#7070th of 100 in Learning and cookbooks
all-agentic-architectures
Python library of 35 agentic patterns with executed notebooks and benchmarks
- Stars
- 4.6k
- License
- MIT
- Last commit
- May 2026
- Last release
- May 2026
- Language
- Jupyter Notebook
Missed the latest GitHub check; these facts may be older.
Overview
A Python library built on LangGraph that implements 35 agentic patterns (Reflection, ReAct, Tree of Thoughts, Corrective RAG, MemGPT, Debate, SWE-Agent and others) behind a shared `.run(task)` interface returning an `ArchitectureResult`. Each pattern has an executed Jupyter notebook, and a 17-task benchmark compares them. It supports nine LLM providers, including Ollama for local models.
Who it is for: Engineers learning or comparing agentic patterns in Python
Strengths
- Uniform `.run(task)` interface lets you swap patterns without changing downstream code
- All 35 notebooks are executed with real LLM outputs; 283 tests pass
- Nine providers selected by one env var, including local Ollama
- Benchmark leaderboard compares architectures per task, with a reported 33/42 correct
Weaknesses
- Benchmark covers one model (Llama-3.3-70B on Nebius) and mostly 1 to 3 attempts per task
- Reference implementations for study, not a framework with deployment or serving
- Default provider is Nebius; Ollama tool calling depends on the model
- 37 integration tests are skipped unless RUN_INTEGRATION=1 and keys are set
What it needs
- no GPU
- Needs LangGraph, FAISS (optional extra), Tavily (optional extra), Playwright (BrowserAgent), LLM provider API key
- Models: Nebius, OpenAI, Anthropic, Groq, Ollama
Also in Learning and cookbooks
See all 100| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 91 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 83 out of 100 |
| 3 | rag_techniquesCollection of 42 runnable notebooks implementing RAG techniques | 82 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 82 out of 100 |
| #5 | ai-for-beginners24-lesson AI curriculum with notebooks in PyTorch and TensorFlow | 81 out of 100 |