Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者による説明(英語の原文)
A personal work twin for every AI agent: your confirmed guidance and explicit grants, enforced.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
TWINMEUP_HOME必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"twin-me-up": {
"command": "uvx",
"args": [
"twin-me-up"
],
"env": {
"TWINMEUP_HOME": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add twin-me-up --env TWINMEUP_HOME=your-value -- uvx twin-me-up動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"twin-me-up": {
"command": "uvx",
"args": [
"twin-me-up"
],
"env": {
"TWINMEUP_HOME": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"twin-me-up": {
"type": "stdio",
"command": "uvx",
"args": [
"twin-me-up"
],
"env": {
"TWINMEUP_HOME": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
TWINMEUP_HOME envこの設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント GitDakky で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.2.1)がレジストリに届いたのは22 日前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにPython (uv)も必要です。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, Agent Data Tools: Utilities
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
103 tools: JSON repair, CSV, hashes, cron, dates, units, validators. 25 free calls.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Teach it once. Every agent you use works the way you would, and asks before it acts.
Quick start · One-prompt install · How it works · Works with · The research · Safety
You probably use more than one AI agent. Each one starts from zero. It does not know what you care about, which corners you never cut, or which decisions you always want to make yourself. So you repeat yourself, correct the same mistakes, and hope nothing consequential happens before you look.
Twin Me Up is a small, local, open-source service that gives every agent the same answers to three questions:
ask. Optional hooks enforce that outside the model.It is not a chatbot of you, a personality clone or an autonomous replacement for you. The evidence does not support those claims, and the research explains why.
| Learning you ratify | Agents propose lessons. Only you confirm, revise, reject or retire them. Every lesson keeps its origin, sources and history. |
| Authority you grant | Agents act on explicit grants for a workflow and named actions, optionally expiring. Actions in the reserved twin. namespace can never be granted to anyone. |
| Enforcement outside the model | Pre-action hooks for Hermes, Claude Code and pi block or escalate ungranted tool calls. They fail closed. |
| Evidence, not vibes | Freeze held-out decisions, then test the twin against a generic assistant and a rules-only baseline. Results come with sample-size warnings. |
| One twin, every agent | One MCP server, a native pi extension, a CLI bridge and function-calling schemas. Thirteen agent systems and frameworks documented, ten verified live. |
| Yours | Local SQLite with owner-only files, a tamper-evident audit log, portable export, and erasure that removes everything derived from a record. No telemetry. |
| A rules file or system prompt | Built-in agent memory | Twin Me Up | |
|---|---|---|---|
| Works across every agent you use | Copied into each one | Within one product | One twin, over MCP |
| Learns from your corrections | No | Often, automatically | Yes, as proposals |
| You approve what it learns | You write all of it | Usually after the fact | Always, before it counts |
| Stops actions you have not allowed | No | No | Yes: grants, ask and hooks |
| Shows whether it actually helps | No | No | Held-out tests against baselines |
| Where your data lives | Your files | The vendor | Your machine |
You need Python 3.11 or later and uv (or pipx). macOS and Linux are tested. Windows should work but is untested.
uv tool install twin-me-up # or: pipx install twin-me-up
twinmeup init # your name and a passphrase, in your own terminal twinmeup connect --list # every supported agent system twinmeup connect claude-code # the exact steps for one of them, with your paths twinmeup doctor # check everything, including a live MCP handshake
twinmeup init asks for your name and a passphrase. The passphrase guards everything only you should do: confirming lessons, granting authority, exporting and erasing. Agents are never given it, and those commands refuse to run without it.
Only need the MCP server? After twinmeup init, any MCP client can start it with uvx twin-me-up. Prefer the latest code? uv tool install git+https://github.com/GitDakky/twin-me-up.
Upgrading? Run uv tool upgrade twin-me-up (or pipx upgrade twin-me-up), then twinmeup doctor. The FAQ explains what an upgrade changes for your twin.
Using Claude Desktop? After twinmeup init, download the .mcpb desktop extension from the latest release and open it. One bundle works on macOS, Windows and Linux.
Already working inside an agent? Paste this into it.
Copy-paste install prompt
Install Twin Me Up for me and connect it to yourself. Twin Me Up is a local, open-source
work twin: it learns how I make decisions, briefs you at the start of work and tells you when you need my approval. Repository: https://github.com/GitDakky/twin-me-up
Work step by step and show me each command you run.
twinmeup init myself, in my own terminal, and wait until I say it is done. It sets my name and a passphrase that only I know. Do not run it for me, do not ask me for the passphrase, and never type a passphrase anywhere.twinmeup connect --list, pick the entry that matches you (or generic), then run twinmeup connect and carry out the steps it prints to register the MCP server and install the skill. If it offers optional enforcement hooks, show me the action map and the hook configuration first, and install them only if I agree.twinmeup doctor and report the result.While you work with my twin:
The agent installs the package, connects itself and checks the result. The two steps that matter stay with you: choosing the passphrase, and approving any enforcement hooks. The prompt is also in docs/install-prompt.md.
flowchart LR
you([You]) twin[("Your twin local store")] agent["Any agent"] hook{{"Pre-action hook"}} you -- "confirm lessons grant and approve" --> twin twin -- "candidate lessons to review" --> you agent -- "twin_brief twin_authorise request approval" --> twin agent -- "record decisions and corrections" --> twin agent -. "every governed tool call" .-> hook hook -- "ungranted: block or ask" --> agent hook -- "checks grants" --> twin
twin_brief. It gets your confirmed guidance for the workflow, with boundaries and escalation rules always included, and a list of what it is authorised to do.twin_authorise. The answer is allow only when a live grant covers the action. Otherwise it is ask: the agent prepares a draft, requests your approval and waits for your decision.| Tool | What it does |
|---|---|
twin_brief | Your confirmed guidance and current authority for a workflow. Call it at the start of work. |
twin_authorise | May I do this now? Returns allow with the covering grant, or ask. |
twin_request_approval | Ask you to approve one action. You decide in your own terminal. |
twin_approval_status | Has the request been approved, declined or not yet decided? |
twin_search | Find confirmed guidance relevant to a question. |
twin_review_queue | Unconfirmed lessons to show you for review. |
twin_track_record | Evidence and stage for a workflow: learning, corrections, evaluations and grants. |
twin_next_questions | The most valuable unanswered questions about a recorded decision. |
twin_record_decision | Capture a real decision: situation, options, choice, reasons. |
twin_amend_decision | Merge your answers to follow-up questions into a recorded decision. |
twin_record_correction | Record when you edit, override or reject the agent's work. |
twin_propose_lesson | Propose a lesson. It has no authority until you confirm it. |
These commands need your passphrase, so agents cannot run them.
| Command | Purpose |
|---|---|
twinmeup init | Set your name and passphrase |
twinmeup lesson confirm, reject, revise, retire | Decide what your twin has learned |
twinmeup grant add, revoke | Give or withdraw authority |
twinmeup approvals approve, decline | Decide what agents have asked to do |
twinmeup eval create, add-case, from-episode, freeze | Build held-out evaluation sets |
twinmeup export | Write a portable bundle of your twin |
twinmeup erase episode | Erase a decision and everything derived from it |
An agent that needs an action it has not been granted asks for it, then waits:
twin_authorise says ask. The agent prepares a draft and calls twin_request_approval with a one-line summary of what an冒頭だけを表示しています。続きはリポジトリで読めます