loopx-project/loopx

Name: loopx-project/loopx
Author: loopx-project

Plugin插件 ⭐ 6,144 Apache-2.0 Subagents & Orchestration子代理与编排 Sessions & Context会话与上下文

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.

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

LoopX is an open, provider-agnostic stateful control plane built for long-horizon AI agents. It runs on top of existing agent harnesses instead of replacing them, and preserves critical state like objectives, progress, todos, evidence, quota, and handoff context across agent turns. To get started, users can clone the repository, install TypeScript and Python 3.11+ dependencies, and launch the personal workspace via the loopx dashboard CLI command. It officially supports multiple popular agent harnesses including Codex, Claude Code, and Cursor, and can also integrate with DeepSeek Harness.

LoopX is designed for AI agent developers and end users working on long-horizon software tasks. It offers a local-first personal workspace that centralizes long-term goals, attention queues, conversation context, tasks, files, and schedules that persist across restarts and different harnesses. When users reopen a project, they can inspect the previous turn’s state and supporting evidence before continuing the next approved action without losing any work progress. This workflow simplifies handoffs across sessions, supports human-in-the-loop review, and adds async collaboration via Lark inboxes for team use.

LoopX is released under the open-source Apache 2.0 license for all versions after v0.4.8, with older historical versions remaining under the original MIT license. Its core control plane is written in TypeScript, and it requires Python 3.11 or newer for supporting tooling and integrations. The current 1.0 release is usable and entering broader adoption, with core state and CLI contracts stable, while advanced integrations are experimental and disabled by default. LoopX is not a full autonomous agent platform, so users should follow local storage rules to avoid leaking private data.

LoopX是一个开源、厂商中立的有状态长周期AI智能体控制平面，采用本地优先架构，可为长周期任务保留目标、进度、待办、证据、配额和交接状态。它运行在现有智能体框架之上，不替换原有执行环境，支持Codex、Claude Code、Cursor等多个主流智能体环境，也可集成到DeepSeek Harness中使用。

LoopX面向需要处理长周期开发任务的AI智能体开发者和普通用户，提供了本地优先的个人工作空间来统一管理长期目标、注意力、会话、任务、文件和日程。用户重新打开项目后，可以查看上一轮的状态和证据，直接继续执行下一个允许的动作，不会跨会话丢失状态信息。

LoopX采用Apache 2.0许可证开源，核心采用TypeScript开发，同时支持Python 3.11及以上版本。当前1.0版本已经可用，正在进入更广泛的采用阶段，部分高级主机集成和高级功能仍处于实验性阶段，默认关闭。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：loopx（loopx-project/loopx）
仓库：https://github.com/loopx-project/loopx
本站详情页：https://www.yhbd.top/plugins/loopx-project-loopx/
本站登记：类型 plugin · 归类 多平台兼容工具（非 DSH 原生） · 许可证 Apache-2.0 · ⭐ 6144 · 最近提交 2026-10-03 · 主语言 Python · 未检测到 DSH 插件清单

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

No DSH plugin manifest detected - it may only carry the dsh-plugin topic, so the install method must be confirmed on the spot未检测到 DSH 插件清单：可能只是打了 dsh-plugin 话题，安装方式要现场确认
Not DSH-native: a multi-platform tool that may require Node / Electron or another runtime first非 DSH 原生，是多平台兼容工具：可能要先装 Node / Electron 等运行时

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add github:loopx-project/loopx

把 loopx-project/loopx 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

45.7 KB · 缓存于 2026-10-03 22:08:58 · 45.7 KB

LoopX

Give your agents a goal. Keep the work moving.

The open, local-first control plane for long-horizon agents and personal agent teams.
_{Keep goals, decisions and evidence across sessions. Work with Codex, Claude Code, DeepSeek Harness and other supported runtimes.}

Get started · Workspace · LHTB results · Docs · 简体中文

_{Source-built App on an authored Workspace stories replay; no live Agent execution · watch the 32-second walkthrough}

Start in Codex App in two steps. Install once:

python3 -m pip install --upgrade loopx && loopx workflow-skills --install

Restart Codex App, then type this in a thread opened on your project:

$loopx fix the open PR review feedback and keep the patch reviewable

_{LoopX connects the project, plans the work as Todos and sets up the heartbeat that keeps it moving. Claude Code uses /loopx <complex task> · other Agent hosts}

LHTB · 46 tasks · GPT-5.6 Sol: LoopX 1.0.3 Heartbeat reaches 0.4948 mean reward — +17.3% vs Plain Codex, +10.6% vs native Codex Goal.
_{Results and pass rates ↓}

More verified work. Less human attention. LoopX gives agents durable goals, bounded continuation, peer ownership and recoverable handoffs. Your runtime provides the model and tools; LoopX keeps track of what to do next, what is accepted, and when to ask you.

What you want to do	Start here
Keep a coding or research agent working across sessions	Install and start
Manage personal projects, schedules and decisions in one place	Personal Agent Workspace
Let agents collaborate and deliver verifiable results	Agent collaboration guide

Meet the Personal Agent Workspace

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 loopx-project/loopx 的 README.md。在 GitHub 查看原文 →