Web Search
Find relevant pages from a query.
Query → Ranked linksTry Web SearchProduct detailsLexmount platform · Web access and browser automation for AI agents
Moli-Powered Cloud Browsers for AI Agents and Harnesses
Built from scratch for AI agents, Moli starts faster and uses less memory than Chrome. Run isolated browser sessions with proxy support on Lexmount while we handle the infrastructure. Try it in our Playground or connect through our SDK.
Explore Playground to choose a product. Create an account to start building.
Find sourcesExtract contentControl browsersDelegate tasks
What do you want to build?
Choose a product by the job you need to do.
Web Fetch
Turn a URL into readable page content.
URL → Structured contentTry Web FetchProduct detailsCloud Browser
Control browser sessions from your code.
Your code → Browser actionsTry Cloud BrowserProduct detailsAgent
Delegate browser tasks to an agent.
Task → Execution → ResultTry AgentProduct detailsSee a web workflow in action.
Find documentation, read the details, then interact with the page.
Find
Web SearchSearch for relevant documentation from a query.
Read
Web FetchTurn a URL into structured content.
Interact
Cloud BrowserControl the browser to take action.
Extract page content
Turn your chosen URL into content for your application.
View runnable exampleRead links from a page
Use the Moli example to extract links from a page.
View runnable exampleReuse a browser context
Use persistent-context examples to retain browser state.
View runnable exampleIllustrative workflow. Use each API independently, or combine them in your application.
Explore examplesChoose the engine that fits your task.
Moli is the engine; Cloud Browser is the managed service. Playground starts with Moli. Choose Chromium for broader compatibility or specific session features.
Chromium
Choose it for persistent contexts, extensions or compatibility-sensitive visual tasks.
- Persistent contexts
- Extensions and file workflows
- Visual fidelity and available replay
Moli
Start with the Playground default and validate structure and interaction tasks on your own pages.
- DOM, text, and links
- Forms and network responses
- Layout and screenshots on demand
Capabilities vary by engine. Check support before choosing.
Keep your browser runs visible.
Inspect live sessions and review available execution evidence when you need to diagnose a task.
Explore observabilityAvailability depends on engine and session settings.Choose a network route for your browser
Configure an official or custom proxy for the task. For sites reachable from your own machine, see the SDK local proxy guide.
Live viewConsoleNetworkSnapshotsLogs
Start the way you work.
Costs and common questions
Validate a representative task, then choose a plan for your usage.
How do I estimate task costs and choose a plan?
Run a small, representative batch of real tasks and check actual browser usage. Choose a plan based on your expected task volume and the concurrency you need.
Read the full answerCan I try my own task before choosing a plan?
Yes. Use your project’s free allowance to run a real task and check whether it can be completed before deciding how much time, concurrency, and functionality you need.
Read the full answerHow much of my Playwright script needs to change?
Start with browser creation, connection, and cleanup, then validate your existing page interactions. For Chromium, you can connect to Lexmount using Playwright’s CDP connection.
Read the full answer