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.

View on GitHub →
PythonMITagent-control-planeai-agentscodexloopxloop-engineering
Stars
782
Δ 7d
Δ 30d
Age
2 mo
Last push
39m ago
787783779775771Aug 3
90-day star history

Where this sits in the catalog

Most-wanted open issues

Ranked by 👍 reactions. 3 open issues total, checked 2026-08-03.

Alternatives in Multi-agent orchestration

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first dev…

237.2k
+3,3697d
JavaScript
6 mo

🙌 OpenHands: AI-Driven Development

83.0k
+7007d
TypeScript
2 yrs

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes…

79.1k
+1,1397d
Python
1 yr

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

69.6k
+1097d
Python
3 yrs

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, a…

66.9k
+7057d
TypeScript
1 yr

A programming framework for agentic AI

60.2k
+1627d
Python
2 yrs