by leo-lilinxiao · Codex Skill · ★ 1.7k
Aim. Iterate. Arrive. Autonomous goal-driven experimentation for Codex. English · 🇨🇳 中文 · 🇯🇵 日本語 · 🇰🇷 한국어 · 🇫🇷 Français · 🇩🇪 Deutsch · 🇪🇸 Español · 🇧🇷 Português · 🇷🇺 Русский Quick Start · What It Does · Architecture · Modes · Configuration · Guide · Recipes Quick St
| Stars | 1,748 |
| Forks | 99 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 59.264/100 |
| Open Issues | 4 |
| Last Updated | 2026-05-20 |
| Created | 2026-03-18 |
| Platforms | cli, codex, python |
| Est. Tokens | ~238k |
Explore other popular codex skill tools:
codex-autoresearch is Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch . It is categorized as a Codex Skill with 1.7k GitHub stars.
codex-autoresearch is primarily written in Python. It covers topics such as automation, autonomous-agent, autoresearch.
You can find installation instructions and usage details in the codex-autoresearch GitHub repository at github.com/leo-lilinxiao/codex-autoresearch. The project has 1.7k stars and 99 forks, indicating an active community.
codex-autoresearch is released under the MIT license, making it free to use and modify according to the license terms.