IronClaw is an Agent OS focused on privacy, security and extensibility

A feature rich implementation of Recursive Language Models, with advanced visualization and logging tools.

Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs, and tools — the model handles its own control flow. Get fully interpretable trajectories and performance that scales directly with model improvements. Without context rot.

A recursive coding agent inpired by RLMs

Automated generation of comprehensive Agents.md for LLMs, driven by the DSPy Recursive language model implementation.

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

Official Implementation of "Reasoning Language Models: A Blueprint"

Open-source autonomous AI agent with a self-model that actually changes as it runs - ego, affect, and identity grounded in real psychology (Higgins, PAD/OCC). Ships code, runs a team, makes money. Local-first, self-custody.

CLI for Recursive Language Models

A small Recursive Language Model: let any LLM run code on its context instead of stuffing it into the prompt.

Traffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and adapters for 29 AI frameworks

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.

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

A drop-in code interpreter using the Monty Python emulator for DSPy's RLM module.

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

The Research Playground for the RLMSs and Coding Agents

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

Persistent REPL scratchpad for coding agents — variables survive across turns, only print() enters context. Agent skill for Claude Code, Codex, Gemini CLI, and 14+ coding agents.

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

Privacy-first recursive context gateway for AI coding agents