by huangruiteng · Codex Skill · ★ 5.7k
Loop engineering for long-running AI agents and peer agent teams. A lightweight state kernel and agent-agnostic local control plane for Codex, Claude Code, Cursor, and other runtimes: objectives, gates, todos, quota, scheduler hints, evidence, and typed continuation in one reviewable loop. 把会干活的 Agent,接成可管理、可复盘、可持续改进的数字员工。 LoopX is a lightweight state kernel and local control plane for loop engineering: it keeps goals, todos, gates, quota, scheduler hints, evidence, and handoffs stable while Codex, Claude Code, Cursor, or another runtime executes each bounded turn.
| Stars | 5,711 |
| Forks | 512 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 65.0397010746698/100 |
| Open Issues | 62 |
| Last Updated | 2026-09-07 |
| Created | 2026-05-31 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~24k |
These tools work well together with loopx for enhanced workflows:
Explore other popular codex skill tools:
loopx is Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.. It is categorized as a Codex Skill with 5.7k GitHub stars.
loopx is primarily written in Python. It covers topics such as agent-control-plane, agent-harness, agent-ops.
You can find installation instructions and usage details in the loopx GitHub repository at github.com/huangruiteng/loopx. The project has 5.7k stars and 512 forks, indicating an active community.
loopx is released under the Apache-2.0 license, making it free to use and modify according to the license terms.