Spec Driven Development
作者：formulahendry
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
在你的电脑上运行★ 440MIT14个月前更新
安装
Tares
概览
作者提供的说明（英文原文）
Always-on AI agents: a software factory for Claude Code, or an AI SRE that watches your systems.
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i1 项中通过 1 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: 在你的电脑上运行
- 传输方式: stdio
- 分类: 其他
- 你需要填写：TARES_AUTH_TOKEN
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：1 项中通过 1 项
- 在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
- 需要你自己填写：
TARESD_URL,TARES_AUTH_TOKEN
标为机密的值是你账户的钥匙。千万不要分享给别人，也不要粘贴到聊天里。
你需要
- PyPI已安装 Python 的 uv（用于 uvx 命令）
你用的是哪个应用？
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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"tares": {
"command": "uvx",
"args": [
"tares",
"mcp",
"--transport",
"stdio"
],
"env": {
"TARESD_URL": "your-value",
"TARES_AUTH_TOKEN": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add tares --env TARESD_URL=your-value --env TARES_AUTH_TOKEN=your-value -- uvx tares mcp --transport stdio运行前请先填写空着的值。
或者自己复制设置
粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json
{
"mcpServers": {
"tares": {
"command": "uvx",
"args": [
"tares",
"mcp",
"--transport",
"stdio"
],
"env": {
"TARESD_URL": "your-value",
"TARES_AUTH_TOKEN": "your-value"
}
}
}
}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。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"tares": {
"type": "stdio",
"command": "uvx",
"args": [
"tares",
"mcp",
"--transport",
"stdio"
],
"env": {
"TARESD_URL": "your-value",
"TARES_AUTH_TOKEN": "your-value"
}
}
}
}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。
这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上，无需账户。
需要你填写的值
TARESD_URLenvAddress of the Tares the server talks to. Start one with `tares up`.- Token or API key for a Tares that has auth on. Leave empty for a local Tares without auth.
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
它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。
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
- ✓ 通过
作者与仓库一致
注册名称已通过域名 glassflow.ai 验证（注册中心会核实域名所有权）
- … 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
- – 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表
与“其他”中的其他服务器比较i
- 星标数多于此分类中其他 32683 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 32683 个服务器的 88% 更新
- 基础检查结果等于或优于此分类中其他 32683 个服务器的 100%
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
Tares 安全吗？
它在 1 项适用的基础检查中通过了 1 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？
你需要填写：TARES_AUTH_TOKEN
它在我的电脑上运行还是在云端？
它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。
它还在维护吗？
GitHub 仓库最后更新于–，最新版本（1.55.1）于4天前进入注册中心。
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。你的电脑上还需要有 Python (uv)。
有什么可以替代它？
同一分类中有：Spec Driven Development, Remote Desktop Commander, MCP Server Autocad Lisp Helper
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
Remote Desktop Commander
作者：desktop-commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
在云端运行★ 211前天更新
安装
MCP Server Autocad Lisp Helper
作者：radwanalmsora
High-precision static analysis and debug server for AutoCAD AutoLISP (.lsp) files.
在你的电脑上运行今天更新
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。
Tares
The open-source platform for always-on AI agents.
Most agents wait for a prompt and forget everything when the session ends. Tares gives agents a place to work from: events from your systems land on one timeline per thing, agents wake when something happens, and what they decide (findings, plans, tickets, reviews, your answers) is kept for the next reader, human or agent. Works with Claude Code, Cursor, Codex and your own agents over MCP.
What you can build with it
Agents that watch your systems
Connect anything that emits events: logs, metrics, alerts, deploys, commits, database rows, webhooks. Tares merges them into one time-ordered timeline per service, repo, customer or job, and a trigger wakes an agent the moment something matters, with that timeline already in hand. The agent writes its conclusion back onto the timeline.
- An AI SRE: an alert fires, the agent reads the service's whole history and writes the diagnosis before anyone opens a dashboard.
- Shared code context: when a change matters, an agent updates the team's context repository with a pull request.
- Anything with a failure mode: failed jobs, sandbox runs, voice calls, each with a timeline, a trigger and a finding that says what broke.
A software factory
One crew of Claude Code sessions on your machine builds every project you hand it. You plan a project with Claude; an orchestrator hands out the tickets, builders open pull requests, a reviewer holds every change to a fixed bar, and builders merge once it passes and CI is green. You talk to one session, and only for decisions that are yours.
- Plan once: a spec, milestones with acceptance checks, and tickets with a working doc each.
- Build in parallel: one crew serves every project, a builder per milestone and repo.
- Nothing is lost: tickets, reviews, the crew's assumptions and your answers live on Tares, so the crew carries on after a restart and you can check every choice it made.
→ Software factory, A project, end to end
Why Tares
- One read instead of ten tool calls. An agent asks about a thing once and gets its correlated history across every source.
- Agents that run on events, not prompts. Triggers wake your agent over MCP or a webhook, or run a Tares agent in-process.
- A record that outlives the session. Findings, plans, tickets, reviews and decisions stay on Tares for the next reader.
- Bring your own agent. Claude Code, Cursor, Codex or your own loop, over MCP. Any model provider for Tares's own agents.
- Yours to run. MIT licensed, one daemon and one DuckDB file on your machine or server. No external database, no broker, no telemetry.
Quickstart
uv tool install tares # or: brew install glassflow/tap/tarestares up # daemon + console on http://127.0.0.1:8787 tares mcp --transport streamable-http # in a second terminal: the MCP endpoint, :8788/mcp
Then pick what you came for.
Give an agent your systems. Add a source under Sources → Add source in the console (or start the demo stack to break something on purpose), and connect your agent:
claude mcp add --transport http tares http://localhost:8788/mcpAsk it: *"Use tares: what happened to api-server in the last 15 minutes?"* → Quickstart
Build software with a crew. Needs Claude Code (signed in, on a plan with background sessions) and gh with write access to your repos:
tares factory crew up # start the crew; the first run asks how far it may gotares factory spec "what you want to build" # in your repo: plan the project and hand it over tares factory crew attach orchestrator # answer the crew's questions
Watch it on the Crew page of the console. → Software factory
Prefer not to run it yourself? [Tares Cloud](https://console.tares-glassflow.com/) is the managed version, with the MCP endpoint already running.
Learn more
| Concepts | sources, timelines, triggers, agents and projects |
| Connectors | Prometheus, OTLP, GitHub, Vercel, Postgres, webhooks, Claude Code sessions and more |
| Agents | connect any MCP client, or run Tares agents on a trigger |
| Software factory | the crew, its commands, and a project from spec to merged |
| Deployment | Docker, servers, TLS and auth |
| AI resources | for coding assistants: Markdown endpoints and instructions to paste |
Feedback
Bug reports and ideas are welcome via GitHub issues or help@glassflow.ai.
License
MIT. This licence covers everything in this repository except directories named ee, which are under the licence in ee/LICENSE.