MCP Vetted

AgentChat

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

Repository
Shy2593666979/AgentChat
Stars
789
Last push
2026-04-15
License
MIT
Category
Databases

Score breakdown — how scoring works

  • Maintenance

    18 / 30
    • Pushed within 4 months79 days ago+18

  • Adoption

    16.8 / 25
    • GitHub stars (no package published — stars weighted fully)789+16.8

  • Documentation

    20 / 25
    • Comprehensive README (6,000+ chars)6861 chars+10
    • Install / setup instructionsyes+6
    • Tools / capabilities documentedno+0
    • Code or client-config exampleyes+4

  • Trust signals

    7 / 20
    • OSS license declaredMIT+7
    • First-party vendor implementationno+0
    • DNS-verified registry namespaceno+0
    • Listed in official MCP Registryno+0
    • Owned by an organizationno+0

Install

From sourcegit clone https://github.com/Shy2593666979/AgentChat

No package published to a registry — see the README for setup instructions.

Always review a server's code and required credentials before connecting it to your MCP client. MCP Vetted scores public metadata — it does not audit code for malicious behavior (yet). Methodology →

View on GitHub ↗