UGT: Use the GitHub Thing

Name: UGT: Use the GitHub Thing
Author: auscaster

作者：auscaster版本 0.3.0i★ –i电脑或云端

注册名称com.usegithubthing/ugt

安装

概览

作者提供的说明（英文原文）

Get open-source GitHub projects running on your computer, with your AI app

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i3 项中通过 2 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 电脑或云端
传输方式: stdio, Streamable HTTP
分类: 开发者工具

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：3 项中通过 2 项
在作者的服务器上运行：你向它提出的内容会经过他们的服务器。
可以做 5 件事（工具） search_recipes, get_project, get_recipe, read_recipe_file …
注册中心没有列出需要填写的密钥。

你需要

在云端运行无需安装任何东西，通过互联网连接

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude：

打开 Settings → Connectors
点击 Add custom connector
粘贴下面的地址，然后点击 Add
如果要求登录，请登录作者的服务

https://mcp.usegithubthing.com/mcp

下载作者的 .mcpb 文件

链接指向作者自己的文件；我们不托管也不重新打包它。打开文件后，Claude Desktop 会进行安装。

在终端中运行这条命令

claude mcp add --transport http ugt https://mcp.usegithubthing.com/mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "ugt": {
      "url": "https://mcp.usegithubthing.com/mcp"
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "ugt": {
      "type": "http",
      "url": "https://mcp.usegithubthing.com/mcp"
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

ChatGPT 只能连接互联网上的服务器：

打开网页版 ChatGPT → Settings → Connectors (Apps)
点击 Create 或 Add（部分套餐需要先在 Advanced 中开启 Developer mode）
粘贴下面的地址，起个名字，然后保存
如果要求登录，请登录作者的服务

https://mcp.usegithubthing.com/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

工具名称和描述与服务器在 2026年11月6日报告的完全一致。这些内容由作者撰写，不是我们写的；我们以纯文本形式显示。

search_recipes
Find how UGT gets a job done on the user's own computer with open-source software from GitHub, such as subtitles, CAD, video or web pages to Markdown. Search by what the user wants done or by a project's name, or omit the query to list the newest recipes. A recipe is a verified w
get_project
Get how UGT runs one GitHub project, by owner/repo or its link: the recipes people have shared for it, each verified for one job. Every GitHub project works with UGT, so the result always says what to do next.
get_recipe
Get one recipe in full: what it takes and makes, what stays usable after a run, the settings it asks for, everything it can reach and why, where it was tested, and every file it runs.
read_recipe_file
Read one of a recipe's files, such as compose.yaml, its Dockerfile or recipe.json, to see exactly what it runs.
get_install
Get the one line that installs UGT on the user's Windows PC, Mac or Linux computer and connects it to their AI apps, UGT for Claude Desktop, and what each computer runs recipes in. Omit the computer to get every one.

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

! 注意
作者与仓库一致
发布者（usegithubthing.com）不是仓库所有者（auscaster）；可能是其他人代为上架的
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
✓ 通过
端点有响应
在 533 毫秒内响应（HTTP 200）
– 不适用
使用 OAuth 登录
无需登录
✓ 通过
工具描述中没有隐藏指令
已读取 5 个工具描述，未发现针对 AI 的隐藏指令

与“开发者工具”中的其他服务器比较i

星标数多于此分类中其他 1394 个服务器的 0%
发布到注册中心的时间比此分类中其他 1394 个服务器的 95% 更新
基础检查结果等于或优于此分类中其他 1394 个服务器的 25%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

UGT: Use the GitHub Thing 安全吗？

它在 3 项适用的基础检查中通过了 2 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

两种方式都可以：安装在你的电脑上，或者连接云端版本。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（0.3.0）于前天进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。

有什么可以替代它？

同一分类中有：GitHub, Desktop Commander, Cloudflare MCP

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

GitHub

作者：github

Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.

电脑或云端★ 34,245MIT3天前更新

安装

Desktop Commander

作者：wonderwhy-er

MCP server for terminal commands, file operations, and process management

在你的电脑上运行★ 10,225MIT16天前更新

安装

Cloudflare MCP

作者：cloudflare

Cloudflare MCP servers

在云端运行★ 4,446Apache-2.014个月前更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

You found it on GitHub. Now use it.

Paste the GitHub link to the project you want to use.

UGT helps get it working on your computer and shows you how to use it again.

Free and open source. Windows, Mac and Linux.

How it works · Get started · What you can do · Why not just ask your agent? · The catalogue · Share your recipe · House rules

How it works

Start with the GitHub link. You can also add an error you ran into or something you want to do with the project.
Follow the setup for your computer. UGT looks for a ready setup or the project's own installer. If it needs a closer look, your AI app continues with the same link and details. A recipe is a setup someone has already checked; your agent can make one when the project has none.
Use what it made. Open the resulting file or app. File jobs check their output, and apps keep their saved data when you stop and reopen them. If a run fails, ask for help with that run without starting the conversation over.
Share it, if you like. Once it works, UGT can submit your recipe to the catalogue, so the next person gets it fast.

Get started

Paste your GitHub project into UGT. The link is enough. If you already tried to install it, you can include the error you saw.

UGT checks for a way to use that project on your computer. If it offers Open in UGT, open it, choose your file if it needs one, and run it. When a file is ready, UGT shows you its folder. An app opens at its own address.

If the project needs a closer look, continue in your desktop AI app. The website carries your link and notes into the project message. If UGT needs installing, it shows how to set it up. UGT has no subscription; your AI app's own usage limits and pricing still apply.

Set up UGT yourself

Claude Desktop: install the UGT desktop extension for your computer. The project page helps you pick the download.
On a Mac or Linux: open Terminal and run curl -fsSL https://usegithubthing.com/install | sh.
On Windows: open PowerShell and run irm https://usegithubthing.com/install.ps1 | iex. Windows may ask for permission and a restart.

Return to your project when setup finishes. On an Intel Mac, start Docker Desktop, OrbStack or Docker Engine first.

For developers

Where	How
Windows	`scoop bucket add auscaster https://github.com/auscaster/scoop-bucket`, then `scoop install ugt`	Today
Windows	`winget install auscaster.ugt`	Next
macOS or Linux	`brew install auscaster/tap/ugt`	Today
Linux	`curl -fsSL https://usegithubthing.com/install \	sh`	Today
Any MCP client	`com.usegithubthing/ugt` in the MCP Registry, or `ugt mcp` over stdio	Today
Any AI app, with nothing installed	The hosted MCP server `https://mcp.usegithubthing.com/mcp`: it finds how UGT runs a project, shows what a recipe runs and reaches, and gives the line that installs UGT	Today
Claude Code, Codex, Gemini CLI	UGT's plugin: `claude plugin install ugt@auscaster` after `claude plugin marketplace add auscaster/agent-plugins`, the same for Codex, or `gemini extensions install https://github.com/auscaster/ugt`	Today
Your browser	A "Use it" button on every GitHub repository	Next
From source, any OS	`go install github.com/auscaster/ugt/cmd/ugt@latest`, then `ugt setup` and `ugt connect`	Today

What you can do with it

GitHub is the world's biggest shelf of free software, and most of it never reaches the people it could help, because it ships as code, not as an app. UGT turns any of it into something you can just ask for.

Ask your agent	What runs
"Put subtitles on this interview"	openai/whisper: speech to text, fully offline. Verified recipe
"Turn my HTML into a four-second intro video"	heygen-com/hyperframes: a headless browser and ffmpeg. Verified recipe
"Design a wall hook I can 3D print"	earthtojake/text-to-cad: an industrial CAD kernel. Verified recipe
"Save these pages as clean Markdown, on my own computer"	firecrawl/firecrawl: a five-service crawler stack. Verified recipe
"Cut the background out of this photo"	danielgatis/rembg: an image segmentation model
"Convert this PDF and Word file to Markdown"	microsoft/markitdown: Microsoft's document converter
"Read this paragraph aloud"	debpalash/VoiceStudio: local text to speech
"List the functions in this program"	NationalSecurityAgency/ghidra: the NSA's reverse-engineering suite, headless

A few featured examples. You never need a recipe from the catalogue: without one, your agent works the project out the first time. A recipe just makes it faster, because someone already did.

Why not just ask your agent?

Your agent can read the code. It usually can't run it for you, and it starts from zero every time.

Most of GitHub assumes Linux. On Windows and on a Mac your agent hits a wall. UGT brings its own private Linux engine, set up in one step, on Linux too: no Docker Desktop, no account, nothing to learn. On an Intel Mac it drives the engine you already have.
Proven once, quick for everyone after. The first agent to get a project working can spend an hour building and fixing: memory limits, wrong-architecture binaries, missing system libraries, a resolver that cannot find the internet. The recipe it leaves behind turns the next person's run into a download.
Proof, not "it started". A container starting is not your job done. Every recipe carries a check that fails unless the output is real: subtitles that fit the recording, a video of the length you asked for, a mesh you can actually print.
Your machine, your files. Projects run in a sandbox with only the files and access their recipe declares. The catalogue reviews that access before admitting a recipe; UGT asks before a locally made recipe reaches beyond its ordinary sandbox. Cloud compute requires your agreement and a stated cost.

The catalogue

Recipes are a shortcut, never a requirement. Each one is a project someone already got doing a job, shared so nobody has to work it out again. A recipe is a folder anyone can read, in recipes/: a compose.yaml that holds everything that runs, and a recipe.json that says what it does. One project can have many recipes, one per job.

Browse them at usegithubthing.com/recipes, or read their source in recipes/. Every one was verified on clean machines before it was admitted, and a new recipe works for everyone the moment it lands, with no update to UGT.

Verified means every service ran as written on clean amd64 and arm64 machines and passed both checks, and both checks rejected deliberately broken outputs. A featured recipe's image is the one that was verified; any other builds on your machine from the same pinned commit and bases.

What's inside a recipe

recipes/openai/whisper/subtitles/

compose.yaml everything that runs: build, limits, mounts, network, and the four services recipe.json what it is: project, commit, task, settings, the access it needs, licence Dockerfile fetches the pinned source itself, so the build needs no clone check/ the check scripts

Service	Does
`task`	Your job, on your files
`check`	Fails unless the job really happened, whatever your input was
`sample`	Puts a known input in place
`sample-check`	Fails unless the known input gave the known answer

It is plain Compose, so there is no new language to learn, and every recipe runs anywhere Compose does. The recipe reference has the rules.

Share your recipe

Got a project doing something useful? Share it, so the next person gets it fast instead of working it out again.

Tell your AI "Use the GitHub Thing: share this recipe", or run ugt recipe submit. UGT checks it runs again from scratch, makes sure nothing personal goes with it (your files, paths and keys), and opens a pull request as you. It is then verified on clean machines with no secrets available, and admitted once it passes; a maintainer reviews any recipe that reaches beyond its sandbox first.

Coming with the UGT app. Until then, from the source:

go install github.com/auscaster/ugt/cmd/ugt@latest

ugt recipe new / # start one, or adopt the project's own Compose file ugt recipe verify # until it passes ugt login # once: approve a code in your browser ugt recipe submit # opens the pull request as you

ugt recipe submit --dry-run shows exactly what would be sent first. CONTRIBUTING.md and the catalogue rules have the details.

Maintain a project? A "Run with UGT" badge is on the way: put it in your README, and one click opens your project in UGT.

House rules

Your files stay yours. Inputs are copied in. Your home folder, keys and the container engine are never handed to a project unless its recipe says why and a maintainer reviewed it, or you agree.
Run anything, hide nothing. A recipe can need the internet, a folder, a device or more. It declares each one, and UGT refuses anything it did not declare. A maintainer reviews it before the catalogue admits it; a recipe from anywhere else asks you before it reaches your computer.
Proof or it didn't happen. No check, no success.
You decide. Installs, admin prompts, big downloads, accounts, keys and cloud compute are always your call, asked plainly before they happen.
Secrets never pass through your agent. UGT asks you for them itself, once, and they live in your system keychain.
Credit travels with the code. Every recipe records its project's licence, and files adapted from upstream keep theirs.
**Your files never leave your

只显示了开头部分；其余内容请在仓库中阅读