Claude Rlm

RLM: Recursive Language Models for Claude Code

A Claude Code skill that implements **Recursive Language Models (RLMs)** — enabling Claude to process arbitrarily long inputs by treating them as external data and recursively delegating analysis to sub-agents.

Based on the paper [Recursive Language Models](https://arxiv.org/abs/2512.24601) (Zhang, Kraska, Khattab; MIT CSAIL, 2026).

What are Recursive Language Models?

LLMs have limited context windows, and their performance degrades as prompts get longer — a phenomenon called **context rot**. The standard solution is context compaction (summarization), but this loses fine-grained information.

RLMs take a fundamentally different approach: **treat the input as an external object in a programming environment, and let the LLM programmatically interact with it through code — including recursively calling itself on slices of the input.**

Three design choices distinguish RLMs from naive agent scaffolds:

1. Symbolic handle: The prompt is stored as a variable in the environment, not pasted into the LLM's context. The model gets metadata (length, preview) and manipulates it through code.
2. Unbounded output via variables: Results are built up in environment variables/files, not limited by the LLM's output length.
3. Symbolic recursion: The LLM can invoke sub-LM calls inside programmatic loops, enabling O(n) or O(n^2) semantic work over inputs of any length.

Installation

Rather than installing this skill directly, we recommend one of these approaches:

1. **Paste this README** into a conversation with your agent and ask it to reimplement the system from scratch. The design decisions and architecture are all here — a capable agent can build it in one session.

2. **Ask your agent to summarize the repo** into a detailed design document, then reimplement from just that document without referencing the code or prompts directly. This gives you a clean-room implementation you fully control.

Installing scrip