GitHub 仓库

FareedKhan-dev/all-agentic-architectures

Jupyter Notebook 首次收录 2025-09-24 更新于 2026-07-16 查看源 ↗

GitHub 仓库 中按Star排名第 347 / 共 783

3.9k Star

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.

项目介绍

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.

  35  ARCHITECTURES   283  PASSING TESTS   17  BENCHMARK TASKS   9  LLM PROVIDERS   0  MOCKED RUNS

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,…

摘自 github.com/FareedKhan-dev/all-agentic-architectures

最新指标

Star 3.9k 2026-07-16
Fork 669 2026-07-16
提交 33 2026-07-16
发布 1 2026-07-16
Watcher 32 2026-07-16
开放 issue 1 2026-07-16
开放 PR 6 2026-07-16