Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
概览
LLMSlim stores what users and agents say word for word, then returns the parts that answer a question within a token budget you set. It runs as an MCP server, a Python library or a small HTTP server. A real Python session with llmslim 0.11.1 from PyPI, typed by a script and recorded with asciinema ( script , recording ). Each MCP setup below starts the same server, llmslim mcp, with uv (Python 3.10 or newer). Memory goes to a local SQLite file, ~/.llmslim/memory.db. The first start downloads LLMSlim and its dependencies. If a client gives up waiting, run uvx --from "llmslim[mcp]" llmslim mcp --help once to fill uv's cache, then restart the client. (pip install llmslim, Python 3.9 or newer): (npm install llmslim, Node 18 or newer), against llmslim serve (pip install "llmslim[server]"): If LLMSlim is useful, a star helps others find it. Feedback is welcome in issues. - remember, recall, list_memories, forget and fit_context. - in SQLite or Postgres.
README
以下为原文 README 节选，完整内容请查看原文。
Use it in 30 seconds
Each MCP setup below starts the same server, llmslim mcp, with uv (Python 3.10 or
newer). Memory goes to a local SQLite file, ~/.llmslim/memory.db.
One click:
安装
uvx --from "llmslim[mcp]" llmslim mcp --help` once to fill uv's cache, then restart the client.