Autoresearch Autonomous experiment loop: try ideas, measure results, keep what works, discard what doesn't, never stop. Works for any optimization target: test speed, bundle size, LLM training, build times, Lighthouse scores, binary size, latency, memory usage. Setup If already exists in the working directory, skip setup and resume the loop — read , , and , then continue experimenting. Otherwise: 1. Gather context : Ask (or infer from and conversation) the Goal , Command to benchmark, Primary metric (name + direction), Files in scope , and Constraints . 2. Create branch : (e.g. ). 3. Read sou…