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。
What is AgentChat?
AgentChat is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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...
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。
This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 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
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx agentchatConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AgentChat
AgentChat is a full-stack LLM-powered multi-agent platform that enables intelligent agents to collaborate on complex tasks through multi-turn dialogue. It integrates LangChain, RAG, MCP protocol, Milvus, ElasticSearch, and a three-tier memory architecture (short-term context, historical summaries, long-term user preferences). Agents can call 10+ built-in tools, load MCP servers at runtime, and generate new MCP servers from OpenAPI specifications with human-in-the-loop approval.
Prerequisites
- Python 3.12+ and Node.js 18+ installed on your machine
- Docker 20.10+ and Docker Compose for containerized deployment
- MySQL 8.0+ and Redis 7.0+ (included in the Docker Compose setup)
- An LLM API key (OpenAI, Anthropic, or compatible provider)
- An MCP-compatible client such as Claude Desktop
Clone the repository
Clone the AgentChat repository to your local machine and navigate into it.
git clone https://github.com/Shy2593666979/AgentChat.git
cd AgentChatConfigure the deployment settings
Edit the Docker Compose configuration file to set your LLM API key, database credentials, and other required environment values before starting services.
cd docker
cp docker_config.yaml.example docker_config.yaml
# Edit docker_config.yaml with your API keys and database settingsStart all services with Docker Compose
Launch the backend API, frontend, MySQL, and Redis containers in detached mode. The backend Swagger docs will be available at /docs after startup.
docker-compose up --build -dVerify the backend is running
Confirm the FastAPI backend started correctly by opening the Swagger UI in your browser. This endpoint lists all available agent tools and API routes.
open http://localhost:8000/docsConfigure Claude Desktop to connect
Add the AgentChat MCP server entry to your Claude Desktop configuration file so Claude can delegate tasks to the agent platform.
Load or create agents
Use the web frontend to create custom agents, attach knowledge bases, assign tools, and define memory policies. The platform supports sub-agents with reasoning, RAG-based Q&A, and MCP server dynamic loading.
open http://localhost:3000AgentChat Examples
Client configuration
Add AgentChat as an MCP server in your Claude Desktop config. Adjust the host and port if your deployment differs from defaults.
{
"mcpServers": {
"agentchat": {
"command": "npx",
"args": ["agentchat"],
"env": {
"AGENTCHAT_API_URL": "http://localhost:8000"
}
}
}
}Prompts to try
Sample prompts that leverage AgentChat's multi-agent collaboration, RAG, and tool-calling capabilities.
- "Use the research agent to summarize the latest papers on transformer architectures and store the findings in the knowledge base."
- "Create a sub-agent that monitors our MySQL database and alerts me when query latency exceeds 500ms."
- "Ask the coding agent to review the auth module, remember any issues it finds, and generate a fix plan."Troubleshooting AgentChat
Docker Compose fails to start MySQL or Redis containers
Ensure ports 3306 and 6379 are not already in use on your host. Run `docker ps` to check for conflicting containers and stop them before retrying `docker-compose up`.
Agents fail to call tools or return empty responses
Check that your LLM API key is correctly set in docker_config.yaml and that the model you specified supports function calling. Review backend logs with `docker-compose logs backend`.
Frontend cannot connect to the backend API
Verify the CORS settings in docker_config.yaml include your frontend origin. If running locally, the default is http://localhost:3000. Restart containers after any config change.
Frequently Asked Questions about AgentChat
What is AgentChat?
AgentChat is a Model Context Protocol (MCP) server that 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。 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AgentChat?
Follow the installation instructions on the AgentChat GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AgentChat?
AgentChat works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AgentChat free to use?
Yes, AgentChat is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
AgentChat Alternatives — Similar Communication Servers
Looking for alternatives to AgentChat? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.
Slack
★ 86.1kEnables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl
LibreChat
★ 37.3kEnhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA
Note Gen
★ 11.9kA cross-platform Markdown AI note-taking software.
DeepChat
★ 5.8k🐬DeepChat - A smart assistant that connects powerful AI to your personal world
WhatsApp MCP
★ 5.7kConnects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without
Apple
★ 3.1kEnables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
Browse More Communication MCP Servers
Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AgentChat in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use AgentChat?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.