Drex 1.1 is now open source.
It’s an experimental decision model built on a diffusion language model backbone, compatible with any app that works with the /v1/systemone endpoint.
Run it locally with llama.cpp, Ollama, or Unsloth, then bring it into your agent harness of choice: Claude Code, Codex, Cursor, OpenCode, and more.
Enjoy building 🦖
GitHub: https://t.co/dQiApWfv5c
Hugging Face:
A diffusion-LM based decision model you can run locally and wire into Claude Code, Codex, Cursor or OpenCode through a compatible endpoint. It is experimental, but it offers a non-autoregressive approach to AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → decisions.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
