Auto Research

Autonomous experiment loop: modify code, evaluate, measure metric, keep wins, discard losses. Inspired by Karpathy's autoresearch.

Works in any project with a measurable metric — ML training, compiler optimization, algorithm tuning, performance benchmarking.

Discovery Flow

If research.json exists, skip to Setup Phase.

Otherwise:

1. Explore the project with 2 parallel subagents — launch both simultaneously using the Agent tool: