All Agentic Architectures AI Agent

by FareedKhan-dev• 4.6k•• Scanned•Claim this listing•Request removal

Coding Agentsagentic aiai agentslangchainlanggraphlangsmith

35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.

All Agentic Architectures is an open-source ai agent by FareedKhan-dev, written mainly in Jupyter Notebook, with 4,646 GitHub stars and the MIT license. Its code was last updated Jun 22, 2026.

about README security reviews

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.

<table> <tr> <td align="center" width="140"><h2><kbd>  35  </kbd></h2>ARCHITECTURES</td> <td align="center" width="140"><h2><kbd>  283  </kbd></h2>PASSING TESTS</td> <td align="center" width="140"><h2><kbd>  17  </kbd></h2>BENCHMARK TASKS</td> <td align="center" width="140"><h2><kbd>  9  </kbd></h2>LLM PROVIDERS</td> <td align="center" width="140"><h2><kbd>  0  </kbd></h2>MOCKED RUNS</td> </tr> </table> </div>

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

pip install "agentic-architectures[nebius,faiss,tavily]"

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.

<details> <summary>Set up a virtualenv from a fresh clone</summary>

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

</details>

Architecture families

Reasoning & Reflection

Self-critique loops that drive answer quality up through iteration. <a href="notebooks/01_reflection.ipynb">Reflection</a> · <a href="notebooks/18_reflexion.ipynb">Reflexion</a> · <a href="notebooks/20_chain_of_verification.ipynb">Chain-of-Verification</a> · <a href="notebooks/19_self_discover.ipynb">Self-Discover</a> · <a href="notebooks/32_constitutional_ai.ipynb">Constitutional AI</a>