rlmflow: A graph approach to Recursive Language Models

GitHub · PyPI · Examples · Changelog pip install rlmflow In this post TLDR Why RLMs RLMs as graphs Internals Spawning recursive agents Context and Session Coding agent Boids simulation Autoresearch: circle packing Extra features Graph manipulation Conclusion Acknowledgements Citation References tldr rlmflow turns Recursive Language Models into inspectable execution graphs. It’s a Python library for writing RLM agents where every query, action, observation, delegation, wait, resume, and result is a typed Pydantic state, and a run is a recursive Graph of agent trajectories. ...

May 2026 · Shyam Sudhakaran