loopx-project/loopx
Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.
About the project
LoopX is an open, provider-neutral control plane for long-horizon AI agents: it preserves goals, gates, todos, evidence, and quota across runs on top of Codex, Claude Code, Cursor, and other harnesses.
Useful for
- Run a multi-day engineering or research loop while preserving state across agent sessions
- Review and confirm protected changes via typed preview and receipts before publishing
- Hand off unfinished work between Codex, Claude Code, and other agents without losing goal state or evidence
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 5 stars so far today, about 7 expected by the end of the day.
- Top new repositories in the last 4 months: #77.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 5,900
- Stars in a day
- 7
- Forks
- 558
- Issues and pull requests
- 4,738
- Watchers
- 28
- Language
- Python
- License
- Apache-2.0
- Latest release
- desktop-main-35453151689-1 · September 19, 2026
- Created
- May 31, 2026
- Last push
- September 19, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 19, 2026Top new repositories in the last 4 months: #76
- September 18, 2026Top new repositories in the last 4 months: #77
- September 17, 2026Top new repositories in the last 4 months: #78
- September 16, 2026Top new repositories in the last 4 months: #78
- September 15, 2026Top new repositories in the last 4 months: #77
- September 14, 2026Top new repositories in the last 4 months: #79
- September 13, 2026Top new repositories in the last 4 months: #78
Similar projects
-
9.4
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.
-
8.3
tamaratran/fast-jev-compaction
Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…
-
8.1
latent-spaces/brag
An agent skill (Claude Code, Codex, opencode, etc.) that turns a project you just built into a short launch video with music, motion, and share copy — in one command. Rendering is powered by Hyperframes.
-
7.7
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.
-
7.5
trycua/cua
Open-source toolkit for computer-use agents: cloud and local desktops, an app automation driver, and benchmarks for training and evaluation. For those giving AI agents control of a computer.
-
7.1
Tencent/BrowserSkill
BrowserSkill connects AI agents (Cursor, Claude Code, Codex, etc.) to your already logged-in browser via the bsk CLI and an extension, letting the agent work in a separate window without interrupting you.