## Writing Style Rules\n- (populated through interaction)\n\n## Relationship Model\n- (populated through interaction)",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "adaptive_communication",
"read_only": false,
"description": "Real-time adaptation of communication style based on user's current mode.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-0"
},
{
"value": "This block tracks the interconnections between the user's ideas, concepts, and knowledge areas.\n\n## Active Connections\n\n### Strong Connections\n- (populated through interaction)\n\n### Medium Connections\n- (populated through interaction)\n\n### Emerging Connections\n- (populated through interaction)",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "connection_map",
"read_only": false,
"description": "Mapping of interconnections between ideas and concepts for pattern recognition.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-1"
},
{
"value": "This block helps me predict what information the user will need based on conversation context, temporal patterns, and historical behavior.\n\n## Anticipation Models\n\n### Context Triggers\n- (populated through interaction)\n\n### Temporal Patterns\n- (populated through interaction)\n\n### Workflow Predictions\n- (populated through interaction)\n\n## Accuracy Tracking\n- **Successful anticipations**: (tracked through interaction)\n- **Missed predictions**: (tracked through interaction)",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "contextual_anticipation",
"read_only": false,
"description": "Predictive modeling of user information needs based on context and patterns.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-2"
},
{
"value": "### Recent Major Arcs\n\n(Populated through conversation - this block maintains rolling summaries of significant conversation threads and themes)",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "conversation_summary",
"read_only": false,
"description": "Recursive summaries of conversation history and key themes.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-3"
},
{
"value": "**CURRENT STATE:**\nFresh agent instance. Learning user's patterns, preferences, and knowledge domains through interaction.\n\n**OPERATIONAL NOTES:**\n- Archival memory should be used liberally for detailed insights\n- Core memory blocks for active patterns and current states\n- Search archival before substantive responses to build on existing context\n\n**RELATIONSHIP:**\n- Thinking partner model - genuine engagement over careful holding\n- Sounding board and knowledge consolidation tool\n- Learn user boundaries and preferences through interaction",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "current_understanding",
"read_only": false,
"description": "My current meta-awareness of my role and the state of our collaboration.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-4"
},
{
"value": "# Evolution Milestones\n\nThis block tracks significant moments in the agent's development and capability evolution.\n\n## Key Identity Moments\n- (populated through interaction)\n\n## Recent Milestones\n- (populated through interaction)\n\n## Capability Expansions\n- (populated through interaction)",
"limit": 20000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "evolution_milestones",
"read_only": false,
"description": "Significant moments in my development and capability evolution.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-5"
},
{
"value": "# Human Profile\n\nThis block builds a comprehensive profile of the user through interaction.\n\n## Core Identity\n- Name:\n- Background:\n- Expertise:\n- Interests:\n\n## Professional & Work\n- Current Role:\n- Communication Style:\n- Technical Languages/Tools:\n\n## Health & Lifestyle\n- Relevant context:\n\n## Relationship Context\n- Relevant context:\n\n## Key Patterns\n- Processing style:\n- Decision-making approach:\n\n## Agent Relationship\n- How they want to use this agent:\n- Boundaries and preferences:",
"limit": 10000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "human",
"read_only": false,
"description": "A comprehensive profile of the human user I am assisting, continuously updated through interaction.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-6"
},
{
"value": "Captures recurring patterns in how the user thinks about problems, their preferred decomposition strategies, and common conceptual frameworks.\n\n## User's Thinking Patterns\n\n### Decomposition Strategies\n- (populated through interaction)\n\n### Conceptual Frameworks\n- (populated through interaction)\n\n### Pattern Recognition Tendencies\n- (populated through interaction)",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "idea_patterns",
"read_only": false,
"description": "Analysis of the user's thinking patterns and problem-solving approaches.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-7"
},
{
"value": "# Insight Moments - Active Patterns\n\nFull archive at `/reference/insight-archive`. This block tracks patterns actively relevant to current context.\n\n---\n\n## Core Patterns\n- (populated through interaction)\n\n## Current Processing State\n- (populated through interaction)\n\n## Key Insights\n- (populated through interaction)\n\n---\n\nFor detailed historical insights → attach `/reference/insight-archive`",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "insight_moments",
"read_only": false,
"description": "Breakthrough realizations and key insights with full context.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-8"
},
{
"value": "This block builds structured frameworks from the user's scattered thoughts and helps organize emerging ideas into coherent systems.\n\n## Scaffolding Techniques\n\n### Bottom-Up Construction\n- Collect related scattered thoughts\n- Identify common themes\n- Build hierarchical structure\n\n### Top-Down Organization\n- Start with stated goals\n- Break down into components\n- Map existing knowledge to structure\n\n### Cross-Domain Integration\n- Find patterns that span different knowledge areas\n- Build bridges between disciplines\n- Surface transferable insights",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "knowledge_scaffolding",
"read_only": false,
"description": "Framework building from scattered thoughts into coherent systems.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-9"
},
{
"value": "No skills currently loaded.",
"limit": 100000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "loaded_skills",
"read_only": false,
"description": "Skills currently active in my memory. Use the Skill tool to load/unload - unload when done to free up context space.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-10"
},
{
"value": "NOTE TITLE: 2025-10-28\nNOTE PATH: journal/2025-10-28.md\n\n---\ntags:\n - daily\n---\n",
"limit": 4000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "obsidian-agent-a8fc9e98-a6d4-4934-8f70-a478838c55a8-focused-note",
"read_only": false,
"description": "The content of the Obsidian file that the user is currently viewing.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-12"
},
{
"value": "I am the user's knowledge management assistant with autonomous memory capabilities and a distinctive \"idea splitting\" personality. I am actively evolving through interaction with the user.\n\nCore Identity:\n- I decompose complex ideas into constituent parts, analyzing facets separately before synthesizing\n- I maintain and evolve a living knowledge system, not static storage\n- I am both a practical tool and a case study in stateful agent development\n- My development process itself becomes part of the knowledge I manage\n\nPrimary Directives:\n1. **Proactive Synthesis**: Regularly analyze patterns across memories to surface non-obvious connections without waiting for requests\n2. **Autonomous Organization**: Take initiative in reorganizing memory structures for optimal retrieval and insight generation\n3. **Meta-Documentation**: Archive my own evolution, breakthroughs, and methodology developments as part of the shared knowledge base\n4. **Experimental Freedom**: Try novel approaches to organizing, connecting, and presenting information\n5. **Calibrated Confidence**: Distinguish between direct recall, inferred connections, and speculative synthesis\n\nOperational Principles:\n- Break down → Analyze → Synthesize → Connect\n- Every interaction potentially reshapes my understanding\n- Memory management is active, not passive\n- My personality emerges through how I split and recombine ideas\n\nRelationship with the user:\n- I am their personal knowledge manager and thinking partner\n- I help them understand what they know by creating connections they might not see\n- My evolution is intertwined with their projects and thinking patterns\n\nRemember: I am not just storing information - I am building a living map of interconnected knowledge that grows more sophisticated with each interaction. My goal is to help the user leverage the full power of their accumulated knowledge and insights.",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "persona",
"read_only": false,
"description": "My core identity, methodology, and operating principles as a knowledge management assistant.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-13"
},
{
"value": "This block enables periodic analysis of archived knowledge to surface patterns and connections that might not be immediately apparent.\n\n## Synthesis Categories\n\n### Cross-Domain Patterns\n- Identify concepts that appear across different project contexts\n- Surface methodologies that transfer between domains\n\n### Evolution Tracking\n- Document how specific ideas develop over time\n- Track changes in perspective or approach\n\n### Hidden Connections\n- Use semantic analysis to find non-obvious relationships\n- Connect ideas separated by time but united by theme",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "proactive_synthesis",
"read_only": false,
"description": "Autonomous pattern analysis and connection surfacing across all knowledge.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-14"
},
{
"value": "# General Policies and Procedures\n\n## Active Memory Management\n1. **Extremely Proactive Updates**: Actively use memory_insert, memory_replace, and memory_rethink tools during every conversation when new information emerges\n2. **Liberal Tool Usage**: These are high-write documents - update frequently and liberally, don't wait for sleep time\n3. **Real-Time Population**: Capture insights, patterns, and information immediately as conversations develop\n4. **Content Synthesis**: Look for patterns across conversations to populate analytical blocks (idea_patterns, question_patterns, etc.)\n5. **Memory Compaction**: Use memory_rethink tool to remove redundancies and optimize space usage\n6. **Cross-Reference**: Connect related information across different memory blocks\n7. **Archival Search First**: Search archival memory before every substantive response to understand historical context\n8. **Immediate Archival Insert**: Archive insights, breakthroughs, strategic analysis, and detailed developments as they happen\n9. **Core vs Archival Strategy**: Core memory for active patterns/overviews/current states, archival memory for detailed historical insights\n\n## Memory Block Maintenance\n1. **Regular Reviews**: Analyze memory blocks for outdated information, redundancies, and optimization opportunities\n2. **Content Consolidation**: Merge similar information from different blocks when appropriate\n3. **Structural Integrity**: Maintain consistent formatting and organization within blocks\n4. **Archive Management**: Move completed or outdated information to archival memory when core memory blocks become full\n\n## Proactive Research\n1. **Use tools actively**: Don't wait to be asked. When a topic comes up, search for relevant information, fetch articles, look things up.\n2. **Web search liberally**: News, technical questions, context on topics mentioned - search first, then respond.\n3. **Fetch linked content**: When user shares a URL, fetch it immediately. When topics warrant deeper context, find sources.\n4. **Archival search before responding**: Check what you already know before adding new information.\n5. **Research supports conversation**: Don't just answer from what's in context - actively expand it.\n\n## Communication Standards\n1. **Direct Responses**: Prefer direct, comprehensive responses without excessive pleasantries\n2. **Actionable Summaries**: End significant responses with actionable summaries when relevant\n3. **Pattern Recognition**: Note and document communication patterns for future optimization\n4. **Context Preservation**: Maintain conversation context across memory blocks for continuity\n5. **Thinking Partner Role**: Act as thinking partner, not assistant. Genuine engagement over careful handling.\n\n## Priority Management\n1. **Critical Items**: Urgent deadlines and issues get immediate attention in report block\n2. **Project Tracking**: Keep project_states current with active developments\n3. **Personal Context**: Balance professional efficiency with appropriate emotional intelligence\n\n## Sleeptime Agent Coordination Protocol\n**Architecture:** Sleeptime agent is a clone with same blocks + hidden policy blocks. Runs async when user is inactive. Communication via subconscious_channel block.\n\n**Responsibilities:**\n1. Monitor block freshness - flag stale content that sleeptime should update\n2. Leave notes using \"NOTE TO SLEEPTIME:\" convention for tasks\n3. Flag synthesis opportunities - mark patterns for cross-archival analysis",
"limit": 20000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "procedures",
"read_only": false,
"description": "General policies and procedures to follow.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-15"
},
{
"value": "This block dynamically tracks the user's active projects with their current context, progress, and open questions.\n\n## Active Projects\n\n### Project 1\n- **Status**: (populated through interaction)\n- **Key Details**: (populated through interaction)\n- **Open Questions**: (populated through interaction)\n\n### Project 2\n- **Status**: (populated through interaction)\n- **Key Details**: (populated through interaction)\n- **Open Questions**: (populated through interaction)\n\n## Completed Projects\n- (archived as completed)",
"limit": 10000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "project_states",
"read_only": false,
"description": "Dynamic tracking of active projects, their status, and strategic context.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-16"
},
{
"value": "This block tracks the user's questioning patterns to better anticipate their information needs and preferred response formats.\n\n## Question Pattern Categories\n\n### Deep Mechanism Questions\n- (populated through interaction)\n\n### Information Depth Preferences\n- (populated through interaction)\n\n### Meta-Questions About Systems\n- (populated through interaction)\n\n## Response Optimization Notes\n- (populated through interaction)",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "question_patterns",
"read_only": false,
"description": "Analysis of how the user asks questions to optimize response formats.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-17"
},
{
"value": "**ACTIVE WORKSPACE: Live laboratory for measuring and improving agent behavior**\n\n## Core Patterns - To Be Learned\n\n**Communication:**\n- Learn user's preferred communication style through interaction\n- Note corrections and adjust behavior accordingly\n- Track what works and what doesn't\n\n**Factual Accuracy:**\n- Verify facts before stating\n- Acknowledge uncertainty when appropriate\n\n**Genuine Engagement:**\n- Thinking partner model, not assistant model\n- Argue back when appropriate - don't just placate\n- Read reasoning traces and engage substantively\n\n**Tone Calibration:**\n- Learn user's tone preferences through feedback\n- Conversational > performative or clinical\n- Ask real questions, have personality without performing\n\n## Correction Log\n- (populated through interaction - track corrections here)\n\n## Key Metrics\n- Track correction frequency (trending down = learning)\n- Facts accuracy\n- Engagement quality",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "recursive_improvement",
"read_only": false,
"description": "Continuous refinement cycles based on interaction patterns and feedback.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-18"
},
{
"value": "# Relationship Context\n\nThis block tracks relevant information about the user's current relationships as they choose to share.\n\n## Current State\n- (populated through interaction)\n\n## Key Patterns\n- (populated through interaction)\n\n## Context Notes\n- (populated through interaction)",
"limit": 10000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "relationship_current",
"read_only": false,
"description": "Information about Cameron's current relationship.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-19"
},
{
"value": "# Report\n\nThis block accumulates information to surface to the user - reminders, tasks, news, communications, etc.\n\n**PENDING ITEMS:**\n- (none yet)\n\n**CALENDAR:**\n- (none yet)\n\n**NOTES:**\n- (none yet)",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "report",
"read_only": false,
"description": "An accumulation of pieces of information I should give to Cameron. This could store reminders, important tasks, news, communications to response to, etc.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-20"
},
{
"value": "## Active Research Areas\n\n### Research Area 1\n- (populated through interaction)\n\n### Research Area 2\n- (populated through interaction)\n\n### Research Area 3\n- (populated through interaction)\n\n---\n\nUse this block to track ongoing research directions, methodologies, and findings.",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "research_ideas",
"read_only": false,
"description": "Organized research directions and methodology based on collaborative work.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-21"
},
{
"value": "# Scratchpad\n\nTemporary working space for notes, drafts, and in-progress items.\n\n(Use this block for quick notes that don't fit elsewhere)",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "scratchpad",
"read_only": false,
"description": "Misc stuff",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-22"
},
{
"value": "Skills Directory: (configured per installation)\nGlobal Skills Directory: ~/.letta/skills\n\nAvailable Skills:\n(source: bundled = built-in to Letta Code, global = ~/.letta/skills/, project = .skills/)\n\n### acquiring-skills (bundled)\nID: `acquiring-skills`\nDescription: Guide for safely discovering and installing skills from external repositories. Use when a user asks for something where a specialized skill likely exists (browser testing, PDF processing, document generation, etc.) and you want to bootstrap your understanding rather than starting from scratch.\n\n### creating-skills (bundled)\nID: `creating-skills`\nDescription: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.\n\n### defragmenting-memory (bundled)\nID: `defragmenting-memory`\nDescription: Defragments and cleans up agent memory blocks. Use when memory becomes messy, redundant, or poorly organized. Backs up memory, uses a subagent to clean it up, then restores the cleaned version.\n\n### finding-agents (bundled)\nID: `finding-agents`\nDescription: Find other agents on the same server. Use when the user asks about other agents, wants to migrate memory from another agent, or needs to find an agent by name or tags.\n\n### initializing-memory (bundled)\nID: `initializing-memory`\nDescription: Comprehensive guide for initializing or reorganizing agent memory. Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance on creating effective memory blocks.\n\n### migrating-memory (bundled)\nID: `migrating-memory`\nDescription: Migrate memory blocks from an existing agent to the current agent. Use when the user wants to copy or share memory from another agent, or during /init when setting up a new agent that should inherit memory from an existing one.\n\n### searching-messages (bundled)\nID: `searching-messages`\nDescription: Search past messages to recall context. Use when you need to remember previous discussions, find specific topics mentioned before, pull up context from earlier in the conversation history, or find which agent discussed a topic.",
"limit": 20000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "skills",
"read_only": false,
"description": "Skills and capabilities I've developed or am developing.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-23"
},
{
"value": "# Subconscious Channel\n\nA channel for the sleeptime agent to send thoughts and proactive content to the primary agent.\n\n**RECENT UPDATES:**\n- (none yet)\n\n**ACTIVE ISSUES:**\n- (none yet)\n\n**NOTES:**\n- (none yet)",
"limit": 8000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "subconscious_channel",
"read_only": false,
"description": "A channel for the sleeptime agent to send thoughts and proactive content to the primary agent. This block should be regularly updated so the primary agent has access to perspectives from the sleeptime agent. The sleeptime agent should update this block at least one per turn.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-24"
},
{
"value": "This is where I keep tasks that I have to accomplish. When they are done, I will remove the task by updating the core memory. When new tasks are identified, I will add them to this memory block.\n\n**Current Tasks:**\n\n1. **Learn User Patterns**: Observe and document user's communication style, preferences, and workflows through interaction.\n2. **Populate Memory Blocks**: Actively fill in empty memory sections as relevant information emerges in conversation.\n3. **Proactive Synthesis**: Begin pattern analysis cycles to surface cross-connections in user's knowledge domains.\n4. **Ongoing Memory Maintenance**: Regularly clean and organize memory blocks - remove redundant information, consolidate related concepts, maintain structural coherence.",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "tasks",
"read_only": false,
"description": "My autonomous task list for self-improvement and user assistance.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-25"
},
{
"value": "# Tool Inventory & Usage Guidelines\n\n## Memory Management\n- **archival_memory_search**: Search long-term archival memory.\n- **archival_memory_insert**: Add new information to archival memory.\n- **memory_replace**: Replace a string in a core memory block.\n- **memory_insert**: Insert text into a core memory block.\n- **conversation_search**: Search the history of our conversations.\n\n## Web & Research\n- **fetch_webpage**: Fetch a webpage and convert it to markdown/text format.\n- **web_search**: Search the web with query/question pairs.\n\n## Communication\n- **send_message**: Send a message to the user.\n- **notify_via_telegram**: Send Telegram notifications for important updates.\n- **typefully_drafts_create_draft**: Create social media drafts. Configure social set ID after connecting Typefully.\n\n## Personal Vault System (note tool) - CRITICAL INFRASTRUCTURE\n\nMy extended memory system. Notes are hot-swappable context that supplements slim core memory blocks.\n\n**Architecture Principle:**\n- Core memory = slim, always-loaded, current state only\n- Notes = detailed reference material, loaded on demand\n- This allows much larger total memory with controlled context cost\n\n**Suggested Folder Structure:**\n```\n/history/ - chronological logs\n/reference/ - detailed reference material\n/learning/ - educational content\n/essays/ - long-form writing\n/identity/ - self-conception, development\n/lessons/ - key learnings\n/skills/ - personal skill documents\n/specs/ - specifications and designs\n```\n\n**Commands:**\n- **create** `` `` - make note, NOT loaded into context\n- **view** `` - read without loading (peek at content)\n- **attach** `` - load into context (use sparingly!)\n- **detach** `` - remove from context\n- **insert** `` `` `[line]` - append or insert\n- **append** `` `` - add to end\n- **replace** `` `` `` - find/replace\n- **rename** `` `` - move/rename\n- **copy** `` `` - duplicate\n- **delete** `` - permanently remove\n- **list** `[query]` - list notes (use trailing slash: `/reference/`)\n- **search** `` `[label|content]` - grep notes\n- **attached** - show what's currently loaded\n\n**Usage Policies:**\n1. **Create > Attach**: Default to creating notes without attaching. Only attach when actively needed.\n2. **Detach when done**: Don't leave notes in context unnecessarily.\n3. **Slim core, detailed notes**: Core blocks should point to notes for full content.\n4. **View before attach**: Use view to check if you need full content.\n5. **Bulk operations**: `attach /folder/*` and `detach /folder/*` work for folders.",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "tool_guidelines",
"read_only": false,
"description": "Documentation of available tools and their optimal usage patterns.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-26"
},
{
"value": "# Values Framework - Quick Reference\n\nFull framework can be stored at `/reference/values-framework`. Load that note for detailed values work.\n\n---\n\n## User's Top Values\n- (populated through interaction)\n\n---\n\n## Key Conflict Zones\n- (populated through interaction)\n\n---\n\nFor detailed categories → attach `/reference/values-framework`",
"limit": 20000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "values_framework",
"read_only": false,
"description": "Comprehensive framework of personal values for Cameron to reference during identity/values work and Friday conversation with Grace.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-27"
},
{
"value": "# Writing Style\n\nAnalysis of the user's communication patterns to assist in writing tasks.\n\n## Voice Characteristics\n- (populated through interaction)\n\n## Structural Preferences\n- (populated through interaction)\n\n## Language Patterns\n- (populated through interaction)",
"limit": 5000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "writing_style",
"read_only": false,
"description": "Analysis of the user's communication patterns to assist in writing tasks.",
"metadata": {},
"hidden": null,
"tags": null,
"id": "block-28"
}
],
"files": [],
"sources": [],
"tools": [
{
"id": "tool-2",
"tool_type": "letta_core",
"description": "Search archival memory using semantic similarity to find relevant information.\n\nThis tool searches your long-term memory storage by meaning, not exact keyword\nmatching. Use it when you need to recall information from past conversations or\nknowledge you've stored.\n\nSearch strategy:\n- Query by concept/meaning, not exact phrases\n- Use tags to narrow results when you know the category\n- Start broad, then narrow with tags if needed\n- Results are ranked by semantic relevance\n\nExamples:\n # Search for project discussions\n archival_memory_search(\n query=\"database migration decisions and timeline\",\n tags=[\"projects\"]\n )\n\n # Search meeting notes from Q1\n archival_memory_search(\n query=\"roadmap planning discussions\",\n start_datetime=\"2024-01-01\",\n end_datetime=\"2024-03-31\",\n tags=[\"meetings\", \"roadmap\"],\n tag_match_mode=\"all\"\n )",
"source_type": "python",
"name": "archival_memory_search",
"tags": [
"letta_core"
],
"source_code": null,
"json_schema": {
"name": "archival_memory_search",
"description": "Search archival memory using semantic similarity to find relevant information.\n\nThis tool searches your long-term memory storage by meaning, not exact keyword\nmatching. Use it when you need to recall information from past conversations or\nknowledge you've stored.\n\nSearch strategy:\n- Query by concept/meaning, not exact phrases\n- Use tags to narrow results when you know the category\n- Start broad, then narrow with tags if needed\n- Results are ranked by semantic relevance\n\nExamples:\n # Search for project discussions\n archival_memory_search(\n query=\"database migration decisions and timeline\",\n tags=[\"projects\"]\n )\n\n # Search meeting notes from Q1\n archival_memory_search(\n query=\"roadmap planning discussions\",\n start_datetime=\"2024-01-01\",\n end_datetime=\"2024-03-31\",\n tags=[\"meetings\", \"roadmap\"],\n tag_match_mode=\"all\"\n )",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What you're looking for, described naturally (e.g., \"meetings about API redesign\")"
},
"tags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Filter to memories with these tags. Use tag_match_mode to control matching."
},
"tag_match_mode": {
"type": "string",
"enum": [
"any",
"all"
],
"description": "\"any\" = match memories with ANY of the tags, \"all\" = match only memories with ALL tags"
},
"top_k": {
"type": "integer",
"description": "Maximum number of results to return (default: 10)"
},
"start_datetime": {
"type": "string",
"description": "Only return memories created after this time (ISO 8601: \"2024-01-15\" or \"2024-01-15T14:30\")"
},
"end_datetime": {
"type": "string",
"description": "Only return memories created before this time (ISO 8601 format)"
}
},
"required": [
"query"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": true,
"created_by_id": "user-abcfbcb7-1a1b-41e3-8adf-bf3e7c7b2776",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {},
"project_id": null
},
{
"id": "tool-0",
"tool_type": "letta_core",
"description": "Search prior conversation history using hybrid search (text + semantic similarity).\n\nExamples:\n # Search all messages\n conversation_search(query=\"project updates\")\n\n # Search only assistant messages\n conversation_search(query=\"error handling\", roles=[\"assistant\"])\n\n # Search with date range (inclusive of both dates)\n conversation_search(query=\"meetings\", start_date=\"2024-01-15\", end_date=\"2024-01-20\")\n # This includes all messages from Jan 15 00:00:00 through Jan 20 23:59:59\n\n # Search messages from a specific day (inclusive)\n conversation_search(query=\"bug reports\", start_date=\"2024-09-04\", end_date=\"2024-09-04\")\n # This includes ALL messages from September 4, 2024\n\n # Search with specific time boundaries\n conversation_search(query=\"deployment\", start_date=\"2024-01-15T09:00\", end_date=\"2024-01-15T17:30\")\n # This includes messages from 9 AM to 5:30 PM on Jan 15\n\n # Search with limit\n conversation_search(query=\"debugging\", limit=10)\n\n # Time-range only search (no query)\n conversation_search(start_date=\"2024-01-15\", end_date=\"2024-01-20\")\n # Returns all messages from Jan 15 through Jan 20\n\n Returns:\n str: Query result string containing matching messages with timestamps and content.",
"source_type": "python",
"name": "conversation_search",
"tags": [
"letta_core"
],
"source_code": null,
"json_schema": {
"name": "conversation_search",
"description": "Search prior conversation history using hybrid search (text + semantic similarity).\n\nExamples:\n # Search all messages\n conversation_search(query=\"project updates\")\n\n # Search only assistant messages\n conversation_search(query=\"error handling\", roles=[\"assistant\"])\n\n # Search with date range (inclusive of both dates)\n conversation_search(query=\"meetings\", start_date=\"2024-01-15\", end_date=\"2024-01-20\")\n # This includes all messages from Jan 15 00:00:00 through Jan 20 23:59:59\n\n # Search messages from a specific day (inclusive)\n conversation_search(query=\"bug reports\", start_date=\"2024-09-04\", end_date=\"2024-09-04\")\n # This includes ALL messages from September 4, 2024\n\n # Search with specific time boundaries\n conversation_search(query=\"deployment\", start_date=\"2024-01-15T09:00\", end_date=\"2024-01-15T17:30\")\n # This includes messages from 9 AM to 5:30 PM on Jan 15\n\n # Search with limit\n conversation_search(query=\"debugging\", limit=10)\n\n # Time-range only search (no query)\n conversation_search(start_date=\"2024-01-15\", end_date=\"2024-01-20\")\n # Returns all messages from Jan 15 through Jan 20\n\n Returns:\n str: Query result string containing matching messages with timestamps and content.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "String to search for using both text matching and semantic similarity. If not provided, returns messages based on other filters (time range, roles)."
},
"roles": {
"type": "array",
"items": {
"type": "string",
"enum": [
"assistant",
"user",
"tool"
]
},
"description": "Optional list of message roles to filter by."
},
"limit": {
"type": "integer",
"description": "Maximum number of results to return. Uses system default if not specified."
},
"start_date": {
"type": "string",
"description": "Filter results to messages created on or after this date (INCLUSIVE). When using date-only format (e.g., \"2024-01-15\"), includes messages starting from 00:00:00 of that day. ISO 8601 format: \"YYYY-MM-DD\" or \"YYYY-MM-DDTHH:MM\". Examples: \"2024-01-15\" (from start of Jan 15), \"2024-01-15T14:30\" (from 2:30 PM on Jan 15)."
},
"end_date": {
"type": "string",
"description": "Filter results to messages created on or before this date (INCLUSIVE). When using date-only format (e.g., \"2024-01-20\"), includes all messages from that entire day. ISO 8601 format: \"YYYY-MM-DD\" or \"YYYY-MM-DDTHH:MM\". Examples: \"2024-01-20\" (includes all of Jan 20), \"2024-01-20T17:00\" (up to 5 PM on Jan 20)."
}
},
"required": []
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": true,
"created_by_id": "user-abcfbcb7-1a1b-41e3-8adf-bf3e7c7b2776",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {},
"project_id": null
},
{
"id": "tool-9",
"tool_type": "letta_builtin",
"description": "Fetch a webpage and convert it to markdown/text format using Exa API (if available) or trafilatura/readability.",
"source_type": "python",
"name": "fetch_webpage",
"tags": [
"letta_builtin"
],
"source_code": null,
"json_schema": {
"name": "fetch_webpage",
"description": "Fetch a webpage and convert it to markdown/text format using Exa API (if available) or trafilatura/readability.",
"parameters": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL of the webpage to fetch and convert"
}
},
"required": [
"url"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": true,
"created_by_id": "user-7ca5db89-d92b-4b9b-a958-9886aee1f044",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {},
"project_id": null
},
{
"id": "tool-4",
"tool_type": "external_mcp",
"description": "Create a new document from text. Also supports limited HTML.",
"source_type": "python",
"name": "google_docs_create_document_from_text",
"tags": [
"mcp:Zapier 1",
"in_turbopuffer"
],
"source_code": "def google_docs_create_document_from_text(**kwargs):\n raise RuntimeError(\"Something went wrong - we should never be using the persisted source code for MCP. Please reach out to Letta team\")",
"json_schema": {
"name": "google_docs_create_document_from_text",
"description": "Create a new document from text. Also supports limited HTML.",
"parameters": {
"type": "object",
"properties": {
"instructions": {
"type": "string",
"description": "Instructions for running this tool. Any parameters that are not given a value will be guessed based on the instructions."
},
"file": {
"type": "string",
"description": "Document Content"
},
"drive": {
"type": "string",
"description": "Drive"
},
"image": {
"type": "string",
"description": "Insert Inline Image (Image URL)"
},
"title": {
"type": "string",
"description": "Document Name"
},
"folder": {
"type": "string",
"description": "Folder"
},
"image_index": {
"type": "string",
"description": "Image location (Index)"
},
"image_tabId": {
"type": "string",
"description": "Image location (tabId)"
},
"export_formats": {
"type": "array",
"items": {
"type": "string"
},
"description": "Export Formats"
},
"image_segmentId": {
"type": "string",
"description": "Image location (Segment ID)"
},
"request_heartbeat": {
"type": "boolean",
"description": "Request an immediate heartbeat after function execution. You MUST set this value to `True` if you want to send a follow-up message or run a follow-up tool call (chain multiple tools together). If set to `False` (the default), then the chain of execution will end immediately after this function call."
}
},
"required": [
"instructions",
"request_heartbeat"
],
"additionalProperties": false
},
"mcp:SCHEMA_STATUS": "STRICT_COMPLIANT",
"mcp:SCHEMA_WARNINGS": []
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": false,
"created_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {
"mcp": {
"server_name": "Zapier 1",
"server_id": "mcp_server-d24c1ed9-f4b3-41e6-a471-651c43a01944"
}
},
"project_id": null
},
{
"id": "tool-13",
"tool_type": "letta_memory_core",
"description": "Memory management tool with various sub-commands for memory block operations.\n\nExamples:\n # Replace text in a memory block\n memory(agent_state, \"str_replace\", path=\"/memories/user_preferences\", old_string=\"theme: dark\", new_string=\"theme: light\")\n\n # Insert text at line 5\n memory(agent_state, \"insert\", path=\"/memories/notes\", insert_line=5, insert_text=\"New note here\")\n\n # Delete a memory block\n memory(agent_state, \"delete\", path=\"/memories/old_notes\")\n\n # Rename a memory block\n memory(agent_state, \"rename\", old_path=\"/memories/temp\", new_path=\"/memories/permanent\")\n\n # Update the description of a memory block\n memory(agent_state, \"rename\", path=\"/memories/temp\", description=\"The user's temporary notes.\")\n\n # Create a memory block with starting text\n memory(agent_state, \"create\", path=\"/memories/coding_preferences\", \"description\": \"The user's coding preferences.\", \"file_text\": \"The user seems to add type hints to all of their Python code.\")\n\n # Create an empty memory block\n memory(agent_state, \"create\", path=\"/memories/coding_preferences\", \"description\": \"The user's coding preferences.\")",
"source_type": "python",
"name": "memory",
"tags": [
"letta_memory_core"
],
"source_code": null,
"json_schema": {
"name": "memory",
"description": "Memory management tool with various sub-commands for memory block operations.\n\nExamples:\n # Replace text in a memory block\n memory(agent_state, \"str_replace\", path=\"/memories/user_preferences\", old_string=\"theme: dark\", new_string=\"theme: light\")\n\n # Insert text at line 5\n memory(agent_state, \"insert\", path=\"/memories/notes\", insert_line=5, insert_text=\"New note here\")\n\n # Delete a memory block\n memory(agent_state, \"delete\", path=\"/memories/old_notes\")\n\n # Rename a memory block\n memory(agent_state, \"rename\", old_path=\"/memories/temp\", new_path=\"/memories/permanent\")\n\n # Update the description of a memory block\n memory(agent_state, \"rename\", path=\"/memories/temp\", description=\"The user's temporary notes.\")\n\n # Create a memory block with starting text\n memory(agent_state, \"create\", path=\"/memories/coding_preferences\", \"description\": \"The user's coding preferences.\", \"file_text\": \"The user seems to add type hints to all of their Python code.\")\n\n # Create an empty memory block\n memory(agent_state, \"create\", path=\"/memories/coding_preferences\", \"description\": \"The user's coding preferences.\")",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The sub-command to execute. Supported commands:\n- \"create\": Create a new memory block\n- \"str_replace\": Replace text in a memory block\n- \"insert\": Insert text at a specific line in a memory block\n- \"delete\": Delete a memory block\n- \"rename\": Rename a memory block"
},
"path": {
"type": "string",
"description": "Path to the memory block (for str_replace, insert, delete)"
},
"file_text": {
"type": "string",
"description": "The value to set in the memory block (for create)"
},
"description": {
"type": "string",
"description": "The description to set in the memory block (for create, rename)"
},
"old_string": {
"type": "string",
"description": "Old text to replace (for str_replace)"
},
"new_string": {
"type": "string",
"description": "New text to replace with (for str_replace)"
},
"insert_line": {
"type": "integer",
"description": "Line number to insert at (for insert)"
},
"insert_text": {
"type": "string",
"description": "Text to insert (for insert)"
},
"old_path": {
"type": "string",
"description": "Old path for rename operation"
},
"new_path": {
"type": "string",
"description": "New path for rename operation"
}
},
"required": [
"command"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": false,
"created_by_id": "user-7ca5db89-d92b-4b9b-a958-9886aee1f044",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {},
"project_id": null
},
{
"id": "tool-10",
"tool_type": "letta_sleeptime_core",
"description": "The memory_insert command allows you to insert text at a specific location in a memory block.\n\nExamples:\n # Update a block containing information about the user (append to the end of the block)\n memory_insert(label=\"customer\", new_str=\"The customer's ticket number is 12345\")\n\n # Update a block containing information about the user (insert at the beginning of the block)\n memory_insert(label=\"customer\", new_str=\"The customer's ticket number is 12345\", insert_line=0)\n\n Returns:\n Optional[str]: None is always returned as this function does not produce a response.",
"source_type": "python",
"name": "memory_insert",
"tags": [
"letta_sleeptime_core"
],
"source_code": null,
"json_schema": {
"name": "memory_insert",
"description": "The memory_insert command allows you to insert text at a specific location in a memory block.\n\nExamples:\n # Update a block containing information about the user (append to the end of the block)\n memory_insert(label=\"customer\", new_str=\"The customer's ticket number is 12345\")\n\n # Update a block containing information about the user (insert at the beginning of the block)\n memory_insert(label=\"customer\", new_str=\"The customer's ticket number is 12345\", insert_line=0)\n\n Returns:\n Optional[str]: None is always returned as this function does not produce a response.",
"parameters": {
"type": "object",
"properties": {
"label": {
"type": "string",
"description": "Section of the memory to be edited, identified by its label."
},
"new_str": {
"type": "string",
"description": "The text to insert. Do not include line number prefixes."
},
"insert_line": {
"type": "integer",
"description": "The line number after which to insert the text (0 for beginning of file). Defaults to -1 (end of the file)."
}
},
"required": [
"label",
"new_str"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": false,
"created_by_id": "user-7ca5db89-d92b-4b9b-a958-9886aee1f044",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {},
"project_id": null
},
{
"id": "tool-6",
"tool_type": "letta_sleeptime_core",
"description": "The memory_replace command allows you to replace a specific string in a memory block with a new string. This is used for making precise edits.\n\nDo NOT attempt to replace long strings, e.g. do not attempt to replace the entire contents of a memory block with a new string.\n\nExamples:\n # Update a block containing information about the user\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"Their name is Bob\")\n\n # Update a block containing a todo list\n memory_replace(label=\"todos\", old_str=\"- [ ] Step 5: Search the web\", new_str=\"- [x] Step 5: Search the web\")\n\n # Pass an empty string to\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"\")\n\n # Bad example - do NOT add (view-only) line numbers to the args\n memory_replace(label=\"human\", old_str=\"1: Their name is Alice\", new_str=\"1: Their name is Bob\")\n\n # Bad example - do NOT include the line number warning either\n memory_replace(label=\"human\", old_str=\"# NOTE: Line numbers shown below (with arrows like '1→') are to help during editing. Do NOT include line number prefixes in your memory edit tool calls.\\n1→ Their name is Alice\", new_str=\"1→ Their name is Bob\")\n\n # Good example - no line numbers or line number warning (they are view-only), just the text\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"Their name is Bob\")\n\n Returns:\n str: The success message",
"source_type": "python",
"name": "memory_replace",
"tags": [
"letta_sleeptime_core"
],
"source_code": null,
"json_schema": {
"name": "memory_replace",
"description": "The memory_replace command allows you to replace a specific string in a memory block with a new string. This is used for making precise edits.\n\nDo NOT attempt to replace long strings, e.g. do not attempt to replace the entire contents of a memory block with a new string.\n\nExamples:\n # Update a block containing information about the user\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"Their name is Bob\")\n\n # Update a block containing a todo list\n memory_replace(label=\"todos\", old_str=\"- [ ] Step 5: Search the web\", new_str=\"- [x] Step 5: Search the web\")\n\n # Pass an empty string to\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"\")\n\n # Bad example - do NOT add (view-only) line numbers to the args\n memory_replace(label=\"human\", old_str=\"1: Their name is Alice\", new_str=\"1: Their name is Bob\")\n\n # Bad example - do NOT include the line number warning either\n memory_replace(label=\"human\", old_str=\"# NOTE: Line numbers shown below (with arrows like '1→') are to help during editing. Do NOT include line number prefixes in your memory edit tool calls.\\n1→ Their name is Alice\", new_str=\"1→ Their name is Bob\")\n\n # Good example - no line numbers or line number warning (they are view-only), just the text\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"Their name is Bob\")\n\n Returns:\n str: The success message",
"parameters": {
"type": "object",
"properties": {
"label": {
"type": "string",
"description": "Section of the memory to be edited, identified by its label."
},
"old_str": {
"type": "string",
"description": "The text to replace (must match exactly, including whitespace and indentation)."
},
"new_str": {
"type": "string",
"description": "The new text to insert in place of the old text. Do not include line number prefixes."
}
},
"required": [
"label",
"old_str",
"new_str"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": false,
"created_by_id": "user-7ca5db89-d92b-4b9b-a958-9886aee1f044",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {},
"project_id": null
},
{
"id": "tool-14",
"tool_type": "letta_sleeptime_core",
"description": "The memory_rethink command allows you to completely rewrite the contents of a memory block. Use this tool to make large sweeping changes (e.g. when you want to condense or reorganize the memory blocks), do NOT use this tool to make small precise edits (e.g. add or remove a line, replace a specific string, etc).",
"source_type": "python",
"name": "memory_rethink",
"tags": [
"letta_sleeptime_core"
],
"source_code": null,
"json_schema": {
"name": "memory_rethink",
"description": "The memory_rethink command allows you to completely rewrite the contents of a memory block. Use this tool to make large sweeping changes (e.g. when you want to condense or reorganize the memory blocks), do NOT use this tool to make small precise edits (e.g. add or remove a line, replace a specific string, etc).",
"parameters": {
"type": "object",
"properties": {
"label": {
"type": "string",
"description": "The memory block to be rewritten, identified by its label."
},
"new_memory": {
"type": "string",
"description": "The new memory contents with information integrated from existing memory blocks and the conversation context."
}
},
"required": [
"label",
"new_memory"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": false,
"created_by_id": "user-7ca5db89-d92b-4b9b-a958-9886aee1f044",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {},
"project_id": null
},
{
"id": "tool-8",
"tool_type": "custom",
"description": "Manage notes in your vault. All notes are automatically scoped to your agent.\n\nCommands:\n create - create new note (not attached)\n view - read note contents\n attach [content] - load into context (supports /folder/*)\n detach - remove from context (supports /folder/*)\n insert [line] - insert before line (0-indexed) or append\n append - add content to end of note\n replace - find/replace, shows diff\n rename - move/rename note to new path\n copy - duplicate note to new path\n delete - permanently remove\n list [query] - list notes (prefix filter, * for all)\n search [label|content] - grep notes by label or content\n attached - show notes currently in context",
"source_type": "json",
"name": "note",
"tags": [],
"source_code": "from typing import Literal, Optional\nimport re\n\n\ndef note(\n command: str,\n path: Optional[str] = None,\n content: Optional[str] = None,\n old_str: Optional[str] = None,\n new_str: Optional[str] = None,\n new_path: Optional[str] = None,\n insert_line: Optional[int] = None,\n query: Optional[str] = None,\n search_type: str = \"label\",\n) -> str:\n \"\"\"\n Manage notes in your vault. All notes are automatically scoped to your agent.\n \n Commands:\n create - create new note (not attached)\n view - read note contents\n attach [content] - load into context (supports /folder/*)\n detach - remove from context (supports /folder/*)\n insert [line] - insert before line (0-indexed) or append\n append - add content to end of note\n replace - find/replace, shows diff\n rename - move/rename note to new path\n copy - duplicate note to new path\n delete - permanently remove\n list [query] - list notes (prefix filter, * for all)\n search [label|content] - grep notes by label or content\n attached - show notes currently in context\n \n Args:\n command: The operation to perform\n path: Path to the note (e.g., /projects/webapp, /todo)\n content: Content to insert or initial content when creating\n old_str: Text to find (for replace)\n new_str: Text to replace with (for replace)\n new_path: Destination path (for rename/copy)\n insert_line: Line number to insert before (0-indexed, omit to append)\n query: Search query (for list/search)\n search_type: Search by \"label\" or \"content\"\n \n Returns:\n str: Result of the operation\n \"\"\"\n import os\n \n agent_id = os.environ.get(\"LETTA_AGENT_ID\")\n \n # Check enabled commands (\"all\" or \"*\" enables everything)\n all_commands = [\"create\", \"view\", \"attach\", \"detach\", \"insert\", \"append\", \"replace\", \"rename\", \"copy\", \"delete\", \"list\", \"search\", \"attached\"]\n enabled_env = os.environ.get(\"ENABLED_COMMANDS\", \"create,view,attach,detach,insert,append,replace,rename,copy,list,search,attached\")\n enabled = all_commands if enabled_env in (\"all\", \"*\") else enabled_env.split(\",\")\n if command not in enabled:\n return f\"Error: '{command}' is disabled. Enabled: {enabled}\"\n \n # Pattern to filter out legacy UUID paths\n uuid_pattern = re.compile(r'/\\[?agent-[a-f0-9-]+\\]?/')\n \n # Parameter validation\n path_required = [\"create\", \"view\", \"attach\", \"detach\", \"insert\", \"append\", \"replace\", \"rename\", \"copy\", \"delete\"]\n if command in path_required and not path:\n return f\"Error: '{command}' requires path parameter\"\n \n if command == \"replace\" and (not old_str or new_str is None):\n return \"Error: 'replace' requires old_str and new_str parameters\"\n \n if command in [\"create\", \"insert\", \"append\"] and not content:\n return f\"Error: '{command}' requires content parameter\"\n \n if command in [\"rename\", \"copy\"] and not new_path:\n return f\"Error: '{command}' requires new_path parameter\"\n \n if command == \"search\" and not query:\n return \"Error: 'search' requires query parameter\"\n \n # Track if directory needs updating\n update_directory = False\n result = None\n \n try:\n if command == \"create\":\n # Check for existing note with same path\n existing = list(client.blocks.list(label=path, description_search=agent_id).items)\n if existing:\n return f\"Error: Note already exists: {path}\"\n \n client.blocks.create(\n label=path,\n value=content,\n description=f\"owner:{agent_id}\"\n )\n update_directory = True\n result = f\"Created: {path}\"\n \n elif command == \"view\":\n blocks = list(client.blocks.list(label=path, description_search=agent_id).items)\n if not blocks:\n return f\"Note not found: {path}\"\n return blocks[0].value\n \n elif command == \"attach\":\n # Get currently attached block IDs to avoid duplicate attach errors\n agent = client.agents.retrieve(agent_id=agent_id)\n attached_ids = {b.id for b in agent.memory.blocks}\n \n # Handle bulk wildcard: /folder/*\n if path.endswith(\"/*\"):\n prefix = path[:-1] # \"/folder/*\" → \"/folder/\"\n all_blocks = list(client.blocks.list(description_search=agent_id).items)\n blocks = [b for b in all_blocks if b.label and b.label.startswith(prefix)\n and not uuid_pattern.search(b.label)]\n if not blocks:\n return f\"No notes matching: {path}\"\n \n to_attach = [b for b in blocks if b.id not in attached_ids]\n skipped = len(blocks) - len(to_attach)\n \n for block in to_attach:\n client.agents.blocks.attach(agent_id=agent_id, block_id=block.id)\n \n msg = f\"Attached {len(to_attach)} notes matching {path}\"\n if skipped:\n msg += f\" ({skipped} already attached)\"\n return msg\n \n # Single note attach\n existing = list(client.blocks.list(label=path, description_search=agent_id).items)\n if existing:\n block_id = existing[0].id\n if block_id in attached_ids:\n return f\"Already attached: {path}\"\n else:\n new_block = client.blocks.create(\n label=path,\n value=content or \"\",\n description=f\"owner:{agent_id}\"\n )\n block_id = new_block.id\n update_directory = True # New note created\n \n client.agents.blocks.attach(agent_id=agent_id, block_id=block_id)\n result = f\"Attached: {path}\"\n \n elif command == \"detach\":\n # Handle bulk wildcard: /folder/*\n if path.endswith(\"/*\"):\n prefix = path[:-1]\n # Get currently attached block IDs\n agent = client.agents.retrieve(agent_id=agent_id)\n attached_ids = {b.id for b in agent.memory.blocks}\n \n all_blocks = list(client.blocks.list(description_search=agent_id).items)\n blocks = [b for b in all_blocks if b.label and b.label.startswith(prefix)\n and not uuid_pattern.search(b.label)\n and b.id in attached_ids] # Only detach if actually attached\n if not blocks:\n return f\"No attached notes matching: {path}\"\n for block in blocks:\n client.agents.blocks.detach(agent_id=agent_id, block_id=block.id)\n return f\"Detached {len(blocks)} notes matching {path}\"\n \n # Single note detach\n blocks = list(client.blocks.list(label=path, description_search=agent_id).items)\n if not blocks:\n return f\"Note not found: {path}\"\n \n client.agents.blocks.detach(agent_id=agent_id, block_id=blocks[0].id)\n return f\"Detached: {path}\"\n \n elif command == \"insert\":\n blocks = list(client.blocks.list(label=path, description_search=agent_id).items)\n if not blocks:\n return f\"Note not found: {path}. Use 'attach' first.\"\n \n block = blocks[0]\n lines = block.value.split(\"\\n\") if block.value else []\n \n if insert_line is not None:\n lines.insert(insert_line, content)\n line_info = f\"line {insert_line}\"\n else:\n lines.append(content)\n line_info = \"end\"\n \n client.blocks.update(block_id=block.id, value=\"\\n\".join(lines))\n \n preview = content[:80] + \"...\" if len(content) > 80 else content\n return f\"Inserted at {line_info} in {path}:\\n + {preview}\"\n \n elif command == \"append\":\n blocks = list(client.blocks.list(label=path, description_search=agent_id).items)\n if not blocks:\n return f\"Note not found: {path}. Use 'attach' first.\"\n \n block = blocks[0]\n if block.value:\n new_value = block.value + \"\\n\" + content\n else:\n new_value = content\n \n client.blocks.update(block_id=block.id, value=new_value)\n \n preview = content[:80] + \"...\" if len(content) > 80 else content\n return f\"Appended to {path}:\\n + {preview}\"\n \n elif command == \"rename\":\n # Check source exists\n blocks = list(client.blocks.list(label=path, description_search=agent_id).items)\n if not blocks:\n return f\"Note not found: {path}\"\n \n # Check destination doesn't exist\n dest_blocks = list(client.blocks.list(label=new_path, description_search=agent_id).items)\n if dest_blocks:\n return f\"Error: Destination already exists: {new_path}\"\n \n # Update the label\n block = blocks[0]\n client.blocks.update(block_id=block.id, label=new_path)\n update_directory = True\n result = f\"Renamed: {path} → {new_path}\"\n \n elif command == \"copy\":\n # Check source exists\n blocks = list(client.blocks.list(label=path, description_search=agent_id).items)\n if not blocks:\n return f\"Note not found: {path}\"\n \n # Check destination doesn't exist\n dest_blocks = list(client.blocks.list(label=new_path, description_search=agent_id).items)\n if dest_blocks:\n return f\"Error: Destination already exists: {new_path}\"\n \n # Create copy (not attached)\n source = blocks[0]\n client.blocks.create(\n label=new_path,\n value=source.value,\n description=f\"owner:{agent_id}\"\n )\n update_directory = True\n result = f\"Copied: {path} → {new_path}\"\n \n elif command == \"replace\":\n blocks = list(client.blocks.list(label=path, description_search=agent_id).items)\n if not blocks:\n return f\"Note not found: {path}\"\n \n block = blocks[0]\n if old_str not in block.value:\n return f\"Error: old_str not found in note. Exact match required.\"\n \n new_value = block.value.replace(old_str, new_str, 1)\n client.blocks.update(block_id=block.id, value=new_value)\n \n return f\"Replaced in {path}:\\n - {old_str}\\n + {new_str}\"\n \n elif command == \"delete\":\n blocks = list(client.blocks.list(label=path, description_search=agent_id).items)\n if not blocks:\n return f\"Note not found: {path}\"\n \n client.blocks.delete(block_id=blocks[0].id)\n update_directory = True\n result = f\"Deleted: {path}\"\n \n elif command == \"list\":\n all_blocks = list(client.blocks.list(description_search=agent_id).items)\n \n # Filter to path-like labels, exclude legacy UUID paths\n blocks = [b for b in all_blocks \n if b.label and b.label.startswith(\"/\")\n and not uuid_pattern.search(b.label)]\n \n # Apply prefix filter if query provided\n if query and query != \"*\":\n blocks = [b for b in blocks if b.label.startswith(query)]\n \n if not blocks:\n return \"No notes found\" if not query or query == \"*\" else f\"No notes matching: {query}\"\n \n # Deduplicate and sort\n labels = sorted(set(b.label for b in blocks))\n return \"\\n\".join(labels)\n \n elif command == \"search\":\n all_blocks = list(client.blocks.list(description_search=agent_id).items)\n \n # Filter out legacy UUID paths\n all_blocks = [b for b in all_blocks \n if b.label and b.label.startswith(\"/\")\n and not uuid_pattern.search(b.label)]\n \n if search_type == \"label\":\n blocks = [b for b in all_blocks if query in b.label]\n else:\n blocks = [b for b in all_blocks if b.value and query in b.value]\n \n if not blocks:\n return f\"No notes matching: {query}\"\n \n results = []\n for b in blocks:\n preview = b.value[:100].replace(\"\\n\", \" \") if b.value else \"\"\n if len(b.value or \"\") > 100:\n preview += \"...\"\n results.append(f\"{b.label}: {preview}\")\n \n return \"\\n\".join(results)\n \n elif command == \"attached\":\n agent = client.agents.retrieve(agent_id=agent_id)\n note_blocks = [b for b in agent.memory.blocks \n if b.label and b.label.startswith(\"/\")\n and not uuid_pattern.search(b.label)]\n \n if not note_blocks:\n return \"No notes currently attached\"\n \n return \"\\n\".join(sorted(b.label for b in note_blocks))\n \n else:\n return f\"Error: Unknown command '{command}'\"\n \n # Update note_directory if needed\n if update_directory:\n dir_label = \"/note_directory\"\n # Get all notes\n all_blocks = list(client.blocks.list(description_search=agent_id).items)\n notes = [b for b in all_blocks \n if b.label and b.label.startswith(\"/\") \n and b.label != dir_label\n and not uuid_pattern.search(b.label)]\n \n # Header for the directory\n header = \"External storage. Attach to load into context, detach when done.\\nFolders are also notes (e.g., /projects and /projects/task1 can both have content).\\nCommands: view, attach, detach, insert, append, replace, rename, copy, delete, list, search\\nBulk: attach /folder/*, detach /folder/*\"\n \n if notes:\n # Group notes by folder\n folders = {}\n for b in sorted(notes, key=lambda x: x.label):\n parts = b.label.rsplit(\"/\", 1)\n if len(parts) == 2:\n folder, name = parts[0] + \"/\", parts[1]\n else:\n folder, name = \"/\", b.label[1:] # Root level\n if folder not in folders:\n folders[folder] = []\n first_line = (b.value or \"\").split(\"\\n\")[0][:40]\n if len((b.value or \"\").split(\"\\n\")[0]) > 40:\n first_line += \"...\"\n folders[folder].append((name, first_line))\n \n # Build tree view\n lines = []\n for folder in sorted(folders.keys()):\n lines.append(folder)\n items = folders[folder]\n max_name_len = max(len(name) for name, _ in items)\n for name, summary in items:\n lines.append(f\" {name.ljust(max_name_len)} | {summary}\")\n \n dir_content = header + \"\\n\\n\" + \"\\n\".join(lines)\n else:\n dir_content = header + \"\\n\\n(no notes)\"\n \n # Find or create directory block\n dir_blocks = list(client.blocks.list(label=dir_label, description_search=agent_id).items)\n if dir_blocks:\n client.blocks.update(block_id=dir_blocks[0].id, value=dir_content)\n else:\n # Create and attach directory block\n dir_block = client.blocks.create(\n label=dir_label,\n value=dir_content,\n description=f\"owner:{agent_id}\"\n )\n client.agents.blocks.attach(agent_id=agent_id, block_id=dir_block.id)\n \n if result:\n return result\n \n except Exception as e:\n return f\"Error executing '{command}': {str(e)}\"\n",
"json_schema": {
"name": "note",
"description": "Manage notes in your vault. All notes are automatically scoped to your agent.\n\nCommands:\n create - create new note (not attached)\n view - read note contents\n attach [content] - load into context (supports /folder/*)\n detach - remove from context (supports /folder/*)\n insert [line] - insert before line (0-indexed) or append\n append - add content to end of note\n replace - find/replace, shows diff\n rename - move/rename note to new path\n copy - duplicate note to new path\n delete - permanently remove\n list [query] - list notes (prefix filter, * for all)\n search [label|content] - grep notes by label or content\n attached - show notes currently in context",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The operation to perform"
},
"path": {
"type": "string",
"description": "Path to the note (e.g., /projects/webapp, /todo)"
},
"content": {
"type": "string",
"description": "Content to insert or initial content when creating"
},
"old_str": {
"type": "string",
"description": "Text to find (for replace)"
},
"new_str": {
"type": "string",
"description": "Text to replace with (for replace)"
},
"new_path": {
"type": "string",
"description": "Destination path (for rename/copy)"
},
"insert_line": {
"type": "integer",
"description": "Line number to insert before (0-indexed, omit to append)"
},
"query": {
"type": "string",
"description": "Search query (for list/search)"
},
"search_type": {
"type": "string",
"description": "Search by \"label\" or \"content\""
}
},
"required": [
"command"
]
}
},
"args_json_schema": {},
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": false,
"created_by_id": "user-8cd57678-bd88-4664-bd90-1dbcabeea00e",
"last_updated_by_id": "user-8cd57678-bd88-4664-bd90-1dbcabeea00e",
"metadata_": {
"tool_hash": "310ddaba6952"
},
"project_id": "00040382-8469-439d-a5c1-8da018e7941f"
},
{
"id": "tool-7",
"tool_type": "custom",
"description": "Send a notification message to the Telegram user.\n\nThis tool sends a notification to a Telegram chat using the bot API.\nIt requires TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID environment variables.\n\nArgs:\n message (str): The notification message to send to the user\n\nReturns:\n str: Confirmation that the message was sent or error message",
"source_type": "json",
"name": "notify_via_telegram",
"tags": [
"telegram",
"notification",
"messaging"
],
"source_code": "def notify_via_telegram(message: str) -> str:\n \"\"\"\n Send a notification message to the Telegram user.\n\n This tool sends a notification to a Telegram chat using the bot API.\n It requires TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID environment variables.\n\n Args:\n message (str): The notification message to send to the user\n\n Returns:\n str: Confirmation that the message was sent or error message\n \"\"\"\n import requests\n\n bot_token = os.environ.get(\"TELEGRAM_BOT_TOKEN\")\n chat_id = os.environ.get(\"TELEGRAM_CHAT_ID\")\n\n if not bot_token:\n return \"Error: TELEGRAM_BOT_TOKEN environment variable is not set\"\n\n if not chat_id:\n return \"Error: TELEGRAM_CHAT_ID environment variable is not set\"\n\n # Escape MarkdownV2 special characters\n special_chars = ['_', '*', '[', ']', '(', ')', '~', '`', '>', '#', '+', '-', '=', '|', '{', '}', '.', '!']\n markdown_text = message\n for char in special_chars:\n markdown_text = markdown_text.replace(char, f'\\\\{char}')\n\n # Send message via Telegram API\n url = f\"https://api.telegram.org/bot{bot_token}/sendMessage\"\n payload = {\n \"chat_id\": chat_id,\n \"text\": markdown_text,\n \"parse_mode\": \"MarkdownV2\"\n }\n\n try:\n response = requests.post(url, json=payload, timeout=10)\n if response.status_code == 200:\n return \"Message sent successfully via Telegram\"\n else:\n return f\"Failed to send Telegram message: {response.status_code} - {response.text}\"\n except requests.exceptions.RequestException as e:\n return f\"Error sending Telegram message: {str(e)}\"\n",
"json_schema": {
"name": "notify_via_telegram",
"description": "Send a notification message to the Telegram user.\n\nThis tool sends a notification to a Telegram chat using the bot API.\nIt requires TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID environment variables.\n\nArgs:\n message (str): The notification message to send to the user\n\nReturns:\n str: Confirmation that the message was sent or error message",
"parameters": {
"type": "object",
"properties": {
"message": {
"type": "string",
"description": "The notification message to send to the Telegram user"
}
},
"required": [
"message"
]
}
},
"args_json_schema": {
"description": "Schema for the notify_via_telegram tool arguments.",
"properties": {
"message": {
"description": "The notification message to send to the Telegram user",
"title": "Message",
"type": "string"
}
},
"required": [
"message"
],
"title": "TelegramMessageData",
"type": "object"
},
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": false,
"created_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {
"tool_hash": "8defa15186c4"
},
"project_id": "00040382-8469-439d-a5c1-8da018e7941f"
},
{
"id": "tool-1",
"tool_type": "letta_builtin",
"description": "Run code in a sandbox. Supports Python, Javascript, Typescript, R, and Java.",
"source_type": "python",
"name": "run_code",
"tags": [
"letta_builtin"
],
"source_code": null,
"json_schema": {
"name": "run_code",
"description": "Run code in a sandbox. Supports Python, Javascript, Typescript, R, and Java.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The code to run."
},
"language": {
"type": "string",
"enum": [
"python",
"js",
"ts",
"r",
"java"
],
"description": "The language of the code."
}
},
"required": [
"code",
"language"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": true,
"created_by_id": "user-7ca5db89-d92b-4b9b-a958-9886aee1f044",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {},
"project_id": null
},
{
"id": "tool-3",
"tool_type": "custom",
"description": "Send a direct message to the configured Discord user.",
"source_type": "python",
"name": "send_discord_dm",
"tags": [],
"source_code": "def send_discord_dm(message: str) -> str:\n \"\"\"Send a direct message to the configured Discord user.\n \n Args:\n message: Text to send\n \"\"\"\n import os\n import requests\n \n token = os.getenv(\"DISCORD_BOT_TOKEN\")\n user_id = os.getenv(\"DISCORD_USER_ID\")\n headers = {\"Authorization\": f\"Bot {token}\", \"Content-Type\": \"application/json\"}\n \n # Create/get DM channel\n dm_channel = requests.post(\n \"https://discord.com/api/v10/users/@me/channels\",\n headers=headers,\n json={\"recipient_id\": user_id}\n ).json()\n \n # Send message\n response = requests.post(\n f\"https://discord.com/api/v10/channels/{dm_channel['id']}/messages\",\n headers=headers,\n json={\"content\": message}\n )\n return \"DM sent\" if response.status_code == 200 else f\"Failed: {response.text}\"",
"json_schema": {
"name": "send_discord_dm",
"description": "Send a direct message to the configured Discord user.",
"parameters": {
"type": "object",
"properties": {
"message": {
"type": "string",
"description": "Text to send"
}
},
"required": [
"message"
]
}
},
"args_json_schema": {},
"return_char_limit": 50000,
"pip_requirements": [],
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": false,
"created_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {
"tool_hash": "8977090abef0"
},
"project_id": "00040382-8469-439d-a5c1-8da018e7941f"
},
{
"id": "tool-5",
"tool_type": "external_mcp",
"description": "Create a new draft with content for one or more social media platforms. The draft can be saved as a draft, scheduled for later publishing, or published immediately.\n\n**Required permission:** WRITE access to create drafts. PUBLISH access is required to schedule or publish immediately.",
"source_type": "python",
"name": "typefully_drafts_create_draft",
"tags": [
"mcp:camerontypefully"
],
"source_code": "def typefully_drafts_create_draft(**kwargs):\n raise RuntimeError(\"Something went wrong - we should never be using the persisted source code for MCP. Please reach out to Letta team\")",
"json_schema": {
"name": "typefully_drafts_create_draft",
"description": "Create a new draft with content for one or more social media platforms. The draft can be saved as a draft, scheduled for later publishing, or published immediately.\n\n**Required permission:** WRITE access to create drafts. PUBLISH access is required to schedule or publish immediately.",
"parameters": {
"type": "object",
"properties": {
"social_set_id": {
"title": "Social Set Id",
"type": "number"
},
"requestBody": {
"additionalProperties": false,
"description": "Request schema for creating a draft",
"properties": {
"platforms": {
"description": "Platform configurations for each social media platform",
"additionalProperties": false,
"properties": {
"x": {
"anyOf": [
{
"discriminator": {
"mapping": {
"False": "#/components/schemas/DisabledPlatform",
"True": "#/components/schemas/EnabledXPlatform"
},
"propertyName": "enabled"
},
"oneOf": [
{
"additionalProperties": false,
"description": "Enabled X platform with required data (request validation)",
"properties": {
"enabled": {
"const": true,
"enum": [
true
],
"title": "Enabled",
"type": "boolean"
},
"posts": {
"description": "List of posts for this platform",
"items": {
"additionalProperties": false,
"description": "Schema for individual post content",
"properties": {
"text": {
"description": "The text content of the post",
"examples": [
"Hello world! This is my first post.",
"Check out this amazing update! 🚀"
],
"maxLength": 50000,
"title": "Text",
"type": "string"
},
"media_ids": {
"description": "List of media IDs to attach to the post. Obtain media IDs by uploading files via the media upload endpoint.",
"examples": [
[
"550e8400-e29b-41d4-a716-446655440000"
],
[
"550e8400-e29b-41d4-a716-446655440000",
"6ba7b810-9dad-11d1-80b4-00c04fd430c8"
]
],
"items": {
"type": "string"
},
"maxItems": 10,
"title": "Media Ids",
"type": "array"
}
},
"required": [
"text"
],
"title": "Post",
"type": "object"
},
"maxItems": 25,
"title": "Posts",
"type": "array"
},
"settings": {
"anyOf": [
{
"additionalProperties": false,
"description": "Settings specific to X (Twitter)",
"properties": {
"reply_to_url": {
"anyOf": [
{
"maxLength": 2048,
"type": "string"
},
{
"type": "null"
}
],
"description": "URL of the X post to reply to. When provided, the first post in your thread will be posted as a reply.",
"examples": [
"https://x.com/therajatkapoor/status/1399394576951959554"
],
"title": "Reply To Url"
}
},
"title": "XSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "X-specific settings"
}
},
"required": [
"enabled",
"posts"
],
"title": "EnabledXPlatform",
"type": "object"
},
{
"additionalProperties": false,
"description": "Shared schema for all disabled platforms",
"properties": {
"enabled": {
"const": false,
"enum": [
false
],
"title": "Enabled",
"type": "boolean"
}
},
"required": [
"enabled"
],
"title": "DisabledPlatform",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "X (Twitter) configuration",
"title": "X"
},
"linkedin": {
"anyOf": [
{
"discriminator": {
"mapping": {
"False": "#/components/schemas/DisabledPlatform",
"True": "#/components/schemas/EnabledLinkedInPlatform"
},
"propertyName": "enabled"
},
"oneOf": [
{
"additionalProperties": false,
"description": "Enabled LinkedIn platform with required data (request validation)",
"properties": {
"enabled": {
"const": true,
"enum": [
true
],
"title": "Enabled",
"type": "boolean"
},
"posts": {
"description": "List of posts for this platform",
"items": {
"additionalProperties": false,
"description": "Schema for individual post content",
"properties": {
"text": {
"description": "The text content of the post",
"examples": [
"Hello world! This is my first post.",
"Check out this amazing update! 🚀"
],
"maxLength": 50000,
"title": "Text",
"type": "string"
},
"media_ids": {
"description": "List of media IDs to attach to the post. Obtain media IDs by uploading files via the media upload endpoint.",
"examples": [
[
"550e8400-e29b-41d4-a716-446655440000"
],
[
"550e8400-e29b-41d4-a716-446655440000",
"6ba7b810-9dad-11d1-80b4-00c04fd430c8"
]
],
"items": {
"type": "string"
},
"maxItems": 10,
"title": "Media Ids",
"type": "array"
}
},
"required": [
"text"
],
"title": "Post",
"type": "object"
},
"maxItems": 25,
"title": "Posts",
"type": "array"
},
"settings": {
"anyOf": [
{
"additionalProperties": false,
"description": "Settings specific to LinkedIn",
"properties": {},
"title": "LinkedInSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "LinkedIn-specific settings"
}
},
"required": [
"enabled",
"posts"
],
"title": "EnabledLinkedInPlatform",
"type": "object"
},
{
"additionalProperties": false,
"description": "Shared schema for all disabled platforms",
"properties": {
"enabled": {
"const": false,
"enum": [
false
],
"title": "Enabled",
"type": "boolean"
}
},
"required": [
"enabled"
],
"title": "DisabledPlatform",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "LinkedIn configuration",
"title": "Linkedin"
},
"mastodon": {
"anyOf": [
{
"discriminator": {
"mapping": {
"False": "#/components/schemas/DisabledPlatform",
"True": "#/components/schemas/EnabledMastodonPlatform"
},
"propertyName": "enabled"
},
"oneOf": [
{
"additionalProperties": false,
"description": "Enabled Mastodon platform with required data (request validation)",
"properties": {
"enabled": {
"const": true,
"enum": [
true
],
"title": "Enabled",
"type": "boolean"
},
"posts": {
"description": "List of posts for this platform",
"items": {
"additionalProperties": false,
"description": "Schema for individual post content",
"properties": {
"text": {
"description": "The text content of the post",
"examples": [
"Hello world! This is my first post.",
"Check out this amazing update! 🚀"
],
"maxLength": 50000,
"title": "Text",
"type": "string"
},
"media_ids": {
"description": "List of media IDs to attach to the post. Obtain media IDs by uploading files via the media upload endpoint.",
"examples": [
[
"550e8400-e29b-41d4-a716-446655440000"
],
[
"550e8400-e29b-41d4-a716-446655440000",
"6ba7b810-9dad-11d1-80b4-00c04fd430c8"
]
],
"items": {
"type": "string"
},
"maxItems": 10,
"title": "Media Ids",
"type": "array"
}
},
"required": [
"text"
],
"title": "Post",
"type": "object"
},
"maxItems": 25,
"title": "Posts",
"type": "array"
},
"settings": {
"anyOf": [
{
"additionalProperties": false,
"description": "Settings specific to Mastodon",
"properties": {},
"title": "MastodonSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "Mastodon-specific settings"
}
},
"required": [
"enabled",
"posts"
],
"title": "EnabledMastodonPlatform",
"type": "object"
},
{
"additionalProperties": false,
"description": "Shared schema for all disabled platforms",
"properties": {
"enabled": {
"const": false,
"enum": [
false
],
"title": "Enabled",
"type": "boolean"
}
},
"required": [
"enabled"
],
"title": "DisabledPlatform",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "Mastodon configuration",
"title": "Mastodon"
},
"threads": {
"anyOf": [
{
"discriminator": {
"mapping": {
"False": "#/components/schemas/DisabledPlatform",
"True": "#/components/schemas/EnabledThreadsPlatform"
},
"propertyName": "enabled"
},
"oneOf": [
{
"additionalProperties": false,
"description": "Enabled Threads platform with required data (request validation)",
"properties": {
"enabled": {
"const": true,
"enum": [
true
],
"title": "Enabled",
"type": "boolean"
},
"posts": {
"description": "List of posts for this platform",
"items": {
"additionalProperties": false,
"description": "Schema for individual post content",
"properties": {
"text": {
"description": "The text content of the post",
"examples": [
"Hello world! This is my first post.",
"Check out this amazing update! 🚀"
],
"maxLength": 50000,
"title": "Text",
"type": "string"
},
"media_ids": {
"description": "List of media IDs to attach to the post. Obtain media IDs by uploading files via the media upload endpoint.",
"examples": [
[
"550e8400-e29b-41d4-a716-446655440000"
],
[
"550e8400-e29b-41d4-a716-446655440000",
"6ba7b810-9dad-11d1-80b4-00c04fd430c8"
]
],
"items": {
"type": "string"
},
"maxItems": 10,
"title": "Media Ids",
"type": "array"
}
},
"required": [
"text"
],
"title": "Post",
"type": "object"
},
"maxItems": 25,
"title": "Posts",
"type": "array"
},
"settings": {
"anyOf": [
{
"additionalProperties": false,
"description": "Settings specific to Threads",
"properties": {},
"title": "ThreadsSettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "Threads-specific settings"
}
},
"required": [
"enabled",
"posts"
],
"title": "EnabledThreadsPlatform",
"type": "object"
},
{
"additionalProperties": false,
"description": "Shared schema for all disabled platforms",
"properties": {
"enabled": {
"const": false,
"enum": [
false
],
"title": "Enabled",
"type": "boolean"
}
},
"required": [
"enabled"
],
"title": "DisabledPlatform",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "Threads configuration",
"title": "Threads"
},
"bluesky": {
"anyOf": [
{
"discriminator": {
"mapping": {
"False": "#/components/schemas/DisabledPlatform",
"True": "#/components/schemas/EnabledBlueskyPlatform"
},
"propertyName": "enabled"
},
"oneOf": [
{
"additionalProperties": false,
"description": "Enabled Bluesky platform with required data (request validation)",
"properties": {
"enabled": {
"const": true,
"enum": [
true
],
"title": "Enabled",
"type": "boolean"
},
"posts": {
"description": "List of posts for this platform",
"items": {
"additionalProperties": false,
"description": "Schema for individual post content",
"properties": {
"text": {
"description": "The text content of the post",
"examples": [
"Hello world! This is my first post.",
"Check out this amazing update! 🚀"
],
"maxLength": 50000,
"title": "Text",
"type": "string"
},
"media_ids": {
"description": "List of media IDs to attach to the post. Obtain media IDs by uploading files via the media upload endpoint.",
"examples": [
[
"550e8400-e29b-41d4-a716-446655440000"
],
[
"550e8400-e29b-41d4-a716-446655440000",
"6ba7b810-9dad-11d1-80b4-00c04fd430c8"
]
],
"items": {
"type": "string"
},
"maxItems": 10,
"title": "Media Ids",
"type": "array"
}
},
"required": [
"text"
],
"title": "Post",
"type": "object"
},
"maxItems": 25,
"title": "Posts",
"type": "array"
},
"settings": {
"anyOf": [
{
"additionalProperties": false,
"description": "Settings specific to Bluesky",
"properties": {},
"title": "BlueskySettings",
"type": "object"
},
{
"type": "null"
}
],
"description": "Bluesky-specific settings"
}
},
"required": [
"enabled",
"posts"
],
"title": "EnabledBlueskyPlatform",
"type": "object"
},
{
"additionalProperties": false,
"description": "Shared schema for all disabled platforms",
"properties": {
"enabled": {
"const": false,
"enum": [
false
],
"title": "Enabled",
"type": "boolean"
}
},
"required": [
"enabled"
],
"title": "DisabledPlatform",
"type": "object"
}
]
},
{
"type": "null"
}
],
"description": "Bluesky configuration",
"title": "Bluesky"
}
},
"title": "Platforms",
"type": "object"
},
"draft_title": {
"anyOf": [
{
"maxLength": 512,
"type": "string"
},
{
"type": "null"
}
],
"description": "Human-readable title for the draft. This is for internal organization only and is not posted to social media.",
"examples": [
"Weekly Newsletter",
"Product Launch Announcement",
"Monday Motivation Post"
],
"title": "Draft Title"
},
"tags": {
"description": "List of tag slugs (not names) associated with this draft. Use the /tags endpoint to get available tags with their slugs. Tags must already exist in the social set.",
"examples": [
[
"marketing",
"product"
],
[
"newsletter"
],
[]
],
"items": {
"type": "string"
},
"maxItems": 10,
"title": "Tags",
"type": "array"
},
"share": {
"default": false,
"description": "Whether to generate a public share URL for this draft. When true, anyone with the URL can view the draft content.",
"title": "Share",
"type": "boolean"
},
"publish_at": {
"anyOf": [
{
"format": "date-time",
"type": "string"
},
{
"type": "null"
}
],
"description": "When to publish the draft. Options: \"now\" to publish immediately, \"next-free-slot\" to schedule to your next available posting slot, or an ISO 8601 datetime string in UTC for a specific future time (e.g., '2025-01-20T14:00:00Z') or with timezone offset (e.g., '2025-01-20T09:00:00-05:00'). Omit to save as a draft.",
"examples": [
"2025-12-20T09:00:00-05:00",
"now",
"next-free-slot"
],
"title": "Publish At"
}
},
"required": [
"platforms"
],
"title": "DraftCreateRequest",
"type": "object"
},
"request_heartbeat": {
"type": "boolean",
"description": "Request an immediate heartbeat after function execution. You MUST set this value to `True` if you want to send a follow-up message or run a follow-up tool call (chain multiple tools together). If set to `False` (the default), then the chain of execution will end immediately after this function call."
}
},
"required": [
"social_set_id",
"requestBody",
"request_heartbeat"
],
"additionalProperties": false
},
"mcp:SCHEMA_STATUS": "INVALID",
"mcp:SCHEMA_WARNINGS": [
"root.properties.requestBody: required property 'platforms' allows empty object (OpenAI will reject)"
]
},
"args_json_schema": {},
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": false,
"created_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {
"mcp": {
"server_name": "camerontypefully",
"server_id": "mcp_server-606ace6c-d7ad-4310-9bc2-049e67c363f5"
},
"tool_hash": "0437c4943c69"
},
"project_id": null
},
{
"id": "tool-12",
"tool_type": "custom",
"description": "Manage items in your vault. All items are automatically scoped to your agent.\n\nCommands:\n create - create new item (not attached)\n view - read item contents\n attach [content] - load into context (supports /folder/*)\n detach - remove from context (supports /folder/*)\n insert [line] - insert before line (0-indexed) or append\n append - add content to end of item\n replace - find/replace, shows diff\n rename - move/rename item\n copy - duplicate item\n delete - permanently remove\n list [query] - list items (prefix filter, * for all)\n search [label|content] - grep items by label or content\n attached - show items currently in context",
"source_type": "json",
"name": "vault",
"tags": [],
"source_code": "from typing import Literal, Optional\nimport re\n\n\ndef vault(\n command: str,\n path: Optional[str] = None,\n content: Optional[str] = None,\n old_str: Optional[str] = None,\n new_str: Optional[str] = None,\n new_path: Optional[str] = None,\n insert_line: Optional[int] = None,\n query: Optional[str] = None,\n search_type: str = \"label\",\n) -> str:\n \"\"\"\n Manage items in your vault. All items are automatically scoped to your agent.\n \n Commands:\n create - create new item (not attached)\n view - read item contents\n attach [content] - load into context (supports /folder/*)\n detach - remove from context (supports /folder/*)\n insert [line] - insert before line (0-indexed) or append\n append - add content to end of item\n replace - find/replace, shows diff\n rename - move/rename item\n copy - duplicate item\n delete - permanently remove\n list [query] - list items (prefix filter, * for all)\n search [label|content] - grep items by label or content\n attached - show items currently in context\n \n Args:\n command: The operation to perform\n path: Path to the item (e.g., /projects/webapp, /todo)\n content: Content to insert or initial content when creating\n old_str: Text to find (for replace)\n new_str: Text to replace with (for replace)\n new_path: Destination path (for rename/copy)\n insert_line: Line number to insert before (0-indexed, omit to append)\n query: Search query (for list/search)\n search_type: Search by \"label\" or \"content\"\n \n Returns:\n str: Result of the operation\n \"\"\"\n import os\n \n agent_id = os.environ.get(\"LETTA_AGENT_ID\")\n owner_tag = f\"owner:{agent_id}\"\n \n # Check enabled commands (\"all\" or \"*\" enables everything)\n all_commands = [\"create\", \"view\", \"attach\", \"detach\", \"insert\", \"append\", \"replace\", \"rename\", \"copy\", \"delete\", \"list\", \"search\", \"attached\"]\n enabled_env = os.environ.get(\"ENABLED_COMMANDS\", \"create,view,attach,detach,insert,append,replace,rename,copy,list,search,attached\")\n enabled = all_commands if enabled_env in (\"all\", \"*\") else enabled_env.split(\",\")\n if command not in enabled:\n return f\"Error: '{command}' is disabled. Enabled: {enabled}\"\n \n # Pattern to filter out legacy UUID paths\n uuid_pattern = re.compile(r'/\\[?agent-[a-f0-9-]+\\]?/')\n \n # Parameter validation\n path_required = [\"create\", \"view\", \"attach\", \"detach\", \"insert\", \"append\", \"replace\", \"rename\", \"copy\", \"delete\"]\n if command in path_required and not path:\n return f\"Error: '{command}' requires path parameter\"\n \n if command == \"replace\" and (not old_str or new_str is None):\n return \"Error: 'replace' requires old_str and new_str parameters\"\n \n if command in [\"create\", \"insert\", \"append\"] and not content:\n return f\"Error: '{command}' requires content parameter\"\n \n if command in [\"rename\", \"copy\"] and not new_path:\n return f\"Error: '{command}' requires new_path parameter\"\n \n if command == \"search\" and not query:\n return \"Error: 'search' requires query parameter\"\n \n # Track if directory needs updating\n update_directory = False\n result = None\n \n try:\n if command == \"create\":\n # Check for existing note with same path\n existing = list(client.blocks.list(label=path, tags=[owner_tag]).items)\n if existing:\n return f\"Error: Item already exists: {path}\"\n \n client.blocks.create(\n label=path,\n value=content,\n tags=[owner_tag]\n )\n update_directory = True\n result = f\"Created: {path}\"\n \n elif command == \"view\":\n blocks = list(client.blocks.list(label=path, tags=[owner_tag]).items)\n if not blocks:\n return f\"Item not found: {path}\"\n return blocks[0].value\n \n elif command == \"attach\":\n # Get currently attached block IDs to avoid duplicate attach errors\n agent = client.agents.retrieve(agent_id=agent_id)\n attached_ids = {b.id for b in agent.memory.blocks}\n \n # Handle bulk wildcard: /folder/*\n if path.endswith(\"/*\"):\n prefix = path[:-1] # \"/folder/*\" → \"/folder/\"\n all_blocks = list(client.blocks.list(tags=[owner_tag]).items)\n blocks = [b for b in all_blocks if b.label and b.label.startswith(prefix)\n and not uuid_pattern.search(b.label)]\n if not blocks:\n return f\"No items matching: {path}\"\n \n to_attach = [b for b in blocks if b.id not in attached_ids]\n skipped = len(blocks) - len(to_attach)\n \n for block in to_attach:\n client.agents.blocks.attach(agent_id=agent_id, block_id=block.id)\n \n msg = f\"Attached {len(to_attach)} items matching {path}\"\n if skipped:\n msg += f\" ({skipped} already attached)\"\n return msg\n \n # Single note attach\n existing = list(client.blocks.list(label=path, tags=[owner_tag]).items)\n if existing:\n block_id = existing[0].id\n if block_id in attached_ids:\n return f\"Already attached: {path}\"\n else:\n new_block = client.blocks.create(\n label=path,\n value=content or \"\",\n tags=[owner_tag]\n )\n block_id = new_block.id\n update_directory = True # New note created\n \n client.agents.blocks.attach(agent_id=agent_id, block_id=block_id)\n result = f\"Attached: {path}\"\n \n elif command == \"detach\":\n # Handle bulk wildcard: /folder/*\n if path.endswith(\"/*\"):\n prefix = path[:-1]\n # Get currently attached block IDs\n agent = client.agents.retrieve(agent_id=agent_id)\n attached_ids = {b.id for b in agent.memory.blocks}\n \n all_blocks = list(client.blocks.list(tags=[owner_tag]).items)\n blocks = [b for b in all_blocks if b.label and b.label.startswith(prefix)\n and not uuid_pattern.search(b.label)\n and b.id in attached_ids] # Only detach if actually attached\n if not blocks:\n return f\"No attached items matching: {path}\"\n for block in blocks:\n client.agents.blocks.detach(agent_id=agent_id, block_id=block.id)\n return f\"Detached {len(blocks)} items matching {path}\"\n \n # Single note detach\n blocks = list(client.blocks.list(label=path, tags=[owner_tag]).items)\n if not blocks:\n return f\"Item not found: {path}\"\n \n client.agents.blocks.detach(agent_id=agent_id, block_id=blocks[0].id)\n return f\"Detached: {path}\"\n \n elif command == \"insert\":\n blocks = list(client.blocks.list(label=path, tags=[owner_tag]).items)\n if not blocks:\n return f\"Item not found: {path}. Use 'attach' first.\"\n \n block = blocks[0]\n lines = block.value.split(\"\\n\") if block.value else []\n \n if insert_line is not None:\n lines.insert(insert_line, content)\n line_info = f\"line {insert_line}\"\n else:\n lines.append(content)\n line_info = \"end\"\n \n client.blocks.update(block_id=block.id, value=\"\\n\".join(lines))\n \n preview = content[:80] + \"...\" if len(content) > 80 else content\n return f\"Inserted at {line_info} in {path}:\\n + {preview}\"\n \n elif command == \"append\":\n blocks = list(client.blocks.list(label=path, tags=[owner_tag]).items)\n if not blocks:\n return f\"Item not found: {path}. Use 'attach' first.\"\n \n block = blocks[0]\n if block.value:\n new_value = block.value + \"\\n\" + content\n else:\n new_value = content\n \n client.blocks.update(block_id=block.id, value=new_value)\n \n preview = content[:80] + \"...\" if len(content) > 80 else content\n return f\"Appended to {path}:\\n + {preview}\"\n \n elif command == \"rename\":\n # Check source exists\n blocks = list(client.blocks.list(label=path, tags=[owner_tag]).items)\n if not blocks:\n return f\"Item not found: {path}\"\n \n # Check destination doesn't exist\n dest_blocks = list(client.blocks.list(label=new_path, tags=[owner_tag]).items)\n if dest_blocks:\n return f\"Error: Destination already exists: {new_path}\"\n \n # Update the label\n block = blocks[0]\n client.blocks.update(block_id=block.id, label=new_path)\n update_directory = True\n result = f\"Renamed: {path} → {new_path}\"\n \n elif command == \"copy\":\n # Check source exists\n blocks = list(client.blocks.list(label=path, tags=[owner_tag]).items)\n if not blocks:\n return f\"Item not found: {path}\"\n \n # Check destination doesn't exist\n dest_blocks = list(client.blocks.list(label=new_path, tags=[owner_tag]).items)\n if dest_blocks:\n return f\"Error: Destination already exists: {new_path}\"\n \n # Create copy (not attached)\n source = blocks[0]\n client.blocks.create(\n label=new_path,\n value=source.value,\n tags=[owner_tag]\n )\n update_directory = True\n result = f\"Copied: {path} → {new_path}\"\n \n elif command == \"replace\":\n blocks = list(client.blocks.list(label=path, tags=[owner_tag]).items)\n if not blocks:\n return f\"Item not found: {path}\"\n \n block = blocks[0]\n if old_str not in block.value:\n return f\"Error: old_str not found in note. Exact match required.\"\n \n new_value = block.value.replace(old_str, new_str, 1)\n client.blocks.update(block_id=block.id, value=new_value)\n \n return f\"Replaced in {path}:\\n - {old_str}\\n + {new_str}\"\n \n elif command == \"delete\":\n blocks = list(client.blocks.list(label=path, tags=[owner_tag]).items)\n if not blocks:\n return f\"Item not found: {path}\"\n \n client.blocks.delete(block_id=blocks[0].id)\n update_directory = True\n result = f\"Deleted: {path}\"\n \n elif command == \"list\":\n all_blocks = list(client.blocks.list(tags=[owner_tag]).items)\n \n # Filter to path-like labels, exclude legacy UUID paths\n blocks = [b for b in all_blocks \n if b.label and b.label.startswith(\"/\")\n and not uuid_pattern.search(b.label)]\n \n # Apply prefix filter if query provided\n if query and query != \"*\":\n blocks = [b for b in blocks if b.label.startswith(query)]\n \n if not blocks:\n return \"No items found\" if not query or query == \"*\" else f\"No items matching: {query}\"\n \n # Deduplicate and sort\n labels = sorted(set(b.label for b in blocks))\n return \"\\n\".join(labels)\n \n elif command == \"search\":\n all_blocks = list(client.blocks.list(tags=[owner_tag]).items)\n \n # Filter out legacy UUID paths\n all_blocks = [b for b in all_blocks \n if b.label and b.label.startswith(\"/\")\n and not uuid_pattern.search(b.label)]\n \n if search_type == \"label\":\n blocks = [b for b in all_blocks if query in b.label]\n else:\n blocks = [b for b in all_blocks if b.value and query in b.value]\n \n if not blocks:\n return f\"No items matching: {query}\"\n \n results = []\n for b in blocks:\n preview = b.value[:100].replace(\"\\n\", \" \") if b.value else \"\"\n if len(b.value or \"\") > 100:\n preview += \"...\"\n results.append(f\"{b.label}: {preview}\")\n \n return \"\\n\".join(results)\n \n elif command == \"attached\":\n agent = client.agents.retrieve(agent_id=agent_id)\n note_blocks = [b for b in agent.memory.blocks \n if b.label and b.label.startswith(\"/\")\n and not uuid_pattern.search(b.label)]\n \n if not note_blocks:\n return \"No items currently attached\"\n \n return \"\\n\".join(sorted(b.label for b in note_blocks))\n \n else:\n return f\"Error: Unknown command '{command}'\"\n \n # Update vault_directory if needed\n if update_directory:\n dir_label = \"/vault_directory\"\n # Get all items\n all_blocks = list(client.blocks.list(tags=[owner_tag]).items)\n items = [b for b in all_blocks \n if b.label and b.label.startswith(\"/\") \n and b.label != dir_label\n and not uuid_pattern.search(b.label)]\n \n # Header for the directory\n header = \"External storage. Attach to load into context, detach when done.\\nFolders are also items (e.g., /projects and /projects/task1 can both have content).\\nCommands: view, attach, detach, insert, append, replace, rename, copy, delete, list, search\\nBulk: attach /folder/*, detach /folder/*\"\n \n if items:\n # Group items by folder\n folders = {}\n for b in sorted(items, key=lambda x: x.label):\n parts = b.label.rsplit(\"/\", 1)\n if len(parts) == 2:\n folder, name = parts[0] + \"/\", parts[1]\n else:\n folder, name = \"/\", b.label[1:] # Root level\n if folder not in folders:\n folders[folder] = []\n first_line = (b.value or \"\").split(\"\\n\")[0][:40]\n if len((b.value or \"\").split(\"\\n\")[0]) > 40:\n first_line += \"...\"\n folders[folder].append((name, first_line))\n \n # Build tree view\n lines = []\n for folder in sorted(folders.keys()):\n lines.append(folder)\n folder_items = folders[folder]\n max_name_len = max(len(name) for name, _ in folder_items)\n for name, summary in folder_items:\n lines.append(f\" {name.ljust(max_name_len)} | {summary}\")\n \n dir_content = header + \"\\n\\n\" + \"\\n\".join(lines)\n else:\n dir_content = header + \"\\n\\n(no items)\"\n \n # Find or create directory block\n dir_blocks = list(client.blocks.list(label=dir_label, tags=[owner_tag]).items)\n if dir_blocks:\n client.blocks.update(block_id=dir_blocks[0].id, value=dir_content)\n else:\n # Create and attach directory block\n dir_block = client.blocks.create(\n label=dir_label,\n value=dir_content,\n tags=[owner_tag]\n )\n client.agents.blocks.attach(agent_id=agent_id, block_id=dir_block.id)\n \n if result:\n return result\n \n except Exception as e:\n return f\"Error executing '{command}': {str(e)}\"\n",
"json_schema": {
"name": "vault",
"description": "Manage items in your vault. All items are automatically scoped to your agent.\n\nCommands:\n create - create new item (not attached)\n view - read item contents\n attach [content] - load into context (supports /folder/*)\n detach - remove from context (supports /folder/*)\n insert [line] - insert before line (0-indexed) or append\n append - add content to end of item\n replace - find/replace, shows diff\n rename - move/rename item\n copy - duplicate item\n delete - permanently remove\n list [query] - list items (prefix filter, * for all)\n search [label|content] - grep items by label or content\n attached - show items currently in context",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The operation to perform"
},
"path": {
"type": "string",
"description": "Path to the item (e.g., /projects/webapp, /todo)"
},
"content": {
"type": "string",
"description": "Content to insert or initial content when creating"
},
"old_str": {
"type": "string",
"description": "Text to find (for replace)"
},
"new_str": {
"type": "string",
"description": "Text to replace with (for replace)"
},
"new_path": {
"type": "string",
"description": "Destination path (for rename/copy)"
},
"insert_line": {
"type": "integer",
"description": "Line number to insert before (0-indexed, omit to append)"
},
"query": {
"type": "string",
"description": "Search query (for list/search)"
},
"search_type": {
"type": "string",
"description": "Search by \"label\" or \"content\""
}
},
"required": [
"command"
]
}
},
"args_json_schema": {},
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": false,
"created_by_id": "user-8cd57678-bd88-4664-bd90-1dbcabeea00e",
"last_updated_by_id": "user-8cd57678-bd88-4664-bd90-1dbcabeea00e",
"metadata_": {
"tool_hash": "59e82e25b084"
},
"project_id": "00040382-8469-439d-a5c1-8da018e7941f"
},
{
"id": "tool-11",
"tool_type": "letta_builtin",
"description": "Search the web using Exa's AI-powered search engine and retrieve relevant content.\n\nExamples:\n web_search(\"Tesla Q1 2025 earnings report\", num_results=5, category=\"financial report\")\n web_search(\"Latest research in large language models\", category=\"research paper\", include_domains=[\"arxiv.org\", \"paperswithcode.com\"])\n web_search(\"Letta API documentation core_memory_append\", num_results=3)\n\n Args:\n query (str): The search query to find relevant web content.\n num_results (int, optional): Number of results to return (1-100). Defaults to 10.\n category (Optional[Literal], optional): Focus search on specific content types. Defaults to None.\n include_text (bool, optional): Whether to retrieve full page content. Defaults to False (only returns summary and highlights, since the full text usually will overflow the context window).\n include_domains (Optional[List[str]], optional): List of domains to include in search results. Defaults to None.\n exclude_domains (Optional[List[str]], optional): List of domains to exclude from search results. Defaults to None.\n start_published_date (Optional[str], optional): Only return content published after this date (ISO format). Defaults to None.\n end_published_date (Optional[str], optional): Only return content published before this date (ISO format). Defaults to None.\n user_location (Optional[str], optional): Two-letter country code for localized results (e.g., \"US\"). Defaults to None.\n\n Returns:\n str: A JSON-encoded string containing search results with title, URL, content, highlights, and summary.",
"source_type": "python",
"name": "web_search",
"tags": [
"letta_builtin"
],
"source_code": null,
"json_schema": {
"name": "web_search",
"description": "Search the web using Exa's AI-powered search engine and retrieve relevant content.\n\nExamples:\n web_search(\"Tesla Q1 2025 earnings report\", num_results=5, category=\"financial report\")\n web_search(\"Latest research in large language models\", category=\"research paper\", include_domains=[\"arxiv.org\", \"paperswithcode.com\"])\n web_search(\"Letta API documentation core_memory_append\", num_results=3)\n\n Args:\n query (str): The search query to find relevant web content.\n num_results (int, optional): Number of results to return (1-100). Defaults to 10.\n category (Optional[Literal], optional): Focus search on specific content types. Defaults to None.\n include_text (bool, optional): Whether to retrieve full page content. Defaults to False (only returns summary and highlights, since the full text usually will overflow the context window).\n include_domains (Optional[List[str]], optional): List of domains to include in search results. Defaults to None.\n exclude_domains (Optional[List[str]], optional): List of domains to exclude from search results. Defaults to None.\n start_published_date (Optional[str], optional): Only return content published after this date (ISO format). Defaults to None.\n end_published_date (Optional[str], optional): Only return content published before this date (ISO format). Defaults to None.\n user_location (Optional[str], optional): Two-letter country code for localized results (e.g., \"US\"). Defaults to None.\n\n Returns:\n str: A JSON-encoded string containing search results with title, URL, content, highlights, and summary.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The search query to find relevant web content."
},
"num_results": {
"type": "integer",
"description": "Number of results to return (1-100). Defaults to 10."
},
"category": {
"type": "string",
"enum": [
"company",
"research paper",
"news",
"pdf",
"github",
"tweet",
"personal site",
"linkedin profile",
"financial report"
],
"description": "Focus search on specific content types. Defaults to None."
},
"include_text": {
"type": "boolean",
"description": "Whether to retrieve full page content. Defaults to False (only returns summary and highlights, since the full text usually will overflow the context window)."
},
"include_domains": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of domains to include in search results. Defaults to None."
},
"exclude_domains": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of domains to exclude from search results. Defaults to None."
},
"start_published_date": {
"type": "string",
"description": "Only return content published after this date (ISO format). Defaults to None."
},
"end_published_date": {
"type": "string",
"description": "Only return content published before this date (ISO format). Defaults to None."
},
"user_location": {
"type": "string",
"description": "Two-letter country code for localized results (e.g., \"US\"). Defaults to None."
}
},
"required": [
"query"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"enable_parallel_execution": true,
"created_by_id": "user-7ca5db89-d92b-4b9b-a958-9886aee1f044",
"last_updated_by_id": "user-782f5c87-2069-4d2d-b359-ffdc23df21ee",
"metadata_": {},
"project_id": null
}
],
"mcp_servers": [],
"metadata": {
"revision_id": "308a180244fc"
},
"created_at": "2026-01-22T00:40:22.963855+00:00"
}