GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者提供的说明(英文原文)
Query a codebase map (routes, features, flows, impact) built by static analysis.
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。
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。
选择你使用的 AI 应用,然后复制设置。
你需要
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": {
"devmap": {
"command": "npx",
"args": [
"-y",
"@flaid/devmap",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add devmap -- npx -y @flaid/devmap mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"devmap": {
"command": "npx",
"args": [
"-y",
"@flaid/devmap",
"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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"devmap": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@flaid/devmap",
"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。
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。
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。
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6日
注册名称已通过 GitHub 账户 itsflaid 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
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。
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。
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)。
GitHub 仓库最后更新于–,最新版本(0.9.0)于6天前进入注册中心。
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 Node.js。
同一分类中有:GitHub, Desktop Commander, Cloudflare MCP
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
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
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。
Analyze once. Reuse context everywhere. A CLI that maps your codebase for developers and AI agents: entry points, critical files, features and routes.
Documentation · Website · GitHub
Every new AI chat about your code starts from zero — you re-explain the same codebase every time. DevMap fixes that.
It's a CLI that combines static analysis with optional AI interpretation to build a structured, reusable understanding layer of your project — once. That layer (.devmap/index.json, feature maps, DEVMAP.md) is what you and any AI agent read afterward, instead of re-scanning or re-pasting the whole repo. Full repo source stays local — nothing gets sent wholesale to the AI model.
npm install --global @flaid/devmap
Or run without a global install:
npx @flaid/devmap --help
Static analysis still works when AI is not configured.
Run these commands from the root of the project you want to understand:
devmap init
devmap analyze devmap onboarding devmap doctor
devmap init selects a provider, validates its key, stores configuration locally, prepares .devmap/, generates DEVMAP.md, and integrates with AGENTS.md safely.
Choose Groq, OpenRouter, or a custom OpenAI-compatible endpoint with the arrow keys during:
devmap init
Groq keys are available at https://console.groq.com/keys. OpenRouter keys are available at https://openrouter.ai/keys.
For custom endpoints, DevMap asks for the base URL (prefilled with http://localhost:20128/v1) and lists the models your server exposes, so any OpenAI-compatible self-hosted gateway works out of the box.
For OpenRouter, DevMap prompts:
OpenRouter model [openrouter/free]:
Press Enter to use the free router, or type any free or paid OpenRouter model ID. The selected model is saved and used as the primary choice.
For non-interactive Groq setup:
GROQ_API_KEY="your-key" devmap init
On PowerShell:
$env:GROQ_API_KEY="your-key"
devmap init Remove-Item Env:GROQ_API_KEY
For non-interactive OpenRouter setup:
OPENROUTER_API_KEY="your-key" devmap init
The key is stored locally in ~/.devmap/config.json. Requests go directly from your machine to the selected provider. DevMap does not send the key to a DevMap-owned server.
devmap init
devmap analyze devmap analyze --fresh devmap map # full project map devmap map # scoped to one feature or file devmap flow # curated top flows devmap flow devmap explain # file, feature, or function devmap onboarding --write devmap onboarding --write --language id devmap doctor devmap config model auto devmap mcp # run as an MCP server
Groq and OpenRouter use the model selected during init. Change either provider's model with:
devmap config model <model-id>
devmap config model auto
devmap mcp runs DevMap as a Model Context Protocol server over stdio. An AI agent asks the project map questions with tool calls and gets structured JSON back, instead of reading a whole context file up front.
devmap analyze
claude mcp add devmap -- npx -y @flaid/devmap mcp
Other clients launch the same command (npx -y @flaid/devmap mcp) as a stdio server:
{
"mcpServers": { "devmap": { "command": "npx", "args": ["-y", "@flaid/devmap", "mcp"] } } }
Tools: devmap_overview, devmap_map, devmap_flow, devmap_routes, devmap_impact, devmap_find, devmap_analyze and, only with --allow-ai, devmap_explain.
The server is read-only and static by default: no AI provider is contacted unless you start it with --allow-ai, and it only writes inside .devmap/ when the agent calls devmap_analyze or you start it with --auto-refresh. Every answer reports whether the snapshot is stale. See the MCP guide for client setup and tool inputs.
DevMap generates:
.devmap/index.json for lightweight AI-agent navigation.devmap/features/*.json for focused feature maps and source priority.devmap/snapshot.json for the full structured project analysis archiveDEVMAP.md for human and AI-agent usage guidanceAGENTS.md only after confirmation when the file already existsExisting AGENTS.md and DEVMAP.md files are never overwritten.
Read .devmap/index.json first, open the relevant feature map, and inspect its sourcePriority files. Use .devmap/snapshot.json only when the lightweight navigation layer is insufficient.
Use --json for scripts, editors, CI, or AI agents:
devmap analyze --json
devmap onboarding --json devmap doctor --json
JSON mode writes one parseable JSON document to stdout without ANSI colors, terminal decoration, or streamed partial output.
Detection covers the full list above; Next.js and Express receive the deepest analysis. Multi-package workspaces are classified per project type, so a monorepo containing a CLI and a web app is reported as both.
.env files and common generated directories are ignored.MIT