End-to-end testing framework powered by visual AI agents that see your interface and adapt to any changes in it.
- ✍️ Build test cases easily with natural language
- 🧠 Strong reasoning agent to plan and adjust tests
- 👁️ Fast visual agent to reliably execute runs
- 📄 Plan is saved to execute runs the same way
- 🛠 Reasoning agent steps in if there is a problem
- 🏃♂️ Run tests locally or in CI/CD pipelines
test('can add and complete todos', { url: 'https://magnitodo.com' })
.step('create 3 todos')
.data('Take out the trash, Buy groceries, Build more test cases with Magnitude')
.check('should see all 3 todos')
.step('mark each todo complete')
.check('says 0 items left')1. Install our test runner in the node project you want to test (or see our demo repo if you don't have a project to try it on)
npm install --save-dev magnitude-test2. Setup Magnitude in your project by running:
This will create a basic tests directory tests/magnitude with:
magnitude.config.ts: Magnitude test configuration fileexample.mag.ts: An example test file
Magnitude requires setting up two LLM clients:
- A strong general multi-modal LLM (the "planner")
- A fast vision LLM with pixel-precision (the "executor")
For the planner, you can use any multi-modal LLM, but we recommend Gemini 2.5 pro. You can use Gemini via Google AI Studio or Vertex AI. If you don't have either set up, you can create an API key in Google AI Studio (requires billing) and export to GOOGLE_API_KEY.
If no GOOGLE_API_KEY is found, Magnitude will fallback to other common providers (ANTHROPIC_API_KEY / OPENAI_API_KEY).
To explicitly select a specific provider and model, see configuration docs. Currently we support Google AI Studio, Google Vertex AI, Anthropic, AWS Bedrock, OpenAI, and OpenAI-compatible providers.
Currently for the executor model, we only support Moondream, which is a fast vision model that Magnitude uses for precise UI interactions.
To configure Moondream, sign up and create an API with Moondream here, then add to your environment as MOONDREAM_API_KEY. This will use the cloud version, which includes 5,000 free requests per day (roughly a few hundred test cases in Magnitude). Moondream is fully open source and self-hostable as well.
🚀 Once you've got your LLMs set up, you're ready to run tests!
Run your Magnitude tests with:
This will run all Magnitude test files discovered with the *.mag.ts pattern. If the agent finds a problem with your app, it will tell you what happened and describe the bug!
To run many tests in parallel, add
-w <workers>
Now that you've got Magnitude set up, you can create real test cases for your app. Here's an example for a general idea:
import { test } from 'magnitude-test';
test('can log in and create company')
.step('Log in to the app')
.data({ username: '[email protected]', password: 'test' }) // any key/values
.check('Can see dashboard') // natural language assertion
.step('Create a new company')
.data('Make up the first 2 values and use defaults for the rest')
.check('Company added successfully');Steps, checks, and data are all natural language. Think of it like you're describing how to test a particular flow to a co-worker - what steps they need to take, what they should check for, and what test data to use.
For more information on how to build test cases see our docs.
You can run Magnitude tests in CI anywhere that you could run Playwright tests, just include LLM client credentials. For instructions on running tests cases on GitHub actions, see here.
We use separate planning / execution models in order to plan effective tests while executing them quickly and reliably. OpenAI or Anthropic's Computer Use APIs are better suited to general purpose desktop/web tasks but lack the speed, reliability, and cost-effectiveness for running test cases. Magnitude's agent is designed from the ground up to plan and execute test cases, and provides a native test runner purpose-built for designing and running these tests.
To get a personalized demo or see how Magnitude can help your company, feel free to reach out to us at [email protected]
You can also join our Discord community for help or any suggestions!