I introduce DANCR, a self-driving research pipeline that continuously generates, prioritizes, and executes modeling strategies for Numerai no manual intervention required.
I built DANCR to leverage LM Studio’s local LLM inference, Tenacity-powered retries, and a trio of specialized agents that ideate, plan, and run experiments in Jupyter notebooks around the clock. Currently using Qwen3-8B.
Your feedback, suggestions and tests are welcome!