memory
Official MCP reference server (memory); see repo README.
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。
| Category | AI, Memory & RAG |
| Publisher type | community |
| ID | Shy2593666979/AgentChat |
| Repository | https://github.com/Shy2593666979/AgentChat |
| Website | http://agentchat.cloud |
| Stars | 915 |
| Last update | 2026-10-11 |
| Language | Python |
| Source | github-topic |
⚠️ Install unverified. We inferred the runtime from the repo language and did not confirm the package name. The configs below are templates. Copy the exact command from the README.
Some servers also need API keys or environment variables. Check the README.
claude_desktop_config.json{
"mcpServers": {
"agentchat": {
"command": "uvx",
"args": [
"<package-name-from-README>"
]
}
}
}.cursor/mcp.json{
"mcpServers": {
"agentchat": {
"command": "uvx",
"args": [
"<package-name-from-README>"
]
}
}
}.vscode/mcp.json{
"servers": {
"agentchat": {
"type": "stdio",
"command": "uvx",
"args": [
"<package-name-from-README>"
]
}
}
}Is this your server? Claim or update this listing · Feature it
[](https://mcpatlas.us/server/shy2593666979-agentchat/)
HTML version and more on the badge page.
Official MCP reference server (memory); see repo README.
Official MCP reference server (sequentialthinking); see repo README.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
The new and trending MCP servers of the week, with install configs. One email a week, free.