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.
loopx helps you manage AI agents that run for a long time. It keeps track of goals, wakes agents up when needed, logs what happened, and makes sure tasks are handed off properly.
To get started right away, visit this link to download the application. Follow the simple steps below.
Goals persist across sessions and agent restarts. Your AI teams always know what to achieve.
Agents automatically resume when usage limits reset or conditions are met. No manual intervention needed.
Tasks are structured as actionable items. Agents pick them up and complete them systematically.
Every action is logged with proof. Review what happened and when, with full traces.
When one agent finishes, handoffs are recorded and verifiable. No confusion about ownership.
Works with Codex, Claude Code, and other coding agents. Switch without changing your workflow.
Running AI agents for hours or days? loopx keeps everything organized. No more lost contexts, forgotten goals, or messy handoffs. It's a lightweight state kernel that works quietly in the background, ensuring your agent teams run smoothly without constant supervision.
loopx acts as a central brain for your agent teams. Here's the basic flow:
It's like having a project manager for your AI agents, without any extra overhead.
Ready to get started? Download loopx for free.
Visit this link to download the application. Then follow the instructions above to get running in minutes.
No programming knowledge required. Works on Windows.
Have questions or need help? Check the loopx GitHub repository for documentation, issues, and discussions. The community is growing, and contributions are welcome.