What are the prerequisites for running AIOS Monorepo?
Node.js (LTS recommended) and npm, Python 3.12.4 and pip, and the `uv` Python package manager.
@AndyLeong33dev
基本信息
This repository contains all source code for AIOS (Langchain server, Website, Desktop application). This will be a good example using MCPs
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"AIOS-source-code-for-MVP": {
"command": "uv",
"args": [
"venv"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
The AIOS Monorepo contains the Artificial Intelligence Operating System (AIOS) project, split into an Electron-based desktop frontend application and a Python-based LangGraph backend server. It is intended for developers who want to build or run AIOS locally.
Set up the backend first: navigate to aios-langgraph-server, copy .env.example to .env, create a virtual environment with uv venv, activate it, run uv sync, then start the server with langgraph dev --no-browser. Then set up the frontend: navigate to aios-desktop-app, copy .env.example to .env, run npm install, then launch with npm run dev. The desktop app connects to the locally running backend.
uv Python package managerNode.js (LTS recommended) and npm, Python 3.12.4 and pip, and the `uv` Python package manager.
After setting up the `aios-langgraph-server` directory, activate the `uv` virtual environment and run `langgraph dev --no-browser`. The server typically starts at `http://localhost:2024`.
After setting up the `aios-desktop-app` directory, run `npm run dev` to launch the Electron application with hot‑reloading enabled.
Both the backend and frontend use a `.env` file copied from `.env.example`. You must fill in necessary variables (e.g., API keys, database credentials) before running.
Navigate to `aios-desktop-app` and use the commands `npm run build:win`, `npm run build:mac`, or `npm run build:linux` for the respective platform.

Manage your Skycloak-hosted Keycloak: clusters, realms, apps, SSO and users, from any MCP client.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

Publish the website your AI assistant just built, straight from the conversation. Static sites, your own domain, one payment, no subscription.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a
评论