A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.
LoopX is a provider-neutral control plane that gives long-running AI-agent work persistent state, decisions, governance, recovery, and handoffs across different agent harnesses. It is for managing and reviewing durable work performed by Codex, Claude Code, Cursor, dsh, or custom agent systems.
Latest release v1.0.5 — LoopX 1.0.5 — first-connect is registration-only, and managed execution is selected instead of inferred · 15 Sept 2026
1 file for Codex and OpenCode: loopx AGENTS.md — 6,412 tokens loaded in every session.
AGENTS.md A 6,412 tok These files are huangruiteng/loopx's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.