RLM ClaudeCAUTION
Recursive Language Models for Claude Code - Infinite memory solution inspired by MIT CSAIL paper
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Your Claude Code sessions forget everything after /compact. RLM fixes that.[](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) [](https://modelcontextprotocol.io) [](https://github.com/EncrEor/rlm-claude/actions/workflows/ci.yml) [](https://codecov.io/gh/EncrEor/rlm-claude) [](https://pypi.org/project/mcp-rlm-server/)
Français | English | 日本語
The Problem
Claude Code has a context window limit. When it fills up:
/compactwipes your conversation history- Previous decisions, insights, and context are lost
- You repeat yourself. Claude makes the same mistakes. Productivity drops.
The Solution
RLM is an MCP server that gives Claude Code persistent memory across sessions:
You: "Remember that the client prefers 500ml bottles" → Saved. Forever. Across all sessions. You: "What did we decide about the API architecture?" → Claude searches its memory and finds the answer.
3 lines to install. 14 tools. Zero configuration.
Quick Install
Requirements: Python 3.10+ (download), Claude Code CLI
Via PyPI (recommended)
pip install mcp-rlm-server[all]
The hooks and templates ship inside the package. Since a pip install gives you no repo checkout, ask the package where they landed:
python -m mcp_server --hooks-dir # e.g. .../site-packages/mcp_server/hooks python -m mcp_server --templates-dir
Point your `~/.claud
392b6526789aOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-rlm-server -- uvx mcp-rlm-server
{
"mcpServers": {
"mcp-rlm-server": {
"command": "uvx",
"args": [
"mcp-rlm-server"
]
}
}
}Exposed tools (14)
13 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
rlm_chunk | read | |
rlm_domains | read | |
rlm_forget | read | |
rlm_grep | read | |
rlm_list_chunks | read | |
rlm_peek | read | |
rlm_recall | read | |
rlm_remember | read | |
rlm_restore | read | |
rlm_retention_preview | read | |
rlm_retention_run | write | |
rlm_search | read | |
rlm_sessions | read | |
rlm_status | read |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (4)
mcp_server/server.py
streamable-http
"$SCRIPT_DIR/../../CLAUDE.md" # Two levels up
"$(cd "$(dirname "$0")" 2>/dev/null && pwd)/../../CLAUDE.md" \
Gates applied: no_behavioural_pass.
392b6526789afull audit observations/trust-audit/mcp-server/encreor__rlm-claude.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 392b6526789a | CAUTION | B | 89 | first audit |
Questions
What is the RLM Claude MCP server?
Recursive Language Models for Claude Code - Infinite memory solution inspired by MIT CSAIL paper
What tools does RLM Claude expose?
14 in total: 13 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is RLM Claude safe to connect to an agent?
With care. The audit graded it B (89/100) and found 4 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does RLM Claude need?
No credential environment variables were found in its source, so it appears to need none.
How does RLM Claude run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as mcp-rlm-server.
How current is this page?
The grade is for one exact copy of the source (392b6526789a), read on 2026-10-08. The repository is watched and re-audited when it changes.