翻訳待ち：Agentrove: Self-hosted AI workspace for orchestrating coding agents

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。

Notifications You must be signed in to change notification settings Fork 61 Star 307 BranchesTags Open more actions menu Folders and files NameName Last commit message Last commit date Latest commit History 1,964 Commits 1,964 Commits .githooks .githooks .github/workflows .github/workflows backend backend desktop desktop frontend frontend mcp-server mcp-server sandbox/docker sandbox/docker screenshots screenshots scripts scripts .dockerignore .dockerignore .env.desktop.example .env.desktop.example .env.example .env.example .gitattributes .gitattributes .gitignore .gitignore .pre-commit-config.yaml .pre-commit-config.yaml LICENSE LICENSE README.md README.md docker-compose-production.yml docker-compose-production.yml docker-compose.yml docker-compose.yml rust-toolchain.toml rust-toolchain.toml Repository files navigation Self-hosted AI coding workspace for running and orchestrating Claude Code, Codex, Copilot, Cursor, Grok, and OpenCode agents from one interface. What It Does Runs Claude, Codex, Copilot, Cursor, Grok, and OpenCode through ACP adapters. Gives each workspace its own Docker or host sandbox. Combines chat, code editor, terminal, file tree, diffs, secrets, and git tools in one workspace. Supports workspaces from empty folders, git clones, existing local folders, or GitHub repositories. Streams agent sessions with cancellation, permission prompts, queued follow-up messages, file mentions, slash commands, and attachments. Includes sub-threads, pinned chats, worktree mode, personas, custom instructions, environment variables, and installed agent skills. Orchestrates multi-agent workflows through the bundled MCP server: a lead chat spawns worker sub-threads on any installed agent, model, and persona — in parallel worktrees when needed — then reviews their results. Provides GitHub-assisted repository browsing, pull request review, PR creation, reviewer selection, and git branch/commit/push/pull helpers. Ships as a Docker web app, a macOS desktop app, and a native iOS app. Orchestrating Agents Agentrove chats aren't just endpoints — they can drive each other. The bundled MCP server (mcp-server/) exposes the whole instance as tools (send_message, get_messages, list_models, list_personas, …), and every chat's agent has those tools available. That turns any chat into an orchestrator: a lead agent on a strong model that decomposes the work, routes each task to the right agent, and reviews what comes back. The primitives: Sub-threads — send_message(parent_chat_id=…) creates a worker chat grouped under the lead chat, in the same workspace and branch. Sub-threads stay flat (no nesting): the lead fans out, workers report back. Per-turn model and persona — each worker runs on any installed agent and model (model_id) with any persona (a custom system prompt). Typical fleet: a fast model with a read-only scout persona for codebase exploration, coding models for implementation, dedicated reviewer personas (bug hunting, structural quality) for QA. list_models reports each model's supported reasoning tiers (thinking_modes), so the lead dials effort per task. Isolated worktrees — worktree=true gives a worker its own git worktree, so parallel workers edit concurrently without conflicts. Polling and follow-ups — the lead polls get_messages until a worker's turn completes, judges the result against the actual code, and sends rework to the worker's own thread; follow-ups inherit the thread's previous model, persona, and reasoning settings. Unattended turns — orchestrated turns run in the agent's full-execution mode, so workers finish without permission prompts. A typical loop: the lead explores with a cheap fast model, hands a precise spec to a coding model in a sub-thread, fans reviewer personas out over the diff in parallel, triages their findings, delegates the accepted fixes — and owns the final result. Models, personas, and routing rules are all user-defined, so the same machinery drives whatever fleet you run. Quick Start Requirements: Docker Docker Compose git clone https://github.com/Mng-dev-ai/agentrove.git cd agentrove cp .env.example .env Set SECRET_KEY in .env: openssl rand -hex 32 Start Agentrove: docker compose up -d Open http://localhost:3000. Desktop Agentrove also has a macOS desktop app built with Tauri. It starts a bundled Python backend sidecar on an available 127.0.0.1 port and connects the frontend to it at launch. Download the latest Apple Silicon build from Releases. Build from source: cd frontend npm install npm run desktop:dev Mobile (iOS) Agentrove also builds a native iOS app with Tauri. Since iOS can't run the local backend sidecar, the app is a thin client: it talks to an Agentrove instance you already host (your Docker or production deployment), reachable from the phone over https/wss. Because the project is open source, you build and sign it yourself — nothing is hardcoded to anyone else's server. Requirements: macOS with Xcode (plus its iOS SDK and Simulator), the Rust iOS targets (rustup target add aarch64-apple-ios aarch64-apple-ios-sim), and CocoaPods. If your device runs an iOS beta whose SDK isn't in a stable Xcode yet, build against the latest stable Xcode's SDK (sudo xcode-select -s /Applications/Xcode.app) — apps built with an older SDK still run on newer iOS. Point the app at your instance: cd frontend cp .env.mobile.example .env.mobile # then set your https/wss URLs npm install Run in the simulator: npm run ios:dev Install on your own iPhone with a free Apple ID — no paid developer account needed (the app must be re-signed every 7 days): npm run tauri ios init generates the Xcode project (first run only). Open frontend/src-tauri/gen/apple/*.xcodeproj in Xcode once, pick your Team under Signing & Capabilities, and connect your iPhone (Xcode needs to register the device and create the provisioning profile). On the phone, enable Developer Mode (Settings → Privacy & Security), then after the first install trust the certificate under Settings → General → VPN & Device Management. Build a standalone .ipa and install it on the connected iPhone. The easiest path is the bundled helper, which builds, signs, exports, and installs in one step. It reads your team from APPLE_DEVELOPMENT_TEAM (so nothing is hardcoded to anyone else's team) and auto-detects the connected device: export APPLE_DEVELOPMENT_TEAM= # find it in Xcode → Signing & Capabilities cd frontend npm run ios:install Or run the steps yourself. The -c flag injects the team into both the build signing and the IPA export, so it stays out of the committed config: npm run ios:build -- --export-method debugging \ -c '{"bundle":{"iOS":{"developmentTeam":""}}}' # -> src-tauri/gen/apple/build/arm64/Agentrove.ipa xcrun devicectl list devices # find your device id xcrun devicectl device install app --device \ src-tauri/gen/apple/build/arm64/Agentrove.ipa To update the app later, re-run npm run ios:install — the standalone build runs on the phone without keeping a Mac connected. Production For a single-host Docker deployment: SECRET_KEY=$(openssl rand -hex 32) \ SERVICE_URL_WEB_80=https://yourdomain.com \ APP_URL=https://yourdomain.com \ ALLOWED_ORIGINS=https://yourdomain.com \ docker compose -f docker-compose-production.yml up -d --build Coolify / reverse proxy Point Coolify at the web service (port 80) using docker-compose-production.yml. Set: Variable Example APP_URL https://yourdomain.com ALLOWED_ORIGINS https://yourdomain.com SECRET_KEY 32+ char secret TRUSTED_PROXY_HOSTS * (default in production compose) If APP_URL / ALLOWED_ORIGINS are unset, the compose file falls back to Coolify's SERVICE_URL_WEB_80 (correct for production and PR previews). If /admin loads as plain unstyled HTML (blue links, no layout), the API is generating http:// URLs for SQLAdmin CSS/JS while the page is https://. Rebuild with the production compose above so nginx forwards Coolify's X-Forwarded-Proto and the API trusts the proxy. Coolify preview deployments (per PR) Advanced → enable Preview Deployments (and Allow Public PR Deployments if the repo is public / accepts fork PRs). Preview Deployments → set the URL template, e.g. pr-{{pr_id}}.yourdomain.com. Point a DNS wildcard (*.yourdomain.com or pr-*.yourdomain.com) at the Coolify server and let Coolify issue certificates. In Environment Variables → Preview Deployments, set: AGENTROVE_STORAGE_SOURCE=agentrove_storage (named volume; do not share production's host path) APP_URL / ALLOWED_ORIGINS empty or $SERVICE_URL_WEB_80 (so each preview gets its own origin) copy SECRET_KEY and other secrets from production Open a PR (or Load Pull Requests and deploy manually). Coolify spins up an isolated compose stack at the preview URL. The sandbox Docker network is per compose project (no fixed name), so preview sandboxes do not join production's network. Stack Frontend: React 19, TypeScript, Vite, Tailwind CSS, Monaco, xterm.js Backend: FastAPI, SQLAlchemy, SQLite, Redis Runtime: ACP, Docker or host sandboxes, Tauri desktop sidecar Community Join the Discord server. Contributing Contributions and feedback are welcome. License Apache 2.0. See LICENSE. Resources Readme Apache-2.0 license Activity Stars 307 stars Watchers 2 watching Forks 61 forks Report repository