loopx

Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executable todos, evidence logs, and verifiable handoffs.

by huangruiteng · GitHub

4.6k

Stars

Forks

Trending

License

Created

Last commit

From the README

Install

curl -fsSL https://huangruiteng.github.io/loopx/install.sh | bash
export PATH="$HOME/.local/bin:$PATH"
loopx doctor

multi-day engineering, research, benchmark, or experiment objectives;
issue and PR loops that must preserve scope, evidence, and review state;
recurring heartbeat or monitor work;
projects with owner, safety, publication, or private-data gates;
peer-agent teams where ownership, leases, and handoff matter;
creator, research, or operations workflows whose progress must remain

Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.

✓ Claimed by its maintainer

What it doesKeeps long-running AI agent work governed, resumable, and auditable across tools, sessions, and machines.

Who it is forDevelopers and teams running AI agents that must survive long tasks, handoffs, review gates, and failures.

What it does not doNot an agent runtime, model provider, or hosted automation service. LoopX governs state, authority, evidence, and continuation around the agents you already use

Written by the person who maintains this project, verified through the repository.

📈 Star history

2026-08-042026-08-14

📈 Track loopx

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime

Get email alerts →

📄 About

loopx has 4.6k stars on GitHub. It has been forked 393 times. loopx is written mainly in Python. It has been in active development since 2026. loopx is available under the MIT license. Its main topics are agent-control-plane, agent-ops, ai-agents, codex.

Read the full guide

❓ Frequently asked questions