Feynman autoresearch
Autonomous experiment loop that tries ideas, measures results, keeps what works, and discards what doesn't. Use when the user asks to optimize a metric, run an experiment loop, improve performance iteratively, or automate benchmarking.
install
source · Clone the upstream repo
git clone https://github.com/getcompanion-ai/feynman
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/getcompanion-ai/feynman "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/autoresearch" ~/.claude/skills/getcompanion-ai-feynman-autoresearch && rm -rf "$T"
manifest:
skills/autoresearch/SKILL.mdsource content
Autoresearch
Run the
/autoresearch workflow. The slash command expands the full workflow instructions in the active session; do not try to read a relative prompt-template path from the installed skill directory.
Tools used:
init_experiment, run_experiment, log_experiment (from pi-autoresearch)
Session files:
autoresearch.md, autoresearch.sh, autoresearch.jsonl