First-class Linux packaging for DeepSeek Harness desktop — AppImage, .deb, .tar.gz for x64/arm64, built by native CI.
# Add to your Claude Code skills
git clone https://github.com/Zhou-Yujing114514/deepseek-harness-linuxGuides for using ai agents skills like deepseek-harness-linux.
See how deepseek-harness-linux compares with popular alternatives.
deepseek-harness-linux is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Zhou-Yujing114514. First-class Linux packaging for DeepSeek Harness desktop — AppImage, .deb, .tar.gz for x64/arm64, built by native CI. It has 57 GitHub stars.
deepseek-harness-linux's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/Zhou-Yujing114514/deepseek-harness-linux" and add it to your Claude Code skills directory (see the Installation section above).
deepseek-harness-linux is primarily written in TypeScript. It is open-source under Zhou-Yujing114514 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 deepseek-harness-linux 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.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
给官方 DeepSeek Harness 桌面端补上一等公民级的 Linux 打包 —— 开箱即用的 AppImage /
.deb/.tar.gz，覆盖 x64 与 arm64 双架构，配套原生 CI 与 AppImage 自动更新。
官方桌面端只发布 macOS 与 Windows；Linux 用户要么退而用 Web 版，要么自己从源码硬编。本项目就是这个缺口的补完：在保留官方桌面全部功能的前提下，把 Linux 当成正式支持平台来打包、测试、分发。
每次构建为每种架构产出三种安装包：
| 格式 | 用途 | 典型文件名 |
|---|---|---|
| AppImage | 单文件免安装，支持自动更新 | deepseek-harness-0.2.0-rc.2-linux-x64.AppImage |
| .deb | Debian / Ubuntu 系原生包管理 | deepseek-harness-0.2.0-rc.2-linux-x64.deb |
| .tar.gz | 便携解压即用 | deepseek-harness-0.2.0-rc.2-linux-x64.tar.gz |
支持架构：x64（AMD / Intel）、arm64（树莓派 5、Apple Silicon 上的 Linux、ARM 服务器等）。
.AppImage。sudo apt install libfuse2 # Debian / Ubuntu
# Fedora / RHEL 系: sudo dnf install fuse2
chmod +x deepseek-harness-*-linux-x64.AppImage
./deepseek-harness-*-linux-x64.AppImage
sudo dpkg -i deepseek-harness-*-linux-x64.deb
deepseek-harness # 或直接从应用菜单启动
tar -xzf deepseek-harness-*-linux-x64.tar.gz
cd deepseek-harness-*-linux-x64
./deepseek-harness # 运行解压目录内的启动入口
在无显示环境（如远程服务器 + VNC）运行时，确保已设置
DISPLAY（例如 xfce4 + TigerVNC 下的:1），桌面会自动拉起。
需要 Node.js 24+、pnpm，以及构建主机上的 libfuse2（AppImage 组装所需）。
git clone https://github.com/Zhou-Yujing114514/deepseek-harness-linux.git
cd deepseek-harness-linux
pnpm install
cp apps/desktop/.env.linux.example apps/desktop/.env.linux # 按需填写发布设置
pnpm --dir apps/desktop run package:linux:x64 # x64
pnpm --dir apps/desktop run package:linux:arm64 # arm64
Desktop (Linux) 工作流会在原生 runner 上按需构建两种架构（ubuntu-24.04 / ubuntu-24.04-arm），产物可在 Actions Artifacts 或自动发布的 Release 中获取。
AppImage 通过 electron-updater 走 AppImage 更新通道，更新描述符为 nightly-linux.yml，全程 HTTPS。未签名构建下，更新仅依赖 HTTPS 传输与 feed 元数据校验，无代码签名验签——请勿用于高信任场景，下载时务必核对 Release 附带的 SHA256。
本项目基于上游 MIT 许可证分发。DeepSeek Harness 由 DeepSeek-AI 开发，版权归其所有；Linux 打包层在同一 MIT 许可下新增。详见 LICENSE 与 THIRD_PARTY_NOTICES.md。