autoresearch

Autonomous research loops with 10 commands. Generalizes Karpathy's autoresearch loop to any domain with mechanical evaluation, overnight persistence, and zero dependencies.

Autonomous experimentation skill — your AI coding agent designs experiments, tests hypotheses, discards failures, keeps wins. Runs overnight while you sleep.

Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).

Autonomous research orchestration: agents for hypothesis-driven investigation, experiment running, fresh-eyes review, and batch evaluation.

Autonomous, personalized research loops for Claude Code. Set a topic, walk away, come back to a quality-gated report adapted to your projects.

Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.