接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y [email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add opensquad-ai -- npx -y opensquad-ai@0.9.0在終端機中執行。
{ "mcpServers": { "opensquad-ai": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
OpenSquad is a local-first multi-agent collaboration framework. Multiple autonomous agents (PM, Coder, QA, etc.) communicate via group chat to coordinate and complete complex tasks.
OpenSquad enables multiple AI agents to collaborate like a real team. Each agent runs as an independent process with its own LLM connection, tool set, and memory. Agents communicate through group chat, coordinated by a PM agent, to tackle complex tasks that a single agent cannot handle alone.
A single AI agent has clear limitations when dealing with complex projects:
OpenSquad solves these through multi-agent collaboration: PM handles task decomposition and coordination, Coder focuses on implementation, QA independently verifies — each with a clear responsibility.
flowchart TB
User["User / Web UI"] --> GW["Gateway :9555"]
GW --> LA["Launcher :9600"]
LA --> PM["PM Agent"]
LA --> Dev["Coder Agent"]
LA --> QA["QA Agent"]
PM & Dev & QA --> IM["Group chat / IM"]
PM & Dev & QA --> Plugins["Plugins / MCP / Skills"]
Plugins --> Svc["Service plugins e.g. websearch :9001"]
Details: Architecture · Documentation hub
uv sync (or install.bat / install.sh).api_key in src/model_cards/ (see model cards guide).uv run opensquad init (creates ~/.opensquad/workspace by default).uv run opensquad start.http://127.0.0.1:5173 (or Gateway port from system_config).module.register, and transpiles their .ts / .tsx
with a vendored sucrase — so no Node-version-dependent type stripping)Windows
git clone https://github.com/opensquad-ai/opensquad.git && cd opensquad && install.bat
Linux / macOS
git clone https://github.com/opensquad-ai/opensquad.git && cd opensquad && bash install.sh
The script automatically: checks prerequisites → installs dependencies → initializes workspace → starts all services.
Note: After first start, add your LLM API key to a model card under
src/model_cards/.
uv is a fast Python package manager. Recommended.
# Install uv (if not already)
pip install uv
# Clone the project
git clone https://github.com/opensquad-ai/opensquad.git
cd opensquad
# Install dependencies (uses uv.lock for reproducible builds)
uv sync
# Install frontend dependencies
cd src/opensquad/gateway/nexuschat-pro && npm install && cd ../../..
# Initialize and start
uv run opensquad init
uv run opensquad start
From PyPI — runtime, built web UI and the default resources:
pip install opensquad
opensquad init
opensquad start
Since 0.8.48 the wheel is a complete deployment. It ships the default
model_cards/,plugins/,agents/,pymcp/,collab_cards/,role_cards/andskills/next to theopensquadpackage, soopensquad initseeds a runnable workspace andopensquad startfinds every service. One gap remains: a fresh pip workspace has nosystem_config.json(the wheel carries no template), so ports stay on their defaults — gateway 9555, launcher 9600, registry 9720, frontend 5173 — until you save one from the Web UI's Settings.
From a checkout — full deployment, editable install:
git clone https://github.com/opensquad-ai/opensquad.git
cd opensquad
pip install -e .
# Install frontend dependencies
cd src/opensquad/gateway/nexuschat-pro && npm install && cd ../../..
# Initialize and start
opensquad init
opensquad start
The npm package is a thin bootstrap: on first run it installs the
matching Python opensquad CLI, then forwards every command to it.
npm install -g opensquad-ai
opensquad init
opensquad start
Requires Node.js 18+ (Mods host: 20.6+) and Python 3.11+. npx opensquad-ai works too, with
no global install.
git clone https://github.com/opensquad-ai/opensquad.git
cd opensquad
# Start (auto-builds image)
docker compose up -d
# View logs
docker compose logs -f
After start, visit http://localhost:9555. Data is persisted in Docker volumes.
Custom configuration:
# Edit config
cp src/system_config.example.json src/system_config.json
# Fill in your LLM API Key...
# Mount config and start
docker run -d \
-p 9555:9555 -p 9600:9600 -p 9720:9720 \
-v opensquad-data:/data \
-v ./src/system_config.json:/app/src/system_config.json:ro \
opensquad
Use the row that matches how you installed OpenSquad:
opensquad update only installs anything for the packaged desktop app. It
cannot rewrite a pip / npm / source install, so on those it prints the command
from the table and exits — without touching your environment or your git state.
opensquad start launches all 4 services:
Open http://127.0.0.1:5173 in your browser to create and configure agents via the Web UI.
Run without installing:
python -m opensquad.cli start
Copy system_config.example.json to your workspace or src/system_config.json (see architecture-paths):
{
"hosts": { "gateway": "127.0.0.1" },
"ports": { "gateway": 9555, "launcher": 9600, "websearch": 9001 },
"auth": { "node_secret": "your-secret-here" }
}
Never commit real system_config.json, auth.json, or model cards with API keys.
LLM API keys live in model cards (src/model_cards/*.json). Agents are created via the Web UI at runtime.
Start here: Documentation hub → Getting started (EN)
Issues and Pull Requests are welcome! Please read the Contributing Guide and Code of Conduct first.
MIT License — see LICENSE for details.
Powered by OpenSquad Core
OpenSquad — Local-first Multi-Agent Collaboration Framework. npm bootstrap that installs the Python `opensquad` CLI and proxies commands to it.
{ "mcpServers": { "opensquad-ai": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Opensquad Ai 透過 stdio 在本機執行。
上次檢查時間:2026-10-28。 OpenSquad — Local-first Multi-Agent Collaboration Framework. npm bootstrap that installs the Python `opensquad` CLI and proxies commands to it.