# RLM

> Use this tool when you need to analyze large codebases, documents, or datasets that exceed token limits, and require hierarchical processing capabilities. The Recursive Language Model (RLM) handles massive contexts by treating content as external variables, supporting multiple LLM providers and automatic content type detection. It provides optimized chunking strategies, parallel batch processing, and context persistence to disk, making it ideal for decomposing complex data into manageable pieces.

Canonical page: https://skillsregistry.net/skills/richardwhiteii-rlm  
JSON: https://api.skillsregistry.net/v1/skills/richardwhiteii-rlm

## Description

Implements the Recursive Language Model (RLM) pattern for handling massive contexts that exceed token limits by treating content as external variables rather than loading directly into prompts. Supports multiple LLM providers (Claude SDK, Ollama), automatic content type detection with optimized chunking strategies, parallel batch processing with concurrency controls, and context persistence to disk. Designed for analyzing large codebases, documents, or datasets by decomposing them into manageable pieces while maintaining hierarchical processing capabilities through controlled recursion depth.

## Trust

- **Trust score (0–1):** 0.81
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/richardwhiteii-rlm)
- **Repository:** <https://github.com/richardwhiteii/rlm>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "richardwhiteii-rlm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/richardwhiteii-rlm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/richardwhiteii-rlm/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt