huangruiteng/loopx
LoopX gives long-running coding-agent work durable goals, gates, ownership, evidence and quotas across bounded turns. It is useful when chat history and a scheduler no longer provide enough control.
LoopX **v0.4.x** is a local, agent-agnostic state kernel for Codex, Claude Code, Cursor and custom runners. It preserves **goals, gates, todos, evidence and quota** while agents execute bounded turns; two published trajectories span **200+ elapsed hours** each.
Use it when work crosses sessions or agents and ownership, stop conditions or human approvals must remain explicit. Its quota check, todo claims, validated writeback and review packets offer a concrete harness pattern even if you do not adopt the project.
LoopX **v0.4.x** is a local, agent-agnostic state kernel for Codex, Claude Code, Cursor and custom runners. It preserves **goals, gates, todos, evidence and quota** while agents execute bounded turns; two published trajectories span **200+ elapsed hours** each. Use it when work crosses sessions or agents and ownership, stop conditions or human approvals must remain explicit. Its quota check, todo claims, validated writeback and review packets offer a concrete harness pattern even if you do not adopt the project. It is early software, and the long trajectories measure wall-clock project lifetime rather than continuous execution or independent reproduction. **Production writes and final authority stay with the human**, so LoopX is not an autonomous production controller.
LoopX turns prior guidance about durable memory, bounded work, evidence-based completion and human authority into a small local state kernel that can span different agent runners. It supports the case for explicit governance across long-lived work while narrowing the evidence: its 200-hour trajectories show persistence over project time, not continuous autonomous execution or independently validated reliability.