← ClaudeAtlas

autoresearchlisted

Autonomous experiment loop: modifies code, runs experiments, evaluates metrics, keeps improvements. Inspired by karpathy/autoresearch + pi-autoresearch + autoexp. Triggers: /autoresearch, 'auto research', 'optimize continuously', 'experiment loop', 'autonomous optimization'.
alfredolopez80/multi-agent-ralph-loop · ★ 146 · AI & Automation · score 80
Install: claude install-skill alfredolopez80/multi-agent-ralph-loop
# /autoresearch - Autonomous Experimentation Loop (v3.1.0) Continuously modify code, run experiments, evaluate metrics, and keep improvements. The agent is a tireless researcher, not an assistant waiting for permission. Inspired by [karpathy/autoresearch](https://github.com/karpathy/autoresearch), [davebcn87/pi-autoresearch](https://github.com/davebcn87/pi-autoresearch), and [autoexp](https://gist.github.com/adhishthite/16d8fd9076e85c033b75e187e8a6b94e). ## Overview ``` +------------------------------------------------------------------+ | AUTORESEARCH LOOP | +------------------------------------------------------------------+ | | | +-------------+ +----------+ +-----------+ | | | HYPOTHESIZE |--->| MODIFY |--->| COMMIT | | | | (strategy) | | (code) | | (git) | | | +-------------+ +----------+ +-----+-----+ | | | | | v | | +-------------+ +----------+ +-----------+ | | | CHECKPOINT? |<---| EVALUATE |<---| RUN | | | | (ask user?) | | (delta) | | (metric) | | | +------+------+ +----+-----+ +-----------+ | | | |