cogito-mem
Long-term memory for Claude Code, on your own machine. Cogi the squirrel keeps every message you and Claude exchange, and brings back what Claude forgot. No API key, no cloud, no AI calls to store.

接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx cogito-mem==0.3.0Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
COGITO_MEM_NAMESPACE=<value> claude mcp add io.github.meridian21lab-cogito-mem -- uvx cogito-mem==0.3.0在終端機中執行。
{ "mcpServers": { "io.github.meridian21lab-cogito-mem": { "command": "uvx", "args": [ "cogito-mem==0.3.0" ], "env": { "COGITO_MEM_NAMESPACE": "<value>" } } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Long-term memory for Claude Code, on your own machine. Cogi the squirrel keeps every message you and Claude exchange, and brings back what Claude forgot. No API key, no cloud, no AI calls to store.

Local long-term memory for Claude Code and other agents: every message kept word for word, no cloud.
You need Claude Code and uv, on macOS or Linux (Windows is experimental). Then, in a terminal:
claude plugin install cogito-mem --marketplace meridian21lab/cogito-mem
The first start downloads the model (310 MB, about a minute). To get updates, turn on auto-update once: /plugin → Marketplaces → cogito-mem → Enable auto-update.
/clearcogi. Each runs the released cogito-mem package from PyPI at the exact version the plugin pins (uvx cogito-mem==<version>); the plugin's uv.lock lists that release and numpy with their checksums. After each reply and at the end of a session, the hooks save the new messages from the session's transcript. At the start of a session and with each prompt, they add the few most relevant memories (at most 300 tokens per prompt). The MCP server gives Claude two tools, memory_query and memory_append, answered by a small service that listens on your computer only (127.0.0.1:7327).cogito-mem and its one dependency, numpy, from PyPI (by uv); llama.cpp's llama-server from llama.cpp's official GitHub releases (skipped if you already have it); and the EmbeddingGemma 2 model (310 MB) from Hugging Face. After that, Cogi makes no network calls.~/.cogito-mem/ on your computer: your messages, and a short note of what each turn did, in one SQLite file. API keys, tokens, private keys and passwords are replaced with [redacted] before anything is saved; tool output and file contents are never saved. Text inside <private>…</private> is skipped, and COGITO_MEM_CAPTURE=off pauses saving.cogito-mem eval locomo-qa, which only you would run, sends benchmark questions to the LLM API you set up for it, with your own key.)claude plugin uninstall cogito-mem@cogito-mem, then delete ~/.cogito-mem.Every file, download and connection, with links to the source: What you install.
Keep your project's rules in CLAUDE.md, and let Cogi remember what happened.
Early access. v0.2 is new, built and tested (over 200 tests), and still being measured. Feedback and issues are very welcome.
Local long-term memory for Claude Code and other agents: every message kept word for word, no cloud.
{ "mcpServers": { "io.github.meridian21lab-cogito-mem": { "command": "uvx", "args": [ "cogito-mem==0.3.0" ], "env": { "COGITO_MEM_NAMESPACE": "<value>" } } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
發布者列出了以下環境變數:COGITO_MEM_NAMESPACE。
Cogito Mem (Cogi) 透過 stdio 在本機執行。
上次檢查時間:2026-11-09。 Local long-term memory for Claude Code and other agents: every message kept word for word, no cloud.