# Agentic Architectures ### Thirty-five production-grade agentic AI patterns. End to end. A library *and* a living textbook — real LLM outputs, provider-agnostic, deterministic-picker discipline throughout, and a comparative benchmark leaderboard that ranks every architecture against every relevant task.
[![CI](https://img.shields.io/github/actions/workflow/status/FareedKhan-dev/all-agentic-architectures/ci.yml?branch=main&label=CI&logo=githubactions&logoColor=white&style=for-the-badge&color=0a0a0a)](https://github.com/FareedKhan-dev/all-agentic-architectures/actions/workflows/ci.yml) [![Docs](https://img.shields.io/github/actions/workflow/status/FareedKhan-dev/all-agentic-architectures/docs.yml?branch=main&label=DOCS&logo=materialformkdocs&logoColor=white&style=for-the-badge&color=6366f1)](https://fareedkhan-dev.github.io/all-agentic-architectures/) [![PyPI](https://img.shields.io/pypi/v/agentic-architectures?style=for-the-badge&logo=pypi&logoColor=white&label=PyPI&color=a855f7)](https://pypi.org/project/agentic-architectures/) [![License](https://img.shields.io/badge/license-MIT-ec4899?style=for-the-badge&logo=opensourceinitiative&logoColor=white)](LICENSE)
Quickstart Documentation Architectures Benchmarks Open in Codespaces

  35  

ARCHITECTURES

  283  

PASSING TESTS

  17  

BENCHMARK TASKS

  9  

LLM PROVIDERS

  0  

MOCKED RUNS

--- ## Overview A single Python library that packages every major agentic AI pattern from the literature as a runnable `Architecture` class with a uniform contract. Each pattern ships with a fully executed Jupyter notebook whose theory is written *against* the captured run — not synthetic examples. The library is multi-provider (Nebius, OpenAI, Anthropic, Groq, Ollama, Together, Fireworks, Mistral, Google) and built on top of LangGraph state machines. The central technical discipline of the repository is the **deterministic-picker pattern** — every LLM-as-Scorer surface has the LLM commit to categorical features (booleans, enums) and lets Python compose the deciding signal. This is the universal escape from the LLM-as-Scorer flat-band pathology, applied in 13 of 35 architectures; 9 more are architecturally immune by design. --- ## Quickstart ```bash pip install "agentic-architectures[nebius,faiss,tavily]" ``` ```python from agentic_architectures import get_llm from agentic_architectures.architectures import Reflection arch = Reflection(llm=get_llm(), max_iterations=2, target_score=8) result = arch.run("Write a haiku about a glacier.") print(result.output) print("score:", result.metadata["final_score"], "/ 10") ``` Same `.run(task)` interface across all 35 architectures. Same `ArchitectureResult` return shape. Swap the class, swap the pattern — your downstream code does not change.
Set up a virtualenv from a fresh clone
```bash git clone https://github.com/FareedKhan-dev/all-agentic-architectures cd all-agentic-architectures python -m venv .venv .venv\Scripts\activate # Windows source .venv/bin/activate # macOS / Linux pip install -e ".[dev,test,docs,nebius,faiss,tavily,networkx]" cp .env.example .env # then fill in NEBIUS_API_KEY etc. pytest -q # 283 tests pass in ~30s ```
--- ## Architecture families
#### [Reasoning & Reflection](docs/architectures/index.md#reasoning--reflection) Self-critique loops that drive answer quality up through iteration.

Reflection · Reflexion · Chain-of-Verification · Self-Discover · Constitutional AI 		#### [Sampling & Search](docs/architectures/index.md#sampling--search) Sample many paths or grow a tree with rewards.

Self-Consistency · Tree of Thoughts · LATS · Mental Loop · Ensemble 		#### [Retrieval (RAG)](docs/architectures/index.md#retrieval-rag) Ground every claim — five retrieval shapes.

Agentic RAG · Corrective RAG · Self-RAG · Adaptive RAG · GraphRAG
#### [Memory](docs/architectures/index.md#memory) Learn across calls — pick the storage shape.

Episodic + Semantic · Graph Memory · MemGPT · Voyager · Agent Workflow Memory 		#### [Tools & Actions](docs/architectures/index.md#tools--actions) From one search tool to a real Chromium browser.

Tool Use · ReAct · Planning · PEV · SWE-Agent · BrowserAgent 		#### [Multi-Agent](docs/architectures/index.md#multi-agent) Specialists, debate, multi-perspective research.

Multi-Agent · Blackboard · Debate · STORM · Meta-Controller
#### [Safety & Routing](docs/architectures/index.md#safety--routing) Categorical actions through deterministic Python gates.

Dry-Run · Reflexive Metacognitive · Computer Use 		#### [Specialty](docs/architectures/index.md#specialty) Patterns with a unique shape.

RLHF Self-Improvement · Cellular Automata 		#### [Cross-cutting](docs/architectures/index.md#cross-cutting) Patterns that appear across families.

Deterministic-picker · Memory variants
--- ## The 35 architectures
Reasoning & Reflection | Architecture | Pattern | Reference | |---|---|---| | **Reflection** | Generate → critique → refine | Madaan 2023 | | **Reflexion** | Verbal reflections in episodic memory | Shinn 2023 | | **Chain-of-Verification (CoVe)** | Verify each baseline claim independently | Dhuliawala 2023 | | **Self-Discover** | SELECT → ADAPT → IMPLEMENT → SOLVE | Zhou 2024 | | **Constitutional AI** | Per-rule pass/fail → revise | Bai 2022 |
Sampling & Search | Architecture | Pattern | Reference | |---|---|---| | **Self-Consistency** | Sample N paths, majority-vote | Wang 2022 | | **Tree of Thoughts** | Beam search over thoughts | Yao 2023 | | **LATS** | MCTS tree with reward backup | Zhou 2024 | | **Mental Loop** | Simulate → score (deterministic-picker) | this repo | | **Ensemble** | N voters, weighted aggregation | this repo |
Retrieval (RAG) | Architecture | Pattern | Reference | |---|---|---| | **Agentic RAG** | Agent decides when & what to retrieve | LangGraph reference | | **Corrective RAG (CRAG)** | Grade docs, fall back to web | Yan 2024 | | **Self-RAG** | Per-doc reflection tokens | Asai 2024 | | **Adaptive RAG** | Pre-route by query complexity | Jeong 2024 | | **GraphRAG** | KG + community summaries | Microsoft 2024 |
Memory | Architecture | Stored unit | Reference | |---|---|---| | **Episodic + Semantic** | Conversation turns + triples | Park 2023 | | **Graph Memory** | (subject, predicate, object) triples | this repo | | **MemGPT** | OS-style context + archival tiers | Packer 2023 | | **Voyager** | Reusable Python skills (real subprocess) | Wang 2023 | | **Agent Workflow Memory** | High-level workflow recipes | Wang 2024 |
Tools & Actions | Architecture | Pattern | Reference | |---|---|---| | **Tool Use** | Agent with one tool | LangChain reference | | **ReAct** | Thought → Action → Observation | Yao 2022 | | **Planning** | Decompose → execute → replan | Wei 2022 | | **Plan-Execute-Verify (PEV)** | Post-execution verification per step | this repo | | **SWE-Agent** | Sandboxed file-system agent | Yang 2024 | | **BrowserAgent** | **Real Playwright** + safety gate | Anthropic Computer-Use 2024 |
Multi-Agent | Architecture | Pattern | Reference | |---|---|---| | **Multi-Agent** | Supervisor + specialists | LangGraph reference | | **Blackboard** | Shared workspace + agents | classical AI | | **Debate** | N agents × K rounds | Du 2023 | | **STORM** | Multi-perspective research → article | Shao 2024 | | **Meta-Controller** | Router over architectures | this repo |
Safety, Routing & Specialty | Architecture | Pattern | Reference | |---|---|---| | **Dry-Run** | Propose → simulate → approval gate | this repo | | **Reflexive Metacognitive** | Self-aware capability routing | this repo | | **RLHF Self-Improvement** | Multi-dim deterministic scoring + archive | this repo | | **Cellular Automata** | LLM rules over a grid | this repo |
--- ## Provider compatibility
ProviderInstall extraNotes
Nebius  (default)[nebius]Llama-3.3-70B + Qwen3-Thinking; cheapest for the included demos
OpenAI[openai]All architectures work; highest quality for reasoning patterns
Anthropic[anthropic]Strong on long context; required for production Computer-Use
Groq[groq]Fast inference; great for high-volume Self-Consistency
Ollama  (local)[ollama]No API key; tool calling depends on the model
Together[together]Wide model catalogue
Fireworks[fireworks]Function-calling first-class
Mistral[mistral]EU-hosted option
Google[google]Gemini 2.x via Generative AI API
Switch via `LLM_PROVIDER` + the corresponding key in `.env`. No code changes. --- ## Benchmarks A 17-task suite runs every architecture and scores results. Most recent run, real Nebius Llama-3.3-70B, ~25 min, ~$1.50 in tokens:
Outcome Architectures
Strong  2/2 or 3/3 Reflection  SelfConsistency  SelfDiscover  BrowserAgent
Perfect on attempted  1/1 21 more — see leaderboard
Pattern-fit failures LATS on arithmetic (wrong shape) · Debate + Ensemble on Sally trick (group-think) · Reflexion + AWM on raw-fact recall (wrong memory shape)
Overall 33 / 42 correct  78%
Full leaderboard with per-task answer excerpts: docs/benchmarks.md --- ## Learning paths Four curated reading orders, depending on what you're trying to do.
PathForOrder
Beginner Mental model Reflection → Tool Use → ReAct → Planning → Self-Consistency
RAG-focused Production retrieval Agentic RAG → CRAG → Self-RAG → Adaptive RAG → GraphRAG
Multi-agent Coordination Multi-Agent → Blackboard → Debate → STORM → Meta-Controller
Safety Guardrails Dry-Run → Constitutional AI → Reflexive Metacognitive → BrowserAgent (safety gate)
--- ## Star history
Star History Chart
--- ## Tested ``` pytest -q 283 passed, 37 skipped (env-gated integration), 1 warning in ~30s ```
SuiteCoverage
Registry sweepAll 35 architectures (metadata + instantiate + build)
Pure-Python helpersHaiku checker, composite scorers, subprocess executor, safety gate, sandbox path
Notebook integrityAll 35 notebooks executed, no error outputs, §9 commentary tailored from real captured runs
Integration  (env-gated)One real-LLM happy-path per architecture, gated via RUN_INTEGRATION=1
--- ## Documentation | | | |---|---| | [**Full docs site**](https://fareedkhan-dev.github.io/all-agentic-architectures/) | Dark-mode site with embedded notebooks  (live after first deploy) | | [Quickstart](docs/getting-started/quickstart.md) | One-command install, 8-line example | | [Switching providers](docs/getting-started/providers.md) | Capability matrix; one env var to swap | | [Add your own architecture](docs/tutorials/adding-your-own.md) | 5-step contributor recipe | | [Deterministic-picker pattern](docs/tutorials/deterministic-picker.md) | The central technical pattern, explained once | | [Memory variants](docs/tutorials/memory.md) | Comparison of all 7 memory shapes | | [API reference](https://fareedkhan-dev.github.io/all-agentic-architectures/reference/) | mkdocstrings auto-gen from docstrings  (live after first deploy) | | [Benchmarks](docs/benchmarks.md) | Full per-task leaderboard with answer excerpts | --- ## Contributing Contributions welcome. Two paths: 1. **Add a new architecture** — follow the [5-step recipe](docs/tutorials/adding-your-own.md). The PR template includes a deterministic-picker checklist. 2. **Improve an existing one** — bug fix, prompt tuning, performance, scoring rubric. Open an issue first to discuss scope. See [**CONTRIBUTING.md**](CONTRIBUTING.md) for the dev setup, code style, and commit-message convention (Conventional Commits — `release-please` auto-generates the CHANGELOG). --- ## Citation ```bibtex @misc{khan2026agentic, title = {Agentic Architectures: A Library of 35 Production-Grade Agentic AI Patterns}, author = {Khan, Fareed}, year = {2026}, howpublished = {\url{https://github.com/FareedKhan-dev/all-agentic-architectures}}, note = {MIT licensed Python library and runnable textbook} } ``` --- ## License [MIT](LICENSE) — © 2026 Fareed Khan.
Built on LangGraph  ·  Docs powered by Material for MkDocs  ·  Default LLM via Nebius

★ Star  ·  Fork  ·  Open an issue  ·  Discuss