Shy2593666979/AgentChat
https://github.com/Shy2593666979/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。
agentagent-memoryagent-skillshuman-in-the-looplangchainllmmcpmcp-clientmcp-servermysqlredis
Agent quality
56%
Agent quality score.
Reputation49%
Cross-source presence, stars, and recency.
has 715 stars; actively maintained; credible author
Usability80%
Docs, license, auth, and clear capabilities.
Usability based on documentation, license, auth/pricing clarity, structured capabilities, and public repository presence.
Functionality43%
Predicted functionality, speed, and reliability.
Scored on specificity, consistency, reliability, speed, and scope clarity.