by TheGreenCedar · Codex Skill · ★ 824
Codex Autoresearch Measured improvement loops for Codex Try it - Install - How it works - Dashboard - Docs - Changelog Codex Autoresearch helps Codex turn "make this better" into a measured loop. Give Codex a goal, a benchmark contract, and a safe edit scope. Codex can run small experiment packets, keep or discard changes with evidence, preserve ASI and metrics across context loss, and package useful work for review. Inspired by the AI-focused karpathy/autoresearch and pi-autoresearch.
| Stars | 824 |
| Forks | 59 |
| Language | TypeScript |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 71.9604508649819/100 |
| Last Updated | 2026-07-08 |
| Created | 2026-04-20 |
| Platforms | codex, node |
| Est. Tokens | ~15k |
These tools work well together with codex-autoresearch for enhanced workflows:
Explore other popular codex skill tools:
codex-autoresearch is A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss, Li. It is categorized as a Codex Skill with 824 GitHub stars.
codex-autoresearch is primarily written in TypeScript. It covers topics such as agent-skills, autonomous-agents, autoresearch.
You can find installation instructions and usage details in the codex-autoresearch GitHub repository at github.com/TheGreenCedar/codex-autoresearch. The project has 824 stars and 59 forks, indicating an active community.
codex-autoresearch is released under the Apache-2.0 license, making it free to use and modify according to the license terms.