Give your agent a browser.
Six tools let any AI agent open a real browser, read the page, and act with Playwright.
// Supports Kernel, Browserbase, and more
const provider = new LocalBrowserProvider();
// Adapters for AI SDK, Pi, and MCP
const { tools } = createAiSdkBrowserTools(provider);
const result = await generateText({
model,
tools,
prompt: "Find the top story on Hacker News",
});55% lower cost than alternatives
Lets your agent work through complex pages with less overhead — and a lot less cost.
Two tools do most of the work.
The agent reads a short page snapshot, then runs the Playwright code it needs.
browser_snapshot
Returns a compact accessibility tree with stable refs. The agent can read the page structure without raw HTML.
browser_exec
Runs Playwright code on the live page. Pass diffSnapshot to get a compact snapshot diff of what changed.
Build and repair browser workflows.
Common questions
Which integrations work today?+
The package includes adapters for AI SDK, Pi, and MCP. The base tools are framework-neutral, so you can also wire them into your own agent loop.
Which browser providers can I use?+
Run Chromium on your machine with LocalBrowserProvider, or use the built-in providers for Libretto Cloud, Browserbase, Kernel, and Steel.
Why does the SDK expose only six tools?+
Most browser work needs two tools: browser_snapshot to read the page and browser_exec to run Playwright. The other four tools open, connect, inspect, and close browser sessions.
Does Browser Tools SDK replace Playwright?+
No. It gives an agent a small tool set and runs its browser_exec code through Playwright. You still have the Playwright API.
Is Browser Tools SDK open source?+
Yes. The package is available under the MIT license in the Libretto repository.
Add browser tools to your agent.
Install the package. Keep your current model and agent framework.