Autoresearch
Autonomous experiment loops on any codebase — one file, one metric, one loop. An agent edits a constrained file, runs an eval, keeps improvements, reverts failures, and repeats unattended. Based on Karpathy’s autoresearch pattern, generalized beyond ML training to any code with a measurable outcome.
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code
Category: Dev Tools & CI — see all ranked ›
- tashan score: 33.0
- Adoption: 1 repos
- Health: active
- GitHub stars: 21
- Contributors: 1
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 ↗ · plugin:pjhoberman/autoresearch/autoresearch
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›