Convert Figma logo to code with AI

microsoft logomagentic-ui

A research prototype of a human-centered web agent

7,756
798
7,756
60
View on GitHub

Top Related Projects

microsoft's avatar

fluentui

19,673

Fluent UI web represents a collection of utilities, React components, and web components for building web applications.

ant-design's avatar

ant-design

97,203

An enterprise-class UI design language and React UI library

mui's avatar

material-ui

97,572

Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.

chakra-ui's avatar

chakra-ui

40,131

Chakra UI is a component system for building SaaS products with speed ⚡️

tailwindlabs's avatar

tailwindcss

91,915

A utility-first CSS framework for rapid UI development.

storybookjs's avatar

storybook

88,611

Storybook is the industry standard workshop for building, documenting, and testing UI components in isolation

Quick Overview

Magnetic UI is an open-source project by Microsoft that provides a set of React components and hooks for building accessible and customizable user interfaces. It aims to offer a flexible and modern approach to UI development, with a focus on performance and ease of use.

Pros

  • Highly customizable components with a focus on accessibility
  • Built with TypeScript for improved type safety and developer experience
  • Lightweight and performant, with a modular architecture
  • Extensive documentation and examples

Cons

  • Relatively new project, which may lead to potential instability or frequent changes
  • Limited number of components compared to more established UI libraries
  • May require a learning curve for developers unfamiliar with React hooks and modern patterns

Code Examples

Creating a custom button with Magnetic UI:

import { Button } from '@microsoft/magnetic-ui';

const CustomButton = () => (
  <Button variant="primary" size="large" onClick={() => console.log('Clicked!')}>
    Click me
  </Button>
);

Using the useToggle hook for managing state:

import { useToggle } from '@microsoft/magnetic-ui';

const ToggleExample = () => {
  const [isOn, toggle] = useToggle(false);

  return (
    <div>
      <p>Toggle is {isOn ? 'ON' : 'OFF'}</p>
      <button onClick={toggle}>Toggle</button>
    </div>
  );
};

Creating a responsive layout with the Grid component:

import { Grid, GridItem } from '@microsoft/magnetic-ui';

const ResponsiveLayout = () => (
  <Grid columns={{ base: 1, md: 2, lg: 3 }} gap={4}>
    <GridItem>Item 1</GridItem>
    <GridItem>Item 2</GridItem>
    <GridItem>Item 3</GridItem>
  </Grid>
);

Getting Started

To start using Magnetic UI in your React project, follow these steps:

  1. Install the package:

    npm install @microsoft/magnetic-ui

  2. Import and use components in your React application:

    import React from 'react';
import { Button, TextField } from '@microsoft/magnetic-ui';

const App = () => (
  <div>
    <TextField label="Name" placeholder="Enter your name" />
    <Button variant="primary">Submit</Button>
  </div>
);

export default App;

  3. Customize the theme (optional):

    import { ThemeProvider, createTheme } from '@microsoft/magnetic-ui';

const customTheme = createTheme({
  colors: {
    primary: '#007bff',
    secondary: '#6c757d',
  },
});

const App = () => (
  <ThemeProvider theme={customTheme}>
    {/* Your app components */}
  </ThemeProvider>
);

Competitor Comparisons

microsoft logo

fluentui

19,673

Fluent UI web represents a collection of utilities, React components, and web components for building web applications.

Pros of Fluent UI

  • More mature and widely adopted, with extensive documentation and community support
  • Offers a comprehensive set of UI components and design system
  • Provides better integration with Microsoft products and services

Cons of Fluent UI

  • Larger bundle size and potentially higher learning curve
  • Less flexibility for customization compared to more lightweight alternatives
  • May have more opinionated design choices that don't fit all project styles

Code Comparison

Fluent UI (React):

import { DefaultButton } from '@fluentui/react';

const MyComponent = () => (
  <DefaultButton text="Click me" onClick={() => console.log('Clicked')} />
);

Magnetic UI:

import { Button } from '@microsoft/magnetic-ui-react';

const MyComponent = () => (
  <Button onClick={() => console.log('Clicked')}>Click me</Button>
);

Note: The code comparison is based on available information, but Magnetic UI's repository doesn't seem to be publicly accessible or may not exist. The comparison assumes a hypothetical implementation similar to other UI libraries.

ant-design logo

ant-design

97,203

An enterprise-class UI design language and React UI library

Pros of Ant Design

  • Extensive component library with a wide range of UI elements
  • Well-established and mature project with a large community
  • Comprehensive documentation and examples

Cons of Ant Design

  • Larger bundle size due to the extensive component set
  • Opinionated design system may require more customization for unique designs

Code Comparison

Ant Design component usage:

import { Button } from 'antd';

const MyComponent = () => (
  <Button type="primary">Click me</Button>
);

Magnetic UI component usage (hypothetical, as the repository doesn't exist):

import { Button } from '@microsoft/magnetic-ui';

const MyComponent = () => (
  <Button variant="primary">Click me</Button>
);

Note: The comparison is limited as the microsoft/magentic-ui repository doesn't exist or is not publicly available. Ant Design is a well-known and widely used UI library for React applications, while there's no information available about Magnetic UI. The code comparison is based on typical React component library usage patterns and may not accurately represent Magnetic UI's actual implementation.

mui logo

material-ui

97,572

Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.

Pros of Material-UI

  • Extensive component library with a wide range of pre-built UI elements
  • Strong community support and regular updates
  • Comprehensive documentation and examples

Cons of Material-UI

  • Larger bundle size due to the extensive component library
  • Steeper learning curve for customization and theming
  • Opinionated design system may not fit all project aesthetics

Code Comparison

Material-UI:

import { Button, TextField } from '@mui/material';

function MyComponent() {
  return (
    <>
      <TextField label="Name" variant="outlined" />
      <Button variant="contained" color="primary">Submit</Button>
    </>
  );
}

Magnetic-UI:

import { Button, TextInput } from '@microsoft/magnetic-ui';

function MyComponent() {
  return (
    <>
      <TextInput label="Name" />
      <Button appearance="primary">Submit</Button>
    </>
  );
}

Summary

Material-UI offers a comprehensive set of components and strong community support, making it suitable for large-scale projects. However, it may have a larger bundle size and a steeper learning curve. Magnetic-UI, being newer and less established, may offer a simpler API and potentially smaller bundle size, but with fewer components and less community support. The choice between the two depends on project requirements, team familiarity, and design preferences.

chakra-ui logo

chakra-ui

40,131

Chakra UI is a component system for building SaaS products with speed ⚡️

Pros of Chakra UI

  • More mature and widely adopted, with a larger community and ecosystem
  • Extensive documentation and examples available
  • Highly customizable with a robust theming system

Cons of Chakra UI

  • Larger bundle size, which may impact initial load times
  • Steeper learning curve due to its extensive feature set
  • Less opinionated, requiring more decisions from developers

Code Comparison

Chakra UI component:

import { Button } from "@chakra-ui/react"

function MyButton() {
  return <Button colorScheme="blue">Click me</Button>
}

Magnetic UI component (hypothetical, as the project is not publicly available):

import { Button } from "@microsoft/magnetic-ui"

function MyButton() {
  return <Button variant="primary">Click me</Button>
}

Note: The code comparison is speculative for Magnetic UI, as it's not publicly accessible. The actual implementation may differ.

It's important to note that Magnetic UI is not publicly available, making a comprehensive comparison challenging. Chakra UI is a well-established, open-source project with a proven track record, while Magnetic UI's features and capabilities are not publicly known. Developers should consider their specific project requirements and the availability of documentation and community support when choosing between these libraries.

tailwindlabs logo

tailwindcss

91,915

A utility-first CSS framework for rapid UI development.

Pros of Tailwind CSS

  • Larger community and ecosystem with extensive documentation
  • More flexible and customizable for various design systems
  • Broader browser and framework compatibility

Cons of Tailwind CSS

  • Steeper learning curve for developers new to utility-first CSS
  • Potentially larger CSS file size if not properly optimized

Code Comparison

Tailwind CSS:

<button class="bg-blue-500 hover:bg-blue-700 text-white font-bold py-2 px-4 rounded">
  Button
</button>

Magnetic UI:

<button class="button primary">
  Button
</button>

Key Differences

  • Tailwind CSS uses utility classes for granular control, while Magnetic UI provides pre-designed components
  • Tailwind CSS requires more class names but offers more flexibility, whereas Magnetic UI has a simpler syntax for common UI elements
  • Tailwind CSS is framework-agnostic, while Magnetic UI is specifically designed for React applications

Use Cases

  • Tailwind CSS: Ideal for projects requiring high customization and design flexibility
  • Magnetic UI: Better suited for rapid prototyping and projects that align with Microsoft's design language

Community and Support

  • Tailwind CSS has a larger community, more third-party resources, and frequent updates
  • Magnetic UI, being newer, has a smaller but growing community backed by Microsoft
storybookjs logo

storybook

88,611

Storybook is the industry standard workshop for building, documenting, and testing UI components in isolation

Pros of Storybook

  • Mature and widely adopted tool with extensive documentation and community support
  • Supports a wide range of frameworks and libraries, including React, Vue, Angular, and more
  • Offers advanced features like addons, testing utilities, and design system integration

Cons of Storybook

  • Can be complex to set up and configure, especially for larger projects
  • May introduce additional build overhead and increase project size
  • Learning curve can be steep for newcomers, particularly when using advanced features

Code Comparison

Storybook component story:

import { Button } from './Button';

export default {
  title: 'Example/Button',
  component: Button,
};

const Template = (args) => <Button {...args} />;

export const Primary = Template.bind({});
Primary.args = {
  primary: true,
  label: 'Button',
};

Magnetic UI component (hypothetical, as the repository doesn't exist):

import { MagneticButton } from '@microsoft/magnetic-ui';

const MyButton = () => (
  <MagneticButton variant="primary">
    Click me
  </MagneticButton>
);

Note: The comparison is limited as the microsoft/magentic-ui repository doesn't exist or is not publicly available. The code example for Magnetic UI is hypothetical and based on common UI library patterns.

Convert Figma logo designs to code with AI

Visual Copilot

Introducing Visual Copilot: A new AI model to turn Figma designs to high quality code using your components.

Try Visual Copilot

README

Magentic-UI Logo

Automate your web tasks while you stay in control

image image Python Versions

Magentic-UI is a research prototype of a human-centered interface powered by a multi-agent system that can browse and perform actions on the web, generate and execute code, and generate and analyze files.

https://github.com/user-attachments/assets/7975fc26-1a18-4acb-8bf9-321171eeade7

🚀 Quick Start

Here's how you can get started with Magentic-UI:

# 1. Setup environment
python3 -m venv .venv
source .venv/bin/activate
pip install magentic-ui --upgrade

# 2. Set your API key
export OPENAI_API_KEY="your-api-key-here"

# 3. Launch Magentic-UI
magentic-ui --port 8081

Then open http://localhost:8081 in your browser to interact with Magentic-UI!

Prerequisites: Requires Docker and Python 3.10+. Windows users should use WSL2. See detailed installation for more info.

✨ What's New

  • File Upload Support: Upload any file through the UI for analysis or modification
  • MCP Agents: Extend capabilities with your favorite MCP servers
  • Easier Installation: We have uploaded our docker containers to GHCR so you no longer need to build any containers! Installation time now is much quicker.

Alternative Usage Options

Without Docker (limited functionality: no code execution):

magentic-ui --run-without-docker --port 8081

Command Line Interface:

magentic-cli --work-dir PATH/TO/STORE/DATA

Custom LLM Clients:

# Azure
pip install magentic-ui[azure]

# Ollama (local models)
pip install magentic-ui[ollama]

You can then pass a config file to the magentic-ui command ( client config) or change the model client inside the UI settings.

For further details on installation please read the 🛠️ Installation section. For common installation issues and their solutions, please refer to the troubleshooting document. See advanced usage instructions with the command magentic-ui --help.

Quick Navigation:

🟪 How it Works  |  🛠️ Installation  |  ⚠️ Troubleshooting  |  🤝 Contributing  |  📄 License

🟪 How it Works

Magentic-UI

Magentic-UI is especially useful for web tasks that require actions on the web (e.g., filling a form, customizing a food order), deep navigation through websites not indexed by search engines (e.g., filtering flights, finding a link from a personal site) or tasks that need web navigation and code execution (e.g., generate a chart from online data).

The interface of Magentic-UI is displayed in the screenshot above and consists of two panels. The left side panel is the sessions navigator where users can create new sessions to solve new tasks, switch between sessions and check on session progress with the session status indicators (🔴 needs input, ✅ task done, ↺ task in progress).

The right-side panel displays the session selected. This is where you can type your query to Magentic-UI alongside any file attachments and observe detailed task progress as well as interact with the agents. The session display itself is split in two panels: the left side is where Magentic-UI presents the plan, task progress and asks for action approvals, the right side is a browser view where you can see web agent actions in real time and interact with the browser. Finally, at the top of the session display is a progress bar that updates as Magentic-UI makes progress.

The example below shows a step by step user interaction with Magentic-UI:

Magentic-UI Landing Co-Planning UI Co-Tasking UI Action Guard UI

What differentiates Magentic-UI from other browser use offerings is its transparent and controllable interface that allows for efficient human-in-the-loop involvement. Magentic-UI is built using AutoGen and provides a platform to study human-agent interaction and experiment with web agents. Key features include:

  • 🧑‍🤝‍🧑 Co-Planning: Collaboratively create and approve step-by-step plans using chat and the plan editor.
  • 🤝 Co-Tasking: Interrupt and guide the task execution using the web browser directly or through chat. Magentic-UI can also ask for clarifications and help when needed.
  • 🛡️ Action Guards: Sensitive actions are only executed with explicit user approvals.
  • 🧠 Plan Learning and Retrieval: Learn from previous runs to improve future task automation and save them in a plan gallery. Automatically or manually retrieve saved plans in future tasks.
  • 🔀 Parallel Task Execution: You can run multiple tasks in parallel and session status indicators will let you know when Magentic-UI needs your input or has completed the task.
Watch the demo video
▶️ Click to watch a video and learn more about Magentic-UI

Autonomous Evaluation

To evaluate its autonomous capabilities, Magentic-UI has been tested against several benchmarks when running with o4-mini: GAIA test set (42.52%), which assesses general AI assistants across reasoning, tool use, and web interaction tasks ; AssistantBench test set (27.60%), focusing on realistic, time-consuming web tasks; WebVoyager (82.2%), measuring end-to-end web navigation in real-world scenarios; and WebGames (45.5%), evaluating general-purpose web-browsing agents through interactive challenges. To reproduce these experimental results, please see the following instructions.

If you're interested in reading more checkout our technical report and blog post.

🛠️ Installation

Pre-Requisites

Note: If you're using Windows, we highly recommend using WSL2 (Windows Subsystem for Linux).

  1. If running on Windows or Mac you should use Docker Desktop or if inside WSL2 you can install Docker directly inside WSL docker in WSL2 guide. If running on Linux, you should use Docker Engine.

If using Docker Desktop, make sure it is set up to use WSL2: - Go to Settings > Resources > WSL Integration - Enable integration with your development distro You can find more detailed instructions about this step here.

  1. During the Installation step, you will need to set up your OPENAI_API_KEY. To use other models, review the Model Client Configuration section below.

  2. You need at least Python 3.10 installed.

If you are on Windows, we recommend to run Magentic-UI inside WSL2 (Windows Subsystem for Linux) for correct Docker and file path compatibility.

PyPI Installation

Magentic-UI is available on PyPI. We recommend using a virtual environment to avoid conflicts with other packages.

python3 -m venv .venv
source .venv/bin/activate
pip install magentic-ui

Alternatively, if you use uv for dependency management, you can install Magentic-UI with:

uv venv --python=3.12 .venv
. .venv/bin/activate
uv pip install magentic-ui

Running Magentic-UI

To run Magentic-UI, make sure that Docker is running, then run the following command:

magentic-ui --port 8081

Note: Running this command for the first time will pull two docker images required for the Magentic-UI agents. If you encounter problems, you can build them directly with the following command:

cd docker
sh build-all.sh

If you face issues with Docker, please refer to the TROUBLESHOOTING.md document.

Once the server is running, you can access the UI at http://localhost:8081.

Configuration

Model Client Configuration

If you want to use a different OpenAI key, or if you want to configure use with Azure OpenAI or Ollama, you can do so inside the UI by navigating to settings (top right icon) and changing model configuration. Another option is to pass a yaml config file when you start Magentic-UI which will override any settings in the UI:

magentic-ui --port 8081 --config config.yaml

Where the config.yaml should look as follows with an AutoGen model client configuration:

gpt4o_client: &gpt4o_client
    provider: OpenAIChatCompletionClient
    config:
      model: gpt-4o-2024-08-06
      api_key: null
      base_url: null
      max_retries: 5

orchestrator_client: *gpt4o_client
coder_client: *gpt4o_client
web_surfer_client: *gpt4o_client
file_surfer_client: *gpt4o_client
action_guard_client: *gpt4o_client
plan_learning_client: *gpt4o_client

You can change the client for each of the agents using the config file and use AzureOpenAI (AzureOpenAIChatCompletionClient), Ollama and other clients.

MCP Server Configuration

You can also extend Magentic-UI's capabilities by adding custom "McpAgents" to the multi-agent team. Each McpAgent can have access to one or more MCP Servers. You can specify these agents via the mcp_agent_configs parameter in your config.yaml.

For example, here's an agent called "airbnb_surfer" that has access to the OpenBnb MCP Server running locally via Stdio.

mcp_agent_configs:
  - name: airbnb_surfer
    description: "The airbnb_surfer has direct access to AirBnB."
    model_client: 
      provider: OpenAIChatCompletionClient
      config:
        model: gpt-4.1-2025-04-14
      max_retries: 10
    system_message: |-
      You are AirBnb Surfer, a helpful digital assistant that can help users acces AirBnB.

      You have access to a suite of tools provided by the AirBnB API. Use those tools to satisfy the users requests.
    reflect_on_tool_use: false
    mcp_servers:
      - server_name: AirBnB
        server_params:
          type: StdioServerParams
          command: npx
          args:
            - -y
            - "@openbnb/mcp-server-airbnb"
            - --ignore-robots-txt

Under the hood, each McpAgent is just a autogen_agentchat.agents.AssistantAgent with the set of MCP Servers exposed as an AggregateMcpWorkbench which is simply a named collection of autogen_ext.tools.mcp.McpWorkbench objects (one per MCP Server).

Currently the supported MCP Server types are autogen_ext.tools.mcp.StdioServerParams and autogen_ext.tools.mcp.SseServerParams.

Building Magentic-UI from source

This step is primarily for users seeking to make modifications to the code, are having trouble with the pypi installation or want the latest code before a pypi version release.

1. Make sure the above prerequisites are installed, and that Docker is running.

2. Clone the repository to your local machine:

git clone https://github.com/microsoft/magentic-ui.git
cd magentic-ui

3. Install Magentic-UI's dependencies with uv or your favorite package manager:

# install uv through https://docs.astral.sh/uv/getting-started/installation/
uv venv --python=3.12 .venv
uv sync --all-extras
source .venv/bin/activate

4. Build the frontend:

First make sure to install node:

# install nvm to install node
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash
nvm install node

Then install the frontend:

cd frontend
npm install -g gatsby-cli
npm install --global yarn
yarn install
yarn build

5. Run Magentic-UI, as usual.

magentic-ui --port 8081

Running the UI from source

If you are making changes to the source code of the UI, you can run the frontend in development mode so that it will automatically update when you make changes for faster development.

  1. Open a separate terminal and change directory to the frontend
cd frontend
  1. Create a .env.development file.
cp .env.default .env.development
  1. Launch frontend server
npm run start
  1. Then run the UI:
magentic-ui --port 8081

The frontend from source will be available at http://localhost:8000, and the compiled frontend will be available at http://localhost:8081.

Troubleshooting

If you were unable to get Magentic-UI running, do not worry! The first step is to make sure you have followed the steps outlined above, particularly with the pre-requisites.

For common issues and their solutions, please refer to the TROUBLESHOOTING.md file in this repository. If you do not see your problem there, please open a GitHub Issue.

Contributing

This project welcomes contributions and suggestions. For information about contributing to Magentic-UI, please see our CONTRIBUTING.md guide, which includes current issues to be resolved and other forms of contributing.

This project has adopted the Microsoft Open Source Code of Conduct. For more information, see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Citation

Please cite our paper if you use our work in your research:

@article{mozannar2025magentic,
  title={Magentic-UI: Towards Human-in-the-loop Agentic Systems},
  author={Mozannar, Hussein and Bansal, Gagan and Tan, Cheng and Fourney, Adam and Dibia, Victor and Chen, Jingya and Gerrits, Jack and Payne, Tyler and Maldaner, Matheus Kunzler and Grunde-McLaughlin, Madeleine and others},
  journal={arXiv preprint arXiv:2507.22358},
  year={2025}
}

License

Microsoft, and any contributors, grant you a license to any code in the repository under the MIT License. See the LICENSE file.

Microsoft, Windows, Microsoft Azure, and/or other Microsoft products and services referenced in the documentation may be either trademarks or registered trademarks of Microsoft in the United States and/or other countries. The licenses for this project do not grant you rights to use any Microsoft names, logos, or trademarks. Microsoft's general trademark guidelines can be found at http://go.microsoft.com/fwlink/?LinkID=254653.

Any use of third-party trademarks or logos are subject to those third-party's policies.

Privacy information can be found at https://go.microsoft.com/fwlink/?LinkId=521839

Microsoft and any contributors reserve all other rights, whether under their respective copyrights, patents, or trademarks, whether by implication, estoppel, or otherwise.