Skill + MCP server to turn your agent into an RLM. Load context, iterate with search/code/think tools, converge on answers.

A recursive coding agent inpired by RLMs

Official Implementation of "Reasoning Language Models: A Blueprint"

CLI for Recursive Language Models

Claude Code skill for handling long-context tasks through recursive decomposition

DSPy's Recursive Language Model (RLM) with Modal Sandbox for secure cloud-based code execution

Minimal runtime for Recursive Language Models (RLMs) inspired by the MIT CSAIL paper "Recursive Language Models".

Privacy-first recursive context gateway for AI coding agents

Prometheus exporter providing metrics from a Reprise License Manager (RLM) instance.

Rust CLI implementing the Recursive Language Model (RLM) pattern for Claude Code. Process documents 100x larger than context windows through intelligent chunking, SQLite persistence, and recursive sub-LLM orchestration.

Regularized least-squares algorithm over the empirical risk minimization

Minimal RLM implementation

A recursive language model (RLM) system with hypergraph memory for agentic coding.

A Model Context Protocol (MCP) server that provides AI agents with persistent memory and semantic file discovery.

Recursive reasoning engine for AI agents and vector databases. Powered by MIT's RLM.

limps your Local Intelligent MCP Planning Server across AI assistants. No subscriptions, no cloud—run it locally. Version control your planning docs in git. No more context drift—one shared source of truth across Claude, Cursor, Copilot, and any MCP tool.

Plugins for Claude Code, rlm & devloop.

A persistent memory MCP server for Claude Code - Recursive Language Model integration for Claude Code inspired by MIT CSAIL paper

MCP‑RLM‑Proxy is a production‑ready MCP proxy for AI agents that need to handle huge tool outputs efficiently. It adds smart caching, automatic response truncation, and powerful RLM‑inspired tools so Claude, GPT‑4, Cursor, and custom MCP clients can query filesystem, Git, APIs, and databases with far fewer tokens and lower LLM costs

Node-based implementation of the Recursive Language Model (RLM)