{"slug":"autoresearch","title":"autoresearch","description":"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.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-06T06:02:17.252Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/pjhoberman/autoresearch.git","web_data":{},"github_data":{},"catalog_sources":{"community":[{"name":"autoresearch","source":{"sha":"0c6409190f82f198c3e65fb856ceb6322c493231","url":"https://github.com/pjhoberman/autoresearch.git","source":"url"},"homepage":"https://github.com/pjhoberman/autoresearch","description":"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."}]}}