agent-browser#
Browser automation CLI designed for AI agents. Compact text output minimizes context usage. 100% native Rust.
npm install -g agent-browser # all platforms brew install agent-browser # macOS agent-browser install # Download Chrome (first time)
or try without installing
npx agent-browser open example.com
Features#
Agent-first: Compact text output uses fewer tokens than JSON, designed for AI context efficiency
Ref-based: Snapshot returns accessibility tree with refs for deterministic element selection
Complete: 50+ commands for navigation, forms, screenshots, network, storage, files, tabs, frames, and debugging
Observable: Video recording, streaming, debugging, profiler, and diffing tools are built in
Modern apps: Network control, React & Web Vitals, init scripts, Next.js + Vercel, and eve Extension workflows have first-class docs
Stateful: Sessions, profiles, auth state, cookies, storage, proxy, and security controls support long-running agents
Cross-platform: macOS, Linux, Windows with native binaries
Works with#
Claude Code, Cursor, GitHub Copilot, OpenAI Codex, Google Gemini, opencode, and any agent that can run shell commands.
Example#
Navigate and get snapshot
agent-browser open example.com agent-browser snapshot -i
Output:
- heading "Example Domain" [ref=e1]
- link "More information..." [ref=e2]
Interact using refs
agent-browser click @e2 agent-browser screenshot page.png agent-browser close
Why refs?#
The snapshot command returns a compact accessibility tree where each element has a unique ref like @e1, @e2. This provides:
Context-efficient: Text output uses ~200-400 tokens vs ~3000-5000 for full DOM
Deterministic: Ref points to exact element from snapshot
Fast: No DOM re-query needed
AI-friendly: LLMs parse text output naturally
Architecture#
Client-daemon architecture for optimal performance:
Rust CLI: Parses commands, communicates with daemon
Native Daemon: Pure Rust daemon using direct CDP, manages Chrome via Chrome DevTools Protocol
The daemon starts automatically and persists between commands. By default, it saves configured restore state, closes its headless browser, and exits after one hour without commands or dashboard input. Without --restore or another restore key, shutdown discards transient browser state and open tabs. Headed browsers, Safari and iOS WebDriver sessions, and user-attached browsers are exempt from the default timeout; provider-owned cloud browsers are not. Use --idle-timeout or AGENT_BROWSER_IDLE_TIMEOUT_MS to tune the timeout, and use 0 to disable it.
Platforms#
Native Rust binaries for macOS (ARM64, x64), Linux (ARM64, x64), and Windows (x64).