huangruiteng/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.

Python5.8K stars529 forks+326 today

View on GitHubShare on X

Topics

#agent-control-plane#ai-agents#codex#loopx#loop-engineering#agent-ops#workflow-automation#agent-harness#long-horizon#dsh-plugin#long-horizon-agents

What it does

LoopX is a lightweight state management tool for long-running AI agent tasks, ensuring objectives, todos, and evidence remain stable across multiple sessions. It matters because it enables continuous, manageable work in complex AI-driven workflows.

Star history

2026-08-23 → 2026-09-12+781 stars

Tracking

Last trending: 2026-08-15

Creator kit

Hook

LoopX: The lightweight solution for managing long-running AI tasks with stability and ease. #AI #DevOps

Content angles

How LoopX simplifies complex AI workflows.
Case studies of LoopX in real-world applications.
Comparative analysis: LoopX vs other state management tools.

Who should care

Developers, researchers, and data scientists working on long-term AI projects.