MAI-UI
MAI-UI: A foundational GUI agent model for real-world applications, available in multiple scales.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 1.8k
- Source
- mcp-github
- Repository
- github.com/Tongyi-MAI/MAI-UI
Overview
MAI-UI is a series of foundational GUI agent models spanning from 2B to 235B parameters. It leverages MCP enhancement for user interaction and task completion, supports device-cloud collaborative systems, and employs large-scale reinforcement learning techniques. This enables AI to better handle GUI-related tasks such as interface understanding and navigation. Ideal for developers requiring complex GUI operations in mobile or desktop environments.
Capabilities
- ▪User interaction and MCP enhancement
- ▪Device-cloud collaborative system
- ▪Large-scale reinforcement learning
- ▪SOTA performance on GUI benchmarking
Use cases
Setup
Please refer to the official documentation for installation and configuration.
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with MAI-UI?
Please visit the project's official website and follow the quick start guide for installation and configuration.
What model sizes does MAI-UI support?
Supports models of various scales, including 2B, 8B, 32B, and 235B-A22B.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.