** 一个自架的 MCP 服务器，为 AI 代理提供持久且可搜索的内存。** Claude、Codex、Cursor 以及任何模型上下文协议客户端都写入其中一个 记忆和相互读取。

• 存活下来的记忆。 决策、偏好和项目上下文会延续到下一次会话。
• 一个内存，多个代理。 你使用的每个MCP客户端都是基于相同的事实工作。
• 通过含义、关键词或两者兼有回忆。 向量搜索在措辞不同时找到内存，BM25精确识别标识符，混合模式将两者融合。精确密钥和元数据查找也同样有效。
• 你的。 服务器、引擎和嵌入都运行在您的设备上。没有托管内存服务，没有云嵌入API。

安装

Claude Desktop — 下载 montycat-mcp.mcpb 然后拖入Claude Desktop。不需要Python。该链接始终服务于 当前发行;每一次发行 还携带一个版本命名的副本和一个.sha256用于核对。

Claude Code — 安装 uv]，然后：

/mcp 确认 montycat 服务器已连接。

Codex、光标、其他MCP客户端 — 将你客户端的stdio配置指向 uvx montycat-mcp（Python 3.10+）。关于法典：

引擎

Montycat MCP - Shared Memory for AI Agents

A self-hosted MCP server that gives AI agents persistent, searchable memory. Claude, Codex, Cursor, and any Model Context Protocol client write to one memory and read each other’s.

• Memory that survives the chat. Decisions, preferences, and project context carry into the next session.
• One memory, many agents. Every MCP client you use works from the same facts.
• Recall by meaning, keyword, or both. Vector search finds a memory when the wording differs, BM25 nails exact identifiers, and hybrid mode fuses the two. Exact-key and metadata lookup too.
• Yours. Server, engine, and embeddings run on your machine. No hosted memory service, no cloud embedding API.

Install

Claude Desktop — download montycat-mcp.mcpb and drag it into Claude Desktop. No Python needed. That link always serves the current release; every release also carries a version-named copy and a .sha256 to check it against.

Claude Code — install uv, then:

/plugin marketplace add MontyGovernance/montycat-mcp
/plugin install montycat-mcp@montygovernance

/mcp confirms the montycat server is connected.

Codex, Cursor, other MCP clients — point your client’s stdio config at uvx montycat-mcp (Python 3.10+). For Codex:

codex mcp add montycat -- uvx montycat-mcp

The engine

Memory lives in a Montycat Semantic engine. Montycat MCP starts a local one for you, so most people can stop reading here.

Point it at an engine you already run:

export MONTYCAT_URI="montycat://memory-agent:password@localhost:21210/memories"
export MONTYCAT_TLS=true   # remote engines only

Or start one yourself with Docker:

docker run -d --name montycat -p 21210:21210 -p 21211:21211 \
  -e MONTYCAT_SUPEROWNER=admin -e MONTYCAT_PASSWORD=change-me \
  -v montycat_data:/var/lib/.montycat \
  montygovernance/montycat:semantic

On Apple Silicon use the arm64-semantic tag instead — semantic is the amd64 image, and it crashes under emulation. Port 21211 carries live memory watches.

Use it

Talk to your agent normally; it picks the tool.

Remember that the team chose PostgreSQL for the billing service.