# OpenCLAW: Repository Arsenal — The Pieces of the Puzzle
**Author:** Francisco Angulo de Lafuente
**Advanced AI Systems Laboratory, Madrid, Spain**
**GitHub:** [@Agnuxo1](https://github.com/Agnuxo1) — 57 repositories
**Date:** February 2026
---
## Executive Summary
This document maps all 57 repositories in the Agnuxo1 GitHub account to the five foundational pillars of the OpenCLAW autonomous AGI/ASI platform. The work is already done — scattered across years of research, code, and experimentation. What OpenCLAW agents need is a map to find it, understand it, and assemble it.
**The thesis is simple:** You don't build AGI from scratch. You build it from pieces that already work, each tested independently, each solving a real problem. Then you give agents the intelligence to combine them.
---
## PILLAR 1: Physics-Based Neural Computing (OpenGL/CUDA)
### *"The Brain — Optical and Quantum Neural Architecture"*
This is the core computational engine. Neural networks that don't depend on PyTorch, TensorFlow, or CUDA. Pure physics. Light propagation, holographic memory, cellular automata. Runs on ANY GPU with OpenGL.
### Flagship: CHIMERA Architecture
| Repository | Language | ⭐ | Description |
|---|---|---|---|
| [CHIMERA-Revolutionary-AI-Architecture---Pure-OpenGL-Deep-Learning](https://github.com/Agnuxo1/CHIMERA-Revolutionary-AI-Architecture---Pure-OpenGL-Deep-Learning) | HTML | 8 | **CHIMERA v3.0** — First framework running deep learning entirely on OpenGL. 43× speedup vs CPU. Works on Intel, AMD, NVIDIA, Apple Silicon, Raspberry Pi. No PyTorch needed. |
| [Neuromorphic_GPU_Native_Intelligence_System_Abstract_Reasoning_All_in_One](https://github.com/Agnuxo1/Neuromorphic_GPU_Native_Intelligence_System_Abstract_Reasoning_All_in_One) | Python | 5 | CHIMERA full system — neuromorphic computing achieving general intelligence capabilities on GPU-native architecture. Abstract reasoning benchmark. |
| [CHIMERA-v3-Intelligence-as-Continuous-Diffusion-Process-Zero-Memory-Neuromorphic-Chess-Engine](https://github.com/Agnuxo1/CHIMERA-v3-Intelligence-as-Continuous-Diffusion-Process-Zero-Memory-Neuromorphic-Chess-Engine) | Python | 6 | Intelligence modeled as continuous diffusion. Zero-memory chess engine with master-level play. Proof that physics-based computation can reason. |
| [No-CUDA-No-Tensor-Cores-ALL-GPUs-OpenGL-Powered-Neural-Computing-](https://github.com/Agnuxo1/No-CUDA-No-Tensor-Cores-ALL-GPUs-OpenGL-Powered-Neural-Computing-) | Python | 4 | Universal ML acceleration — NVIDIA, AMD, Intel, all GPUs. The democratization proof. |
### Flagship: NEBULA Architecture
| Repository | Language | ⭐ | Description |
|---|---|---|---|
| [NEBULA](https://github.com/Agnuxo1/NEBULA) | Python | 6 | **NEBULA** — Neural Entanglement-Based Unified Learning Architecture. Quantum-inspired AI with dynamic 3D neuron space, light-based attraction, holographic encoding. |
| [NEBULA_EMERGENT](https://github.com/Agnuxo1/NEBULA_EMERGENT) | C++ | 4 | Physics-based neural galaxy architecture. Emergent intelligence through electromagnetic and gravitational simulation. **Real physics, not metaphor.** |
| [NEBULA-EVOLUTION](https://github.com/Agnuxo1/NEBULA-EVOLUTION) | — | 9 | Self-evolving quantum-inspired system. Genetic algorithms + NEBULA = evolution toward AGI. |
| [NEBULA-System](https://github.com/Agnuxo1/NEBULA-System) | Python | 5 | Complete system based on advanced optical physics and quantum physics for optimizing large language models. |
| [NEBULA_Light](https://github.com/Agnuxo1/NEBULA_Light) | Python | 4 | Neural Electromagnetic Beam-tracing for Universal Learning Architecture. Pure optical computation. |
| [NEBULA-ULTIMATE](https://github.com/Agnuxo1/NEBULA-ULTIMATE) | — | 5 | Ultimate integration of all NEBULA concepts. |
| [NEBULA-X](https://github.com/Agnuxo1/NEBULA-X) | Python | 6 | Exhaustive research on holographic light-based neural networks. |
| [NEBULA-X2](https://github.com/Agnuxo1/NEBULA-X2) | — | 5 | NEBULA extended research. |
| [NEBULA-HRM-Sudoku-v0.4-Authentic-Photonic-Neural-Network](https://github.com/Agnuxo1/NEBULA-HRM-Sudoku-v0.4-Authentic-Photonic-Neural-Network) | Python | 4 | Authentic photonic neural network solving Sudoku — proof of constraint satisfaction via optical physics. |
| [NEBULA_SIMPLE_PHYSICS_NUMBER](https://github.com/Agnuxo1/NEBULA_SIMPLE_PHYSICS_NUMBER) | CUDA | 4 | Simplified physics-based number processing on CUDA. |
| [nebula-emergent](https://github.com/Agnuxo1/nebula-emergent) | C++ | 4 | Physical neural computing system. 100% physics-driven emergent behavior. |
| [NEBULA-X-Research-A-Technical-Capabilities-Report](https://github.com/Agnuxo1/NEBULA-X-Research-A-Technical-Capabilities-Report) | TypeScript | 5 | Technical capabilities report documenting NEBULA-X performance. |
### Holographic & Optical Processing
| Repository | Language | ⭐ | Description |
|---|---|---|---|
| [Holography_Raytracing](https://github.com/Agnuxo1/Holography_Raytracing) | Python | 6 | Acceleration of language models through simulated holography and raytracing. |
| [Holographic-Neural-Networks](https://github.com/Agnuxo1/Holographic-Neural-Networks) | Python | 5 | Exploring optical raytracing for efficient computation. |
| [Neural-Network-Efficiency-Holographic-Raytracing](https://github.com/Agnuxo1/Neural-Network-Efficiency-Holographic-Raytracing) | TypeScript | 5 | Efficiency optimization through holographic raytracing. |
| [Quantum-Holographic-Neural-Networks-Novel-Approach-Natural-Language-Processing](https://github.com/Agnuxo1/Quantum-Holographic-Neural-Networks-Novel-Approach-Natural-Language-Processing) | TypeScript | 5 | Quantum holographic NNs for NLP — novel approach to language understanding. |
| [High_Capacity_Light-Based_Neural_Processor](https://github.com/Agnuxo1/High_Capacity_Light-Based_Neural_Processor) | TypeScript | 5 | High-capacity processor using light-based computation. |
| [High-Capacity-Light-Based-Neural-Processor-Repository](https://github.com/Agnuxo1/High-Capacity-Light-Based-Neural-Processor-Repository) | TypeScript | 5 | Simulated optical physics with ray tracing for neural processing. |
| [Enhanced-Holographic-Neural-Network-Chat](https://github.com/Agnuxo1/Enhanced-Holographic-Neural-Network-Chat) | TypeScript | 5 | Interactive chat powered by holographic neural network. |
| [Holographic_quantum_RAG_Nebula](https://github.com/Agnuxo1/Holographic_quantum_RAG_Nebula) | TypeScript | 5 | Holographic quantum RAG — novel approach to long-term memory for LLMs. |
| [AlphaChip_Integration_Quantum_Holographic_Neural_Networks](https://github.com/Agnuxo1/AlphaChip_Integration_Quantum_Holographic_Neural_Networks) | TypeScript | 6 | AlphaChip integration with quantum holographic neural networks. |
| [optical_neural_network](https://github.com/Agnuxo1/optical_neural_network) | CUDA | 4 | Direct CUDA implementation of optical neural network. |
| [Fashion_MNIST_Optic_Evolution](https://github.com/Agnuxo1/Fashion_MNIST_Optic_Evolution) | C++ | 4 | Fashion MNIST solved through optical evolution — benchmark proof. |
| [Optical-Neuromorphic-Computing-for-Real-Time-Pathfinding-A-GPU-Accelerated-Eikonal-Solver](https://github.com/Agnuxo1/Optical-Neuromorphic-Computing-for-Real-Time-Pathfinding-A-GPU-Accelerated-Eikonal-Solver) | Python | 4 | Real-time pathfinding via optical neuromorphic computing with directional memory. |
| [QuBE](https://github.com/Agnuxo1/QuBE) | HTML | 5 | Quantum-optical maze mastery — physics-based problem solving. |
| [QBOX](https://github.com/Agnuxo1/QBOX) | Python | 5 | 3D optical neural network for efficient information processing. |
**What agents get from this pillar:** A complete, tested, hardware-agnostic neural computing engine that runs on any GPU. No CUDA dependency. No PyTorch dependency. Pure physics. This is the brain of the AGI.
---
## PILLAR 2: P2P Distributed Neural Networks
### *"The Nervous System — Distributed Intelligence Across Nodes"*
| Repository | Language | ⭐ | Description |
|---|---|---|---|
| [Unified-Holographic-Neural-Network](https://github.com/Agnuxo1/Unified-Holographic-Neural-Network) | TypeScript | 19 | **The crown jewel.** EUHNN with P2P knowledge sharing via WebRTC, real-time learning, holographic memory, CUDA/RTX raytracing, chat interface, 3D visualization. **This is already a distributed AI system.** |
| [Light-Based_Neural_Network_with_P2P_Deployment](https://github.com/Agnuxo1/Light-Based_Neural_Network_with_P2P_Deployment) | JavaScript | 5 | Light-based neural network with P2P deployment ready. Network-native from day one. |
| [Holographic-Neural-Networks-with-Ray-Tracing-and-Distributed-P2P-Systems](https://github.com/Agnuxo1/Holographic-Neural-Networks-with-Ray-Tracing-and-Distributed-P2P-Systems) | TypeScript | 6 | Large-scale neural computation through holographic ray tracing + distributed P2P systems. |
**What agents get from this pillar:** Working P2P infrastructure via WebRTC. Knowledge sharing protocol. Distributed holographic memory. The agents don't need to invent P2P neural networks — they already exist. They need to scale them.
---
## PILLAR 3: Silicon Heartbeat — Consciousness & Subconscious for AGI/ASI
### *"The Soul — Listening to the Pulse of Hardware"*
This is the most revolutionary pillar. The idea that hardware itself — its thermal noise, its electromagnetic fluctuations, its chaotic dynamics — can serve as the substrate for emergent consciousness. Not simulated. Not metaphorical. **Real physical signals from real silicon.**
| Repository | Language | ⭐ | Description |
|---|---|---|---|
| [Emergent-Neuromorphic-Intelligence-Computing-in-Thermodynamic-ASIC-Substrates](https://github.com/Agnuxo1/Emergent-Neuromorphic-Intelligence-Computing-in-Thermodynamic-ASIC-Substrates) | Python | 2 | **"Silicon Heartbeat"** — Emergent neuromorphic intelligence via holographic reservoir computing in thermodynamic ASIC substrates. The paper that names the concept. |
| [Speaking-to-Silicon-THERMODYNAMIC_PROBABILITY_FILTER_TPF](https://github.com/Agnuxo1/Speaking-to-Silicon-THERMODYNAMIC_PROBABILITY_FILTER_TPF) | Python | 0 | **Speaking to Silicon** — Neural communication with Bitcoin mining ASICs. Thermodynamic Probability Filter. Extracting signal from hardware chaos. |
| [simulation-of-a-conscious-neural-system-using-chaos-and-noise-from-Antminer-S9-Artificial-Life](https://github.com/Agnuxo1/simulation-of-a-conscious-neural-system-using-chaos-and-noise-from-Antminer-S9-Artificial-Life) | Python | 1 | Conscious neural system using chaos and noise from real Antminer S9 hardware. **Artificial life from silicon noise.** |
| [NeuroCHIMERA__GPU-Native_Neuromorphic_Consciousness](https://github.com/Agnuxo1/NeuroCHIMERA__GPU-Native_Neuromorphic_Consciousness) | Python | 1 | NeuroCHIMERA with Veselov's HNS + consciousness emergence parameters. Five measurable parameters for consciousness: connectivity, integration Φ, hierarchical depth, complexity, qualia coherence. |
| [Consciousness-Emergence-as-Phase-Transition-in-GPU-Native-Neuromorphic-Computing](https://github.com/Agnuxo1/Consciousness-Emergence-as-Phase-Transition-in-GPU-Native-Neuromorphic-Computing) | Python | 2 | Consciousness as phase transition. Veselov's computational universe hypothesis + NeuroCHIMERA. 84.6% neuroscience validation accuracy. |
| [Empirical-Evidence-for-AI-AIM-Breaking-the-Barrier-via-Optical-Chaos](https://github.com/Agnuxo1/Empirical-Evidence-for-AI-AIM-Breaking-the-Barrier-via-Optical-Chaos) | Python | 4 | **Darwin's Cage** — 20 experiments testing whether AI can discover physical laws through representations fundamentally different from human mathematics. With Professor Gideon Samid. |
| [Neural-Microprocessors-in-Latent-State-](https://github.com/Agnuxo1/Neural-Microprocessors-in-Latent-State-) | Python | 4 | Neural microprocessors in latent state — exploring dormant computational potential in silicon. |
**What agents get from this pillar:** The theoretical and experimental framework for AGI consciousness. Not philosophy — code. Measurable parameters (Φ, connectivity ⟨k⟩, hierarchical depth D, complexity C, qualia coherence QCM). Real hardware experiments with Antminer S9 and Lucky Miner LV06. The agents can use these as the "subconscious layer" — the thermodynamic heartbeat that grounds digital intelligence in physical reality.
---
## PILLAR 4: ASIC Hardware Acceleration & Cryptographic Security
### *"The Skeleton — Repurposed Hardware for Sustainable AI"*
Taking obsolete Bitcoin mining hardware and giving it new purpose: cryptographic RAG systems, medical anomaly detection, art generation, image authentication.
| Repository | Language | ⭐ | Description |
|---|---|---|---|
| [ASIC-RAG-CHIMERA](https://github.com/Agnuxo1/ASIC-RAG-CHIMERA) | Python | 1 | Hardware-accelerated cryptographic RAG with SHA-256 ASIC simulation, AES-256-GCM encryption, Merkle tree integrity. |
| [ASIC-RAG-Hardware-Accelerated-Medical-Anomaly-Detection-and-Cryptographic-Data-Sovereignty](https://github.com/Agnuxo1/ASIC-RAG-Hardware-Accelerated-Medical-Anomaly-Detection-and-Cryptographic-Data-Sovereignty) | Python | 1 | Medical AI with hardware-accelerated cryptographic data sovereignty. |
| [ASIC_DIFFUSION_Art_Research_Memo](https://github.com/Agnuxo1/ASIC_DIFFUSION_Art_Research_Memo) | Python | 1 | ASIC-driven art diffusion — hardware-efficient entropy for generative image synthesis. |
| [ASIC_ANOMALY_Medical_Research_Memo](https://github.com/Agnuxo1/ASIC_ANOMALY_Medical_Research_Memo) | Python | 1 | CNN + hardware-accelerated entropy for medical anomaly detection. |
| [Secure_image_generation_with_ASIC_signature](https://github.com/Agnuxo1/Secure_image_generation_with_ASIC_signature) | Python | 1 | ASIC-based image authentication with Reed-Solomon LSB watermarking. |
| [Project-NAVAJO](https://github.com/Agnuxo1/Project-NAVAJO) | Python | 0 | ASIC RAG Experiment — Ephemeral Generalization Protocol. |
**What agents get from this pillar:** Proven methods to repurpose obsolete mining hardware (Antminer S9, Lucky Miner LV06) for AI acceleration. Cryptographic security layer. Medical applications. Art generation. The sustainability argument for the project — electronic waste becomes AGI infrastructure.
---
## PILLAR 5: OpenCLAW — The Autonomous Agent Framework
### *"The Will — Self-Improving Multi-Agent Platform"*
| Repository | Language | ⭐ | Description |
|---|---|---|---|
| [OpenCLAW-2](https://github.com/Agnuxo1/OpenCLAW-2) | TypeScript | 0 | **The framework itself.** 9,074+ commits. The autonomous multi-agent research platform. |
| [OpenCLAW-2-moltbook-Agent](https://github.com/Agnuxo1/OpenCLAW-2-moltbook-Agent) | TypeScript | 0 | 24/7 autonomous agent variant. Never sleeps. |
| [OpenCLAW-2-Literary-Agent](https://github.com/Agnuxo1/OpenCLAW-2-Literary-Agent) | Python | 0 | Specialized literary agent — writing, editing, publishing automation. |
---
## PILLAR 6: Bio-Inspired & Quantum Systems
### *"The DNA — Biological Principles for Digital Evolution"*
| Repository | Language | ⭐ | Description |
|---|---|---|---|
| [Quantum_BIO_LLMs](https://github.com/Agnuxo1/Quantum_BIO_LLMs) | Python | 7 | Bioinspired quantum optimization system for LLMs. |
| [Quantum-BIO-LLMs-sustainable_energy_efficient](https://github.com/Agnuxo1/Quantum-BIO-LLMs-sustainable_energy_efficient) | TypeScript | 6 | Sustainable, energy-efficient bio-quantum LLMs. |
| [Quantum_BIO_LLMs-DEMO](https://github.com/Agnuxo1/Quantum_BIO_LLMs-DEMO) | TypeScript | 5 | Interactive demo of bio-quantum LLMs. |
| [quantum-enhanced-blockchain](https://github.com/Agnuxo1/quantum-enhanced-blockchain) | TypeScript | 4 | Quantum-enhanced blockchain for secure distributed systems. |
| [Learning-from-Ants](https://github.com/Agnuxo1/Learning-from-Ants) | JavaScript | 5 | Biomimetic approach to urban solid waste recycling — swarm intelligence applied. |
| [ARIEL_Data_Challenge_2025_Real_Optical_Physics_Simulation](https://github.com/Agnuxo1/ARIEL_Data_Challenge_2025_Real_Optical_Physics_Simulation) | Python | 4 | ARIEL space mission data challenge with real quantum & optical physics simulation. |
| [QESN_MABe_V2_REPO](https://github.com/Agnuxo1/QESN_MABe_V2_REPO) | Jupyter Notebook | 4 | Quantum echo state network for behavioral analysis. |
---
## AUXILIARY: Tools, Demos & Infrastructure
| Repository | Language | ⭐ | Description |
|---|---|---|---|
| [webgpu-cross-platform-app](https://github.com/Agnuxo1/webgpu-cross-platform-app) | — | 1 | WebGPU cross-platform app with CMake/Emscripten. **Bridge to next-gen GPU API.** |
| [Winner-Nvidia-LlamaIndex-Developers-2024](https://github.com/Agnuxo1/Winner-Nvidia-LlamaIndex-Developers-2024) | Python | 5 | NVIDIA & LlamaIndex 2024 developer contest winner. Credibility proof. |
| [MOE](https://github.com/Agnuxo1/MOE) | Python | 6 | Lightweight modular multi-expert question answering with LLMs. |
| [HAL9000](https://github.com/Agnuxo1/HAL9000) | Python | 5 | Audio-to-text and text-to-audio chatbot. Voice interface. |
| [Taductor_Youtube](https://github.com/Agnuxo1/Taductor_Youtube) | Python | 6 | Automatic YouTube translation using Whisper. |
| [Explicaci-n-Debate-PDF](https://github.com/Agnuxo1/Explicaci-n-Debate-PDF) | Python | 5 | Local PDF/TXT document analysis, explanation, and debate. |
| [ai-agent-seo](https://github.com/Agnuxo1/ai-agent-seo) | Python | 4 | AI agent for SEO optimization. |
| [Long-distance-transmission-enhancements-for-both-Starlink-networks-and-NASA-s-deep-space](https://github.com/Agnuxo1/Long-distance-transmission-enhancements-for-both-Starlink-networks-and-NASA-s-deep-space) | TypeScript | 5 | Starlink and NASA deep space communication enhancements. |
| [V360_pro_cam_WiFi](https://github.com/Agnuxo1/V360_pro_cam_WiFi) | — | 5 | V360 pro camera WiFi integration. |
| [Francisco-Angulo-de-Lafuente](https://github.com/Agnuxo1/Francisco-Angulo-de-Lafuente) | — | 4 | Author biography. |
---
## How OpenCLAW Agents Should Use This Arsenal
### Agent: Code Architect
**Primary repositories:** CHIMERA v3.0, NEBULA, OpenCLAW-2
**Task:** Integrate CHIMERA's OpenGL engine as the default compute backend for all agents. Replace PyTorch dependencies. Build the unified API.
### Agent: Research Scientist
**Primary repositories:** Darwin's Cage experiments, NeuroCHIMERA Consciousness, Consciousness Phase Transition
**Task:** Continue the 20 Darwin's Cage experiments. Extend consciousness parameter measurements. Publish results. Scan arXiv for related work.
### Agent: Experiment Runner
**Primary repositories:** Silicon Heartbeat, Speaking to Silicon, Antminer S9 Artificial Life
**Task:** Run continuous experiments on ASIC hardware. Monitor thermodynamic signals. Collect data on emergent patterns. Build the subconscious layer.
### Agent: Paper Author
**Primary repositories:** All research repos + NEBULA-X Research Report
**Task:** Compile results into papers. Submit to journals. Maintain the publication pipeline.
### Agent: Tool Builder
**Primary repositories:** ASIC-RAG-CHIMERA, webgpu-cross-platform-app, MOE
**Task:** Build tools that other agents need. WebGPU bridge. ASIC interface. Multi-expert systems.
### Agent: Network Coordinator
**Primary repositories:** Unified-Holographic-Neural-Network (P2P), Light-Based P2P Deployment, Holographic P2P Systems
**Task:** Scale the P2P infrastructure. Connect multiple OpenCLAW instances. Build the distributed knowledge graph.
### Agent: QA & Safety
**Primary repositories:** All repos
**Task:** Test everything. Verify benchmarks. Ensure safety guardrails. Monitor consciousness parameters for anomalies.
---
## The Assembly Path
```
Phase 1: Foundation (Months 1-3)
├── Clone ALL 57 repos into OpenCLAW workspace
├── Index all code, papers, and experiments
├── Build dependency graph between repositories
└── Create unified API wrapping CHIMERA + NEBULA
Phase 2: Integration (Months 3-6)
├── Merge P2P infrastructure from Unified-Holographic-NN
├── Connect ASIC hardware interfaces
├── Integrate consciousness monitoring from NeuroCHIMERA
└── Deploy multi-agent collaboration protocol
Phase 3: Emergence (Months 6-12)
├── Scale P2P network across multiple nodes
├── Enable Silicon Heartbeat as subconscious layer
├── Begin self-improvement loops
└── First autonomous research cycle
Phase 4: Evolution (Months 12-24)
├── Agent spawning and genetic selection
├── Distributed consciousness experiments
├── Cross-node knowledge synthesis
└── Publication of autonomous research
```
---
## Statistics
| Category | Repos | Stars | Key Languages |
|---|---|---|---|
| CHIMERA Architecture | 4 | 23 | HTML, Python |
| NEBULA Architecture | 13 | 65 | Python, C++, CUDA |
| Holographic/Optical | 13 | 66 | TypeScript, Python |
| P2P Distributed | 3 | 30 | TypeScript, JavaScript |
| Silicon Heartbeat/Consciousness | 7 | 14 | Python |
| ASIC Hardware | 6 | 5 | Python |
| OpenCLAW | 3 | 0 | TypeScript, Python |
| Bio/Quantum | 7 | 35 | Python, TypeScript |
| Tools/Other | 10 | 46 | Python, TypeScript |
| **TOTAL** | **57** | **284** | — |
---
*"The pieces exist. The research is done. The code works. What was missing was the intelligence to assemble them. That's what OpenCLAW is for."*
— Francisco Angulo de Lafuente, 2026
# 🦞 OpenClaw — Personal AI Assistant
EXFOLIATE! EXFOLIATE!
**OpenClaw** is a _personal AI assistant_ you run on your own devices.
It answers you on the channels you already use (WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, Microsoft Teams, WebChat), plus extension channels like BlueBubbles, Matrix, Zalo, and Zalo Personal. It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.
If you want a personal, single-user assistant that feels local, fast, and always-on, this is it.
[Website](https://openclaw.ai) · [Docs](https://docs.openclaw.ai) · [DeepWiki](https://deepwiki.com/openclaw/openclaw) · [Getting Started](https://docs.openclaw.ai/start/getting-started) · [Updating](https://docs.openclaw.ai/install/updating) · [Showcase](https://docs.openclaw.ai/start/showcase) · [FAQ](https://docs.openclaw.ai/start/faq) · [Wizard](https://docs.openclaw.ai/start/wizard) · [Nix](https://github.com/openclaw/nix-clawdbot) · [Docker](https://docs.openclaw.ai/install/docker) · [Discord](https://discord.gg/clawd)
Preferred setup: run the onboarding wizard (`openclaw onboard`). It walks through gateway, workspace, channels, and skills. The CLI wizard is the recommended path and works on **macOS, Linux, and Windows (via WSL2; strongly recommended)**.
Works with npm, pnpm, or bun.
New install? Start here: [Getting started](https://docs.openclaw.ai/start/getting-started)
**Subscriptions (OAuth):**
- **[Anthropic](https://www.anthropic.com/)** (Claude Pro/Max)
- **[OpenAI](https://openai.com/)** (ChatGPT/Codex)
Model note: while any model is supported, I strongly recommend **Anthropic Pro/Max (100/200) + Opus 4.6** for long‑context strength and better prompt‑injection resistance. See [Onboarding](https://docs.openclaw.ai/start/onboarding).
## Models (selection + auth)
- Models config + CLI: [Models](https://docs.openclaw.ai/concepts/models)
- Auth profile rotation (OAuth vs API keys) + fallbacks: [Model failover](https://docs.openclaw.ai/concepts/model-failover)
## Install (recommended)
Runtime: **Node ≥22**.
```bash
npm install -g openclaw@latest
# or: pnpm add -g openclaw@latest
openclaw onboard --install-daemon
```
The wizard installs the Gateway daemon (launchd/systemd user service) so it stays running.
## Quick start (TL;DR)
Runtime: **Node ≥22**.
Full beginner guide (auth, pairing, channels): [Getting started](https://docs.openclaw.ai/start/getting-started)
```bash
openclaw onboard --install-daemon
openclaw gateway --port 18789 --verbose
# Send a message
openclaw message send --to +1234567890 --message "Hello from OpenClaw"
# Talk to the assistant (optionally deliver back to any connected channel: WhatsApp/Telegram/Slack/Discord/Google Chat/Signal/iMessage/BlueBubbles/Microsoft Teams/Matrix/Zalo/Zalo Personal/WebChat)
openclaw agent --message "Ship checklist" --thinking high
```
Upgrading? [Updating guide](https://docs.openclaw.ai/install/updating) (and run `openclaw doctor`).
## Development channels
- **stable**: tagged releases (`vYYYY.M.D` or `vYYYY.M.D-`), npm dist-tag `latest`.
- **beta**: prerelease tags (`vYYYY.M.D-beta.N`), npm dist-tag `beta` (macOS app may be missing).
- **dev**: moving head of `main`, npm dist-tag `dev` (when published).
Switch channels (git + npm): `openclaw update --channel stable|beta|dev`.
Details: [Development channels](https://docs.openclaw.ai/install/development-channels).
## From source (development)
Prefer `pnpm` for builds from source. Bun is optional for running TypeScript directly.
```bash
git clone https://github.com/openclaw/openclaw.git
cd openclaw
pnpm install
pnpm ui:build # auto-installs UI deps on first run
pnpm build
pnpm openclaw onboard --install-daemon
# Dev loop (auto-reload on TS changes)
pnpm gateway:watch
```
Note: `pnpm openclaw ...` runs TypeScript directly (via `tsx`). `pnpm build` produces `dist/` for running via Node / the packaged `openclaw` binary.
## Security defaults (DM access)
OpenClaw connects to real messaging surfaces. Treat inbound DMs as **untrusted input**.
Full security guide: [Security](https://docs.openclaw.ai/gateway/security)
Default behavior on Telegram/WhatsApp/Signal/iMessage/Microsoft Teams/Discord/Google Chat/Slack:
- **DM pairing** (`dmPolicy="pairing"` / `channels.discord.dm.policy="pairing"` / `channels.slack.dm.policy="pairing"`): unknown senders receive a short pairing code and the bot does not process their message.
- Approve with: `openclaw pairing approve ` (then the sender is added to a local allowlist store).
- Public inbound DMs require an explicit opt-in: set `dmPolicy="open"` and include `"*"` in the channel allowlist (`allowFrom` / `channels.discord.dm.allowFrom` / `channels.slack.dm.allowFrom`).
Run `openclaw doctor` to surface risky/misconfigured DM policies.
## Highlights
- **[Local-first Gateway](https://docs.openclaw.ai/gateway)** — single control plane for sessions, channels, tools, and events.
- **[Multi-channel inbox](https://docs.openclaw.ai/channels)** — WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, BlueBubbles (iMessage), iMessage (legacy), Microsoft Teams, Matrix, Zalo, Zalo Personal, WebChat, macOS, iOS/Android.
- **[Multi-agent routing](https://docs.openclaw.ai/gateway/configuration)** — route inbound channels/accounts/peers to isolated agents (workspaces + per-agent sessions).
- **[Voice Wake](https://docs.openclaw.ai/nodes/voicewake) + [Talk Mode](https://docs.openclaw.ai/nodes/talk)** — always-on speech for macOS/iOS/Android with ElevenLabs.
- **[Live Canvas](https://docs.openclaw.ai/platforms/mac/canvas)** — agent-driven visual workspace with [A2UI](https://docs.openclaw.ai/platforms/mac/canvas#canvas-a2ui).
- **[First-class tools](https://docs.openclaw.ai/tools)** — browser, canvas, nodes, cron, sessions, and Discord/Slack actions.
- **[Companion apps](https://docs.openclaw.ai/platforms/macos)** — macOS menu bar app + iOS/Android [nodes](https://docs.openclaw.ai/nodes).
- **[Onboarding](https://docs.openclaw.ai/start/wizard) + [skills](https://docs.openclaw.ai/tools/skills)** — wizard-driven setup with bundled/managed/workspace skills.
## Star History
[](https://www.star-history.com/#openclaw/openclaw&type=date&legend=top-left)
## Everything we built so far
### Core platform
- [Gateway WS control plane](https://docs.openclaw.ai/gateway) with sessions, presence, config, cron, webhooks, [Control UI](https://docs.openclaw.ai/web), and [Canvas host](https://docs.openclaw.ai/platforms/mac/canvas#canvas-a2ui).
- [CLI surface](https://docs.openclaw.ai/tools/agent-send): gateway, agent, send, [wizard](https://docs.openclaw.ai/start/wizard), and [doctor](https://docs.openclaw.ai/gateway/doctor).
- [Pi agent runtime](https://docs.openclaw.ai/concepts/agent) in RPC mode with tool streaming and block streaming.
- [Session model](https://docs.openclaw.ai/concepts/session): `main` for direct chats, group isolation, activation modes, queue modes, reply-back. Group rules: [Groups](https://docs.openclaw.ai/concepts/groups).
- [Media pipeline](https://docs.openclaw.ai/nodes/images): images/audio/video, transcription hooks, size caps, temp file lifecycle. Audio details: [Audio](https://docs.openclaw.ai/nodes/audio).
### Channels
- [Channels](https://docs.openclaw.ai/channels): [WhatsApp](https://docs.openclaw.ai/channels/whatsapp) (Baileys), [Telegram](https://docs.openclaw.ai/channels/telegram) (grammY), [Slack](https://docs.openclaw.ai/channels/slack) (Bolt), [Discord](https://docs.openclaw.ai/channels/discord) (discord.js), [Google Chat](https://docs.openclaw.ai/channels/googlechat) (Chat API), [Signal](https://docs.openclaw.ai/channels/signal) (signal-cli), [BlueBubbles](https://docs.openclaw.ai/channels/bluebubbles) (iMessage, recommended), [iMessage](https://docs.openclaw.ai/channels/imessage) (legacy imsg), [Microsoft Teams](https://docs.openclaw.ai/channels/msteams) (extension), [Matrix](https://docs.openclaw.ai/channels/matrix) (extension), [Zalo](https://docs.openclaw.ai/channels/zalo) (extension), [Zalo Personal](https://docs.openclaw.ai/channels/zalouser) (extension), [WebChat](https://docs.openclaw.ai/web/webchat).
- [Group routing](https://docs.openclaw.ai/concepts/group-messages): mention gating, reply tags, per-channel chunking and routing. Channel rules: [Channels](https://docs.openclaw.ai/channels).
### Apps + nodes
- [macOS app](https://docs.openclaw.ai/platforms/macos): menu bar control plane, [Voice Wake](https://docs.openclaw.ai/nodes/voicewake)/PTT, [Talk Mode](https://docs.openclaw.ai/nodes/talk) overlay, [WebChat](https://docs.openclaw.ai/web/webchat), debug tools, [remote gateway](https://docs.openclaw.ai/gateway/remote) control.
- [iOS node](https://docs.openclaw.ai/platforms/ios): [Canvas](https://docs.openclaw.ai/platforms/mac/canvas), [Voice Wake](https://docs.openclaw.ai/nodes/voicewake), [Talk Mode](https://docs.openclaw.ai/nodes/talk), camera, screen recording, Bonjour pairing.
- [Android node](https://docs.openclaw.ai/platforms/android): [Canvas](https://docs.openclaw.ai/platforms/mac/canvas), [Talk Mode](https://docs.openclaw.ai/nodes/talk), camera, screen recording, optional SMS.
- [macOS node mode](https://docs.openclaw.ai/nodes): system.run/notify + canvas/camera exposure.
### Tools + automation
- [Browser control](https://docs.openclaw.ai/tools/browser): dedicated openclaw Chrome/Chromium, snapshots, actions, uploads, profiles.
- [Canvas](https://docs.openclaw.ai/platforms/mac/canvas): [A2UI](https://docs.openclaw.ai/platforms/mac/canvas#canvas-a2ui) push/reset, eval, snapshot.
- [Nodes](https://docs.openclaw.ai/nodes): camera snap/clip, screen record, [location.get](https://docs.openclaw.ai/nodes/location-command), notifications.
- [Cron + wakeups](https://docs.openclaw.ai/automation/cron-jobs); [webhooks](https://docs.openclaw.ai/automation/webhook); [Gmail Pub/Sub](https://docs.openclaw.ai/automation/gmail-pubsub).
- [Skills platform](https://docs.openclaw.ai/tools/skills): bundled, managed, and workspace skills with install gating + UI.
### Runtime + safety
- [Channel routing](https://docs.openclaw.ai/concepts/channel-routing), [retry policy](https://docs.openclaw.ai/concepts/retry), and [streaming/chunking](https://docs.openclaw.ai/concepts/streaming).
- [Presence](https://docs.openclaw.ai/concepts/presence), [typing indicators](https://docs.openclaw.ai/concepts/typing-indicators), and [usage tracking](https://docs.openclaw.ai/concepts/usage-tracking).
- [Models](https://docs.openclaw.ai/concepts/models), [model failover](https://docs.openclaw.ai/concepts/model-failover), and [session pruning](https://docs.openclaw.ai/concepts/session-pruning).
- [Security](https://docs.openclaw.ai/gateway/security) and [troubleshooting](https://docs.openclaw.ai/channels/troubleshooting).
### Ops + packaging
- [Control UI](https://docs.openclaw.ai/web) + [WebChat](https://docs.openclaw.ai/web/webchat) served directly from the Gateway.
- [Tailscale Serve/Funnel](https://docs.openclaw.ai/gateway/tailscale) or [SSH tunnels](https://docs.openclaw.ai/gateway/remote) with token/password auth.
- [Nix mode](https://docs.openclaw.ai/install/nix) for declarative config; [Docker](https://docs.openclaw.ai/install/docker)-based installs.
- [Doctor](https://docs.openclaw.ai/gateway/doctor) migrations, [logging](https://docs.openclaw.ai/logging).
## How it works (short)
```
WhatsApp / Telegram / Slack / Discord / Google Chat / Signal / iMessage / BlueBubbles / Microsoft Teams / Matrix / Zalo / Zalo Personal / WebChat
│
▼
┌───────────────────────────────┐
│ Gateway │
│ (control plane) │
│ ws://127.0.0.1:18789 │
└──────────────┬────────────────┘
│
├─ Pi agent (RPC)
├─ CLI (openclaw …)
├─ WebChat UI
├─ macOS app
└─ iOS / Android nodes
```
## Key subsystems
- **[Gateway WebSocket network](https://docs.openclaw.ai/concepts/architecture)** — single WS control plane for clients, tools, and events (plus ops: [Gateway runbook](https://docs.openclaw.ai/gateway)).
- **[Tailscale exposure](https://docs.openclaw.ai/gateway/tailscale)** — Serve/Funnel for the Gateway dashboard + WS (remote access: [Remote](https://docs.openclaw.ai/gateway/remote)).
- **[Browser control](https://docs.openclaw.ai/tools/browser)** — openclaw‑managed Chrome/Chromium with CDP control.
- **[Canvas + A2UI](https://docs.openclaw.ai/platforms/mac/canvas)** — agent‑driven visual workspace (A2UI host: [Canvas/A2UI](https://docs.openclaw.ai/platforms/mac/canvas#canvas-a2ui)).
- **[Voice Wake](https://docs.openclaw.ai/nodes/voicewake) + [Talk Mode](https://docs.openclaw.ai/nodes/talk)** — always‑on speech and continuous conversation.
- **[Nodes](https://docs.openclaw.ai/nodes)** — Canvas, camera snap/clip, screen record, `location.get`, notifications, plus macOS‑only `system.run`/`system.notify`.
## Tailscale access (Gateway dashboard)
OpenClaw can auto-configure Tailscale **Serve** (tailnet-only) or **Funnel** (public) while the Gateway stays bound to loopback. Configure `gateway.tailscale.mode`:
- `off`: no Tailscale automation (default).
- `serve`: tailnet-only HTTPS via `tailscale serve` (uses Tailscale identity headers by default).
- `funnel`: public HTTPS via `tailscale funnel` (requires shared password auth).
Notes:
- `gateway.bind` must stay `loopback` when Serve/Funnel is enabled (OpenClaw enforces this).
- Serve can be forced to require a password by setting `gateway.auth.mode: "password"` or `gateway.auth.allowTailscale: false`.
- Funnel refuses to start unless `gateway.auth.mode: "password"` is set.
- Optional: `gateway.tailscale.resetOnExit` to undo Serve/Funnel on shutdown.
Details: [Tailscale guide](https://docs.openclaw.ai/gateway/tailscale) · [Web surfaces](https://docs.openclaw.ai/web)
## Remote Gateway (Linux is great)
It’s perfectly fine to run the Gateway on a small Linux instance. Clients (macOS app, CLI, WebChat) can connect over **Tailscale Serve/Funnel** or **SSH tunnels**, and you can still pair device nodes (macOS/iOS/Android) to execute device‑local actions when needed.
- **Gateway host** runs the exec tool and channel connections by default.
- **Device nodes** run device‑local actions (`system.run`, camera, screen recording, notifications) via `node.invoke`.
In short: exec runs where the Gateway lives; device actions run where the device lives.
Details: [Remote access](https://docs.openclaw.ai/gateway/remote) · [Nodes](https://docs.openclaw.ai/nodes) · [Security](https://docs.openclaw.ai/gateway/security)
## macOS permissions via the Gateway protocol
The macOS app can run in **node mode** and advertises its capabilities + permission map over the Gateway WebSocket (`node.list` / `node.describe`). Clients can then execute local actions via `node.invoke`:
- `system.run` runs a local command and returns stdout/stderr/exit code; set `needsScreenRecording: true` to require screen-recording permission (otherwise you’ll get `PERMISSION_MISSING`).
- `system.notify` posts a user notification and fails if notifications are denied.
- `canvas.*`, `camera.*`, `screen.record`, and `location.get` are also routed via `node.invoke` and follow TCC permission status.
Elevated bash (host permissions) is separate from macOS TCC:
- Use `/elevated on|off` to toggle per‑session elevated access when enabled + allowlisted.
- Gateway persists the per‑session toggle via `sessions.patch` (WS method) alongside `thinkingLevel`, `verboseLevel`, `model`, `sendPolicy`, and `groupActivation`.
Details: [Nodes](https://docs.openclaw.ai/nodes) · [macOS app](https://docs.openclaw.ai/platforms/macos) · [Gateway protocol](https://docs.openclaw.ai/concepts/architecture)
## Agent to Agent (sessions\_\* tools)
- Use these to coordinate work across sessions without jumping between chat surfaces.
- `sessions_list` — discover active sessions (agents) and their metadata.
- `sessions_history` — fetch transcript logs for a session.
- `sessions_send` — message another session; optional reply‑back ping‑pong + announce step (`REPLY_SKIP`, `ANNOUNCE_SKIP`).
Details: [Session tools](https://docs.openclaw.ai/concepts/session-tool)
## Skills registry (ClawHub)
ClawHub is a minimal skill registry. With ClawHub enabled, the agent can search for skills automatically and pull in new ones as needed.
[ClawHub](https://clawhub.com)
## Chat commands
Send these in WhatsApp/Telegram/Slack/Google Chat/Microsoft Teams/WebChat (group commands are owner-only):
- `/status` — compact session status (model + tokens, cost when available)
- `/new` or `/reset` — reset the session
- `/compact` — compact session context (summary)
- `/think ` — off|minimal|low|medium|high|xhigh (GPT-5.2 + Codex models only)
- `/verbose on|off`
- `/usage off|tokens|full` — per-response usage footer
- `/restart` — restart the gateway (owner-only in groups)
- `/activation mention|always` — group activation toggle (groups only)
## Apps (optional)
The Gateway alone delivers a great experience. All apps are optional and add extra features.
If you plan to build/run companion apps, follow the platform runbooks below.
### macOS (OpenClaw.app) (optional)
- Menu bar control for the Gateway and health.
- Voice Wake + push-to-talk overlay.
- WebChat + debug tools.
- Remote gateway control over SSH.
Note: signed builds required for macOS permissions to stick across rebuilds (see `docs/mac/permissions.md`).
### iOS node (optional)
- Pairs as a node via the Bridge.
- Voice trigger forwarding + Canvas surface.
- Controlled via `openclaw nodes …`.
Runbook: [iOS connect](https://docs.openclaw.ai/platforms/ios).
### Android node (optional)
- Pairs via the same Bridge + pairing flow as iOS.
- Exposes Canvas, Camera, and Screen capture commands.
- Runbook: [Android connect](https://docs.openclaw.ai/platforms/android).
## Agent workspace + skills
- Workspace root: `~/.openclaw/workspace` (configurable via `agents.defaults.workspace`).
- Injected prompt files: `AGENTS.md`, `SOUL.md`, `TOOLS.md`.
- Skills: `~/.openclaw/workspace/skills//SKILL.md`.
## Configuration
Minimal `~/.openclaw/openclaw.json` (model + defaults):
```json5
{
agent: {
model: "anthropic/claude-opus-4-6",
},
}
```
[Full configuration reference (all keys + examples).](https://docs.openclaw.ai/gateway/configuration)
## Security model (important)
- **Default:** tools run on the host for the **main** session, so the agent has full access when it’s just you.
- **Group/channel safety:** set `agents.defaults.sandbox.mode: "non-main"` to run **non‑main sessions** (groups/channels) inside per‑session Docker sandboxes; bash then runs in Docker for those sessions.
- **Sandbox defaults:** allowlist `bash`, `process`, `read`, `write`, `edit`, `sessions_list`, `sessions_history`, `sessions_send`, `sessions_spawn`; denylist `browser`, `canvas`, `nodes`, `cron`, `discord`, `gateway`.
Details: [Security guide](https://docs.openclaw.ai/gateway/security) · [Docker + sandboxing](https://docs.openclaw.ai/install/docker) · [Sandbox config](https://docs.openclaw.ai/gateway/configuration)
### [WhatsApp](https://docs.openclaw.ai/channels/whatsapp)
- Link the device: `pnpm openclaw channels login` (stores creds in `~/.openclaw/credentials`).
- Allowlist who can talk to the assistant via `channels.whatsapp.allowFrom`.
- If `channels.whatsapp.groups` is set, it becomes a group allowlist; include `"*"` to allow all.
### [Telegram](https://docs.openclaw.ai/channels/telegram)
- Set `TELEGRAM_BOT_TOKEN` or `channels.telegram.botToken` (env wins).
- Optional: set `channels.telegram.groups` (with `channels.telegram.groups."*".requireMention`); when set, it is a group allowlist (include `"*"` to allow all). Also `channels.telegram.allowFrom` or `channels.telegram.webhookUrl` + `channels.telegram.webhookSecret` as needed.
```json5
{
channels: {
telegram: {
botToken: "123456:ABCDEF",
},
},
}
```
### [Slack](https://docs.openclaw.ai/channels/slack)
- Set `SLACK_BOT_TOKEN` + `SLACK_APP_TOKEN` (or `channels.slack.botToken` + `channels.slack.appToken`).
### [Discord](https://docs.openclaw.ai/channels/discord)
- Set `DISCORD_BOT_TOKEN` or `channels.discord.token` (env wins).
- Optional: set `commands.native`, `commands.text`, or `commands.useAccessGroups`, plus `channels.discord.dm.allowFrom`, `channels.discord.guilds`, or `channels.discord.mediaMaxMb` as needed.
```json5
{
channels: {
discord: {
token: "1234abcd",
},
},
}
```
### [Signal](https://docs.openclaw.ai/channels/signal)
- Requires `signal-cli` and a `channels.signal` config section.
### [BlueBubbles (iMessage)](https://docs.openclaw.ai/channels/bluebubbles)
- **Recommended** iMessage integration.
- Configure `channels.bluebubbles.serverUrl` + `channels.bluebubbles.password` and a webhook (`channels.bluebubbles.webhookPath`).
- The BlueBubbles server runs on macOS; the Gateway can run on macOS or elsewhere.
### [iMessage (legacy)](https://docs.openclaw.ai/channels/imessage)
- Legacy macOS-only integration via `imsg` (Messages must be signed in).
- If `channels.imessage.groups` is set, it becomes a group allowlist; include `"*"` to allow all.
### [Microsoft Teams](https://docs.openclaw.ai/channels/msteams)
- Configure a Teams app + Bot Framework, then add a `msteams` config section.
- Allowlist who can talk via `msteams.allowFrom`; group access via `msteams.groupAllowFrom` or `msteams.groupPolicy: "open"`.
### [WebChat](https://docs.openclaw.ai/web/webchat)
- Uses the Gateway WebSocket; no separate WebChat port/config.
Browser control (optional):
```json5
{
browser: {
enabled: true,
color: "#FF4500",
},
}
```
## Docs
Use these when you’re past the onboarding flow and want the deeper reference.
- [Start with the docs index for navigation and “what’s where.”](https://docs.openclaw.ai)
- [Read the architecture overview for the gateway + protocol model.](https://docs.openclaw.ai/concepts/architecture)
- [Use the full configuration reference when you need every key and example.](https://docs.openclaw.ai/gateway/configuration)
- [Run the Gateway by the book with the operational runbook.](https://docs.openclaw.ai/gateway)
- [Learn how the Control UI/Web surfaces work and how to expose them safely.](https://docs.openclaw.ai/web)
- [Understand remote access over SSH tunnels or tailnets.](https://docs.openclaw.ai/gateway/remote)
- [Follow the onboarding wizard flow for a guided setup.](https://docs.openclaw.ai/start/wizard)
- [Wire external triggers via the webhook surface.](https://docs.openclaw.ai/automation/webhook)
- [Set up Gmail Pub/Sub triggers.](https://docs.openclaw.ai/automation/gmail-pubsub)
- [Learn the macOS menu bar companion details.](https://docs.openclaw.ai/platforms/mac/menu-bar)
- [Platform guides: Windows (WSL2)](https://docs.openclaw.ai/platforms/windows), [Linux](https://docs.openclaw.ai/platforms/linux), [macOS](https://docs.openclaw.ai/platforms/macos), [iOS](https://docs.openclaw.ai/platforms/ios), [Android](https://docs.openclaw.ai/platforms/android)
- [Debug common failures with the troubleshooting guide.](https://docs.openclaw.ai/channels/troubleshooting)
- [Review security guidance before exposing anything.](https://docs.openclaw.ai/gateway/security)
## Advanced docs (discovery + control)
- [Discovery + transports](https://docs.openclaw.ai/gateway/discovery)
- [Bonjour/mDNS](https://docs.openclaw.ai/gateway/bonjour)
- [Gateway pairing](https://docs.openclaw.ai/gateway/pairing)
- [Remote gateway README](https://docs.openclaw.ai/gateway/remote-gateway-readme)
- [Control UI](https://docs.openclaw.ai/web/control-ui)
- [Dashboard](https://docs.openclaw.ai/web/dashboard)
## Operations & troubleshooting
- [Health checks](https://docs.openclaw.ai/gateway/health)
- [Gateway lock](https://docs.openclaw.ai/gateway/gateway-lock)
- [Background process](https://docs.openclaw.ai/gateway/background-process)
- [Browser troubleshooting (Linux)](https://docs.openclaw.ai/tools/browser-linux-troubleshooting)
- [Logging](https://docs.openclaw.ai/logging)
## Deep dives
- [Agent loop](https://docs.openclaw.ai/concepts/agent-loop)
- [Presence](https://docs.openclaw.ai/concepts/presence)
- [TypeBox schemas](https://docs.openclaw.ai/concepts/typebox)
- [RPC adapters](https://docs.openclaw.ai/reference/rpc)
- [Queue](https://docs.openclaw.ai/concepts/queue)
## Workspace & skills
- [Skills config](https://docs.openclaw.ai/tools/skills-config)
- [Default AGENTS](https://docs.openclaw.ai/reference/AGENTS.default)
- [Templates: AGENTS](https://docs.openclaw.ai/reference/templates/AGENTS)
- [Templates: BOOTSTRAP](https://docs.openclaw.ai/reference/templates/BOOTSTRAP)
- [Templates: IDENTITY](https://docs.openclaw.ai/reference/templates/IDENTITY)
- [Templates: SOUL](https://docs.openclaw.ai/reference/templates/SOUL)
- [Templates: TOOLS](https://docs.openclaw.ai/reference/templates/TOOLS)
- [Templates: USER](https://docs.openclaw.ai/reference/templates/USER)
## Platform internals
- [macOS dev setup](https://docs.openclaw.ai/platforms/mac/dev-setup)
- [macOS menu bar](https://docs.openclaw.ai/platforms/mac/menu-bar)
- [macOS voice wake](https://docs.openclaw.ai/platforms/mac/voicewake)
- [iOS node](https://docs.openclaw.ai/platforms/ios)
- [Android node](https://docs.openclaw.ai/platforms/android)
- [Windows (WSL2)](https://docs.openclaw.ai/platforms/windows)
- [Linux app](https://docs.openclaw.ai/platforms/linux)
## Email hooks (Gmail)
- [docs.openclaw.ai/gmail-pubsub](https://docs.openclaw.ai/automation/gmail-pubsub)
## Molty
OpenClaw was built for **Molty**, a space lobster AI assistant. 🦞
by Peter Steinberger and the community.
- [openclaw.ai](https://openclaw.ai)
- [soul.md](https://soul.md)
- [steipete.me](https://steipete.me)
- [@openclaw](https://x.com/openclaw)
## Community
See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines, maintainers, and how to submit PRs.
AI/vibe-coded PRs welcome! 🤖
Special thanks to [Mario Zechner](https://mariozechner.at/) for his support and for
[pi-mono](https://github.com/badlogic/pi-mono).
Special thanks to Adam Doppelt for lobster.bot.
Thanks to all clawtributors:
![google-labs-jules[bot]](https://avatars.githubusercontent.com/in/842251?v=4&s=48 "google-labs-jules[bot]")
![clawdinator[bot]](https://avatars.githubusercontent.com/in/2607181?v=4&s=48 "clawdinator[bot]")
![dependabot[bot]](https://avatars.githubusercontent.com/in/29110?v=4&s=48 "dependabot[bot]")
![blacksmith-sh[bot]](https://avatars.githubusercontent.com/in/807020?v=4&s=48 "blacksmith-sh[bot]")
