Agent Browser
High-performance Rust headless browser automation CLI with Node.js fallback for AI agents
by
Seth Rose
Agent Browser Overview
Agent Browser is a headless browser automation tool built for AI agents. It exposes a composable CLI to navigate pages, interact with elements, extract structured data, and run JavaScript.
Its core is implemented in Rust for speed, with a Node.js fallback layer for broad compatibility.
Workflow
Use `agent-browser navigate <url>` to point the browser to any URL.
Use `agent-browser snapshot` to capture the page structure and available elements.
Use snapshot refs to click, type, scroll, and select elements.
Take another snapshot or screenshot to confirm results before continuing.
Core Features
Navigation & Snapshots
Open pages and get structured element refs for reliable interaction.
Click, Type & Scroll
Interact with any element through structured commands.
JavaScript Execution
Run arbitrary JS in page context via `evaluate`.
Tab Management
List, open, switch, and close tabs programmatically.
Screenshots
Capture screenshots at any step in your automation flow.
Waits & Conditions
Pause for time or wait for specific conditions.
Rust Core + Node.js Fallback
High performance with broad compatibility.
System Requirements
- Node.js (required for Node.js fallback)
- npm (install via `npm install -g agent-browser`)
- No API key required (runs locally)
Use Cases
Web Automation
Automate repetitive tasks like form submissions and multi-step workflows.
Data Extraction
Extract structured data from dynamically rendered pages.
Form Filling
Programmatically fill and submit forms with inputs.
UI Testing
Simulate user interactions via CLI for UI testing.
Installation
npx clawhub@latest install agent-browserRun in your terminal, or click the Install button at the top of this page for one-click setup.
FAQ
Do I need an API key?
No. Agent Browser runs locally and does not require any API key or external service credentials.
What runtime environments are required?
Node.js and npm are required. The CLI installs globally via npm and uses a Node.js fallback layer.
Can it handle JavaScript-rendered pages?
Yes. It operates a real browser and can interact with JavaScript-rendered pages via snapshots and refs.
How do I interact with page elements?
Take a snapshot, then use the provided element refs with commands like click, fill, type, scroll, and select.
What is agent browser (agent-browser) for OpenClaw skills?
agent-browser is a browser automation CLI for AI agents. It uses a fast Rust CLI with a Node.js fallback. Install with `npm install -g agent-browser` and run `agent-browser install` to download Chromium.
What is the core workflow for agent browser / agent-browser?
Use `agent-browser open <url>`, take a snapshot with `agent-browser snapshot -i` to get refs, then click/fill with refs (e.g. `click @e1`, `fill @e2 "text"`) and re-snapshot after changes.
Does agent browser openclaw require Node.js?
Yes. agent-browser uses a fast Rust CLI with a Node.js fallback, and npm-based installation requires Node.js.
Is openclaw agent browser cross-platform?
agent-browser provides native Rust binaries for macOS, Linux, and Windows, with Node.js fallback support across platforms.