Lexora — Personal AI workspace built around Desktop / 以 Desktop 为核心的个人 AI 工作台
# Add to your Claude Code skills
git clone https://github.com/haohaoxue-site/LexoraLast scanned: 8/31/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-08-31T10:35:38.579Z",
"npmAuditRan": false,
"pipAuditRan": true,
"promptInjectionRan": true
}Lexora is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by haohaoxue-site. Lexora — Personal AI workspace built around Desktop / 以 Desktop 为核心的个人 AI 工作台. It has 111 GitHub stars.
Yes. Lexora passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/haohaoxue-site/Lexora" and add it to your Claude Code skills directory (see the Installation section above).
Lexora is primarily written in TypeScript. It is open-source under haohaoxue-site on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Lexora against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Lexora 是一个以 Desktop 为核心的个人 AI 工作台。在你授权的范围内使用本地文件与工具,想你所想,行你所行。
Desktop 在本地运行,以任务为中心,将对话、本地上下文、工具执行、自动化和产物集中在同一个工作台中。

| 能力 | 描述 |
|---|---|
| 任务工作台 | 通过自然语言发起任务,持续呈现执行过程、运行历史与生成产物。 |
| 本地上下文 | 在授权目录中理解和处理文档、图片、文件与代码。 |
| 工具与控制 | 连接多种模型,使用 Skills、MCP 与本机工具,并在关键操作前请求确认。 |
| 自动化 | 创建定时与重复任务,记录每次执行过程与结果。 |
| 桌面反馈 | 通过通知和原生桌宠呈现任务状态。 |
| 层级 | 技术 |
|---|---|
| Desktop | Electron、Vue 3、TypeScript、Vite、Naive UI、UnoCSS |
| Agent Runtime | Pi SDK、MCP SDK、Node.js、SQLite、JSONL |
| Native Pet | Rust、GTK、Cairo、GDK Pixbuf |
pnpm install
pnpm dev:buddy
Web 将逐步成为 Desktop 在文档编辑、知识沉淀与公开发布方面的内容延伸。目前仍独立运行,并支持自部署。

页面树、富文本编辑、文档 AI、历史版本、单页发布和站点发布。
| 层级 | 技术 |
|---|---|
| Web | Vue 3、TypeScript、Vite、Vue Router、Pinia、Element Plus、UnoCSS |
| Editor | Tiptap、ProseMirror |
| API | NestJS、Fastify、Prisma、PostgreSQL、Redis、BullMQ |
| Agent | LangGraph、LangChain、PostgreSQL Checkpointer、Redis Streams |
| Infrastructure | Docker Compose、Nginx、RustFS |
pnpm install
cp infrastructure/.env.dev.example infrastructure/.env
pnpm dev:infra
pnpm dev:db:sync
pnpm dev
infrastructure/.env 是本地开发配置真源。pnpm dev 会先按白名单生成 apps/api/.env 和 apps/agent/.env;这些生成文件可以临时手改,但下一次运行 pnpm dev 会被覆盖。
lexora/
├── apps/
│ ├── web/ # Vue 3 前端应用
│ ├── api/ # NestJS API 服务
│ ├── agent/ # LangGraph AI 运行服务
│ ├── buddy/ # Lexora Desktop
│ └── website/ # 产品落地页与文档站点
├── packages/
│ ├── assets/ # 跨应用品牌与运行时资产
│ ├── contracts/ # 共享契约层:schema、endpoint、常量、领域类型
│ └── shared/ # 共享函数层
└── infrastructure/ # docker 及环境配置
Lexora 使用 AGPL-3.0-only 许可证。