SkillsPlugins & marketplacesHooksSlash commands

loopx-project/loopx

The control plane for 24/7 always-on agents. Turn long-horizon goals into verifiable results across Codex, Claude Code, and custom runtimes—from local SQLite to team scale.

Stars
6,739
+7 days
—
Forks
639
Language
Python
License
Apache-2.0
Last push
22 Nov 2026

Summary

Summary written by AI from the README; it may be imprecise.

This harness-neutral control plane coordinates long-running AI agents across runtimes like Claude Code, Codex, and DeepSeek Harness. It preserves goals, execution plans, decision trails, and verifiable evidence in a local SQLite store so work continues across sessions, restarts, and compaction cycles without context loss. Developers can oversee multi-day engineering or research tasks, configure recurring heartbeat schedules, and enforce human approval gates on protected actions.

Use it when

  • When running long-horizon engineering or research tasks that span multiple sessions and tool restarts
  • Need to maintain persistent goals, task state, and decision history across Claude Code or Codex runs
  • Want to schedule recurring agent heartbeats with explicit human approval gates for critical actions

Install

The README has no clear install command. See the instructions on GitHub.

Includes hooks that run shell commands on your machine. Read them before installing.

Stars over 90 days

Collecting: 2 of 90 days so far. The chart appears after 7 days.

Type to search the reference, templates and lessons.