Awesome AI AgentsMCP Server Framework

trycua/cua

⭐ 22604 Python added to this list on 2025-03-20 repository created 2025-01-31

c/ua (pronounced "koo-ah", short for Computer-Use Agent) is an advanced framework designed to enable AI agents to control full operating systems within high-performance, lightweight virtual containers. It leverages Apple's Virtualization.Framework to create and run macOS and Linux virtual machines on Apple Silicon hardware with near-native performance, achieving up to 97% of native speed. This makes it highly efficient for running complex AI workflows in isolated environments. The framework offers two main capabilities: high-performance virtualization and a computer-use interface for AI agents. The virtualization component, accessible via the Lume CLI, allows users to manage virtual machines with exceptional speed and security. The computer-use interface enables AI systems to observe and interact with these virtual environments, allowing them to perform tasks such as application control, web browsing, coding, and executing complex workflows autonomously. c/ua emphasizes security and isolation by running AI agents in fully isolated virtual environments rather than on the host system, reducing risks associated with granting AI direct access to the main operating system. It supports both macOS and Linux environments, providing flexibility and reproducibility for AI workflows. The framework also integrates with various large language model (LLM) providers, facilitating seamless AI agent operation. The project includes multiple libraries within a monorepo structure: Lume for VM management, Computer for the computer-use interface, Agent for running agentic workflows, and several accessory libraries for core functionality and server components. It supports Python 3.10+ and requires Apple Silicon Macs running macOS 15 or newer. Users can quickly get started by installing the Lume CLI for virtualization or the full suite for AI agent capabilities, including Python libraries and VM images. The project provides extensive documentation, example notebooks, and demos showcasing AI agents performing real-world tasks. It also offers a Gradio UI for interactive agent use. Overall, c/ua is a cutting-edge platform for securely running AI agents in high-performance virtualized environments, enabling sophisticated autonomous workflows on Apple Silicon Macs.

https://github.com/trycua/cua

agent-frameworkai-agentsai-workflowsapple-siliconc/uacomputer-interfacecomputer-use-agentgradio-uihigh-performanceisolated-environmentsisolationlightweight-virtual-containerslinuxllm-integrationlume-climacosmonorepopythonreproducibilitysecurityvirtualizationvirtualization.frameworkvm-management

Also in MCP Server Framework

thedaviddias/Front-End-Checklist

Front-End Checklist is an open-source quality system for modern web development, offering comprehensive best practices for humans and AI agents.

PrefectHQ/fastmcp

FastMCP offers a Pythonic framework for building Model Context Protocol (MCP) servers and clients, facilitating structured communication for AI agents and models.

pascalorg/editor

Local-first 3D building editor built with React Three Fiber and WebGPU that exposes an MCP service so AI agents can create and edit 3D scenes.

nukeop/nuclear

Nuclear is a free, open-source, ad-free music player for Windows, macOS, and Linux, featuring streaming from various sources, playlist management, a powerful plugin system, and integration with AI ...

googleapis/mcp-toolbox

MCP Toolbox for Databases is an open-source server that connects AI agents and applications to enterprise databases using the Model Context Protocol (MCP).

apify/apify-mcp-server

Model Context Protocol server that exposes thousands of Apify Actors as tools, letting AI agents scrape social media, search engines, maps and e-commerce sites over hosted HTTP or local stdio.

grab/cursor-talk-to-figma-mcp

Cursor Talk to Figma MCP is an integration that enables Cursor AI to communicate with Figma programmatically for reading and modifying designs, automating and enhancing the design workflow.

Helicone/helicone

Helicone is an open-source LLM observability platform that enables developers to monitor, evaluate, and experiment with large language model applications through easy integration and comprehensive tools.