Autoresearch Agent
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
Works with: Claude Code, Cursor, Codex CLI
Category: Dev Tools & CI — see all ranked ›
Work: Agent development · Model evaluation
Who it is for: AI engineer
- Adoption: 1 repos
- Health: active
- GitHub stars: 23,181
- Contributors: 30
- License: MIT
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · skill:alirezarezvani/autoresearch-agent
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›