Rlm Infinite Memory For Claude Code

@EncrEor

Visit Server

5 months ago

RLM solves Claude Code's biggest limitation: memory loss. Every time you /compact or hit the context limit, your decisions, insights, and conversation history disappear. RLM fixes this with an MCP server that auto-saves before context loss, lets you store key decisions as searchable insights, and keeps your full conversation history in persistent chunks. Features include BM25 ranked search, fuzzy matching (typo-tolerant), multi-project organization, and smart retention that auto-archives old chunks. Inspired by MIT CSAIL's Recursive Language Models paper. Install in 3 lines, zero configuration needed.

Overview Tools Comments

Comments

Try in Playground

Server Config

{
  "mcpServers": {
    "rlm-server": {
      "command": "python3",
      "args": [
        "/path/to/rlm-claude/mcp_server/server.py"
      ]
    }
  }
}

Build with ShipAny.