Rlm Infinite Memory For Claude Code MCP Server

Recursive Language Models for Claude Code - Infinite memory solution inspired by MIT CSAIL paper

Remote serverstreamable-httpPython

What is the Rlm Infinite Memory For Claude Code MCP Server?

Recursive Language Models for Claude Code - Infinite memory solution inspired by MIT CSAIL paper

What the server does

Claude Code has a context window limit. When it fills up: - /compact wipes your conversation history - Previous decisions, insights, and context are lost - You repeat yourself. Claude makes the same mistakes. Productivity drops.

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the Rlm Infinite Memory For Claude Code MCP Server

{
  "mcpServers": {
    "rlm-claude": {
      "command": "uvx",
      "args": ["mcp-rlm-server"],
      "env": {
        "RLM_EMBEDDING_PROVIDER": "your-value",
        "RLM_LANG": "your-value",
        "RLM_CONTEXT_DIR": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
RLM_EMBEDDING_PROVIDERConfiguration value read at startup.Optional
RLM_LANGConfiguration value read at startup.Optional
RLM_CONTEXT_DIRFilesystem location the server is allowed to use.Optional

Example prompts to try

  • “Use Rlm Infinite Memory For Claude Code to Language.”

Frequently asked questions

Rlm works natively with Claude Code via MCP, while Letta/MemGPT requires its own runtime. Rlm offers auto-save before compact, hybrid search (regex + BM25 + semantic), fuzzy search, multi-project support, smart retention, and sub-agent analysis—all with zero-config installation.