Autoresearch: Turning AI Coding Assistants into Autonomous Improvement Engines
tom_doerr · x · 2026-07-30
This is an open-source project with over 5.4k GitHub stars that transforms AI coding tools like Claude Code, OpenCode, and OpenAI Codex into autonomous improvement engines.
Inspired by Karpathy's autoresearch, the core mechanism operates via a goal-directed loop: Set a GOAL → The agent runs the LOOP (Modify → Verify → Keep/Discard) → Repeat forever. It allows developers to set constraints and mechanical metrics, enabling the AI to autonomously handle continuous code optimization and iteration.
Related event: Autoresearch Enables Autonomous Iteration for AI Coding Assistants(2 posts)→
More from coding & agent
- Reflection's Beam, a 501B-parameter open MoE model with 1M context, lands on Hugging Face under Apache 2.0 — QGallouedec · 2026-10-16
- 'LLM code is sloppy' rebutted with real ffmpeg code: identical if/else branches in a top library — kingslyj · 2026-10-16
- Office-editing tool calls need file, worktree and unit: lessons from dsh-univer-office — FunDistribution6537 · 2026-10-16
- Architect MD workflow: Gemini one-shot outputs that beat Opus, via 5-lens plan critique — oikk01 · 2026-10-16
- Prove a coding agent actually ran the tests: check artifacts, not approvals — ComprehensiveShake76 · 2026-10-16
- Building an acceptance harness for AI spreadsheet edits: allowlists, recalc checks, idempotency — ukdicha-modakkk · 2026-10-16