Stars
基于 LangGraph 的多智能体差旅系统，覆盖 意图识别 → 出差申请 → 审批跟踪 → 行程规划 → 预订执行 的完整闭环。
Renshu AI is a multi-agent Traditional Chinese Medicine (TCM) consultation system featuring a decoupled front-end and back-end architecture built with FastAPI and React, utilizing the "Harness" par…
Autonomous multi-agent AI system with document processing, web automation, and code execution powered by LLM agents and MCP servers
AI PDF chatbot agent built with LangChain & LangGraph
Core 7 layers of production grade agentic system
李白 👤 作为唐代杰出诗人，其诗歌作品在中国文学史上具有重要地位。近年来，随着数字技术和人工智能的快速发展，传统文化普及推广的形式也面临着创新与变革。国内外对于李白诗歌的研究虽已相当深入，但在数字化、智能化普及方面仍存在不足。因此，本项目旨在通过构建李白知识图谱，结合大模型训练出专业的AI智能体，以生成式对话应用的形式，推动李白文化的普及与推广。
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
Open source alternative to LangGraph Platform (now LangSmith Deployments) - Self-hosted AI agent backend with FastAPI and PostgreSQL. Zero vendor lock-in, full control over your agent infrastructure.
使用LangGraph+DeepSeek-R1+FastAPI+Gradio实现一个带有记忆功能的流量包推荐智能客服web端用例,同时也支持gpt大模型、国产大模型(OneApi方式)、Ollama本地开源大模型、阿里通义千问大模型
Tenacious tool calling built on LangGraph
这是一个 LangChain 1.0 和 LangGraph 1.0 的学习仓库，学习如何进行agent开发，涵盖从基础概念到实战项目的完整学习路径。
Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit
Full-stack AI app generator — FastAPI + Next.js with AI Agents, RAG, streaming, auth, and 20+ integrations out of the box.
五星大厨:全面Multi-Agent 的客服机器人，基于langraph实现，txt2sql ,txt2cypher, lightrag, 多模态 等
Advanced Multi-Turn QA System with LLM and Intent Recognition. 基于LLM大语言模型意图识别、参数抽取结合slot词槽技术实现多轮问答、NL2API. 打造Function Call多轮问答最佳实践
Everything you need to know to build your own RAG application
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agen…
目前OpenClaw和NanoBot都是用于个人的，不太支持多用户，基于多用户重新修改Bot，没有对Openclaw进行任何更改，原生能力封装
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
企业级 Agentic RAG 智能体 - 全链路覆盖文档解析、多路检索、意图识别、问题重写、会话记忆、MCP 工具调用与深度思考。面向真实业务场景，从 0 到 1 完整工程实现。
LC-StudyLab 是一个完整演示 LangChain v1.0 全家桶能力的开源项目，整合了 LangGraph、DeepAgents、RAG 检索增强生成、Guardrails 安全校验与流式输出智能体等核心特性，帮助开发者系统掌握 LangChain v1 的所有关键组件
Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs