Show HN: Magnitude – open-source AI browser automation framework

4 months ago 31

Magnitude uses vision AI to enable you to control your browser with natural language

🧭 Navigate - Sees and understands any interface to plan out actions
🖱️ Interact - Executes precise actions using mouse and keyboard
🔍 Extract - Intelligently extracts useful structured data
✅ Verify - Built-in test runner with powerful visual assertions

You can use it to automate tasks on the web, integrate between apps without APIs, extract data, test your web apps, or as a building block for your own browser agents.

↕️ Magnitude in action! ↕️

// Magnitude can handle high-level tasks await agent.act('Create a task', { // Optionally pass data that the agent will use where appropriate data: { title: 'Use Magnitude', description: 'Run "npx create-magnitude-app" and follow the instructions', }, }); // It can also handle low-level actions await agent.act('Drag "Use Magnitude" to the top of the in progress column'); // Intelligently extract data based on the DOM content matching a provided zod schema const tasks = await agent.extract( 'List in progress tasks', z.array(z.object({ title: z.string(), description: z.string(), // Agent can extract existing data or new insights difficulty: z.number().describe('Rate the difficulty between 1-5') })), );

Running your first browser automation

This will create a new project and walk you through the steps for setting up Magnitude. It will also create an example script that you can run right away!

To install the test runner for use in an existing web app, please run:

npm i --save-dev magnitude-test && npx magnitude init

This will create a basic tests directory tests/magnitude with:

magnitude.config.ts: Magnitude test configuration file
example.mag.ts: An example test file

For information on how to run tests and integrate into CI/CD see here.

Note

Magnitude requires a large visually grounded model. We recommend Claude Sonnet 4 for the best performance, but are also compatible with Qwen-2.5VL 72B. See docs for more information.

❌ Problem #1: Most browser agents draw numbered boxes around page elements - doesn't generalize well due to complex modern sites

✅ Solution: Vision-first architecture

Visually grounded LLM specifies pixel coordinates
True generalization independent of DOM structure
Future-proof architecture for desktop apps, VMs, etc.

❌ Problem #2: Most browser agents follow "high-level prompt + tools = work until done" - works for demos, not production

✅ Solution: Controllable & repeatable automation

Flexible abstraction levels (granular actions vs. flows)
Custom actions + prompts at agent and action level
Deterministic runs via native caching system (in progress)

Please see our docs for more information on how to best build Magnitude automations and test cases.

If you are an enterprise and want more features or support, feel free to reach out to us at [email protected] or schedule a call here to discuss your needs.

You can also join our Discord community for help or any suggestions!

Read Entire Article