Chrome DevTools Protocol in your terminal. Opens a persistent connection to Chrome where commands can be executed sequentially via Unix pipes. Designed for AI agents and developers who want direct browser control without framework overhead.

• Raw CDP access - All 644 protocol methods available directly
• Token efficient - No overhead from MCP tool definitions; progressive discovery loads only what's needed
• Self-correcting - Errors clearly exposed with semantic exit codes and suggestions
• Composable - Unix philosophy: pipes, jq, shell scripts work naturally

When to use alternatives:

• Puppeteer/Playwright: Complex multi-step scripts, mature testing ecosystem
• Chrome DevTools MCP: Already invested in MCP infrastructure

Built for agents: Self-discovery (--list, --search), semantic exit codes, structured errors, case-insensitive commands, token-efficient output.

We benchmarked bdg against Chrome DevTools MCP Server on real developer debugging tasks.

Full benchmark analysis →

Key findings: CLI provided 33% better token efficiency through selective queries vs full accessibility tree dumps, plus capabilities MCP doesn't expose (memory profiling, HAR export, batch JS execution).

npm install -g browser-debugger-cli@alpha

Platform Support:

• ✅ macOS and Linux
• ✅ Windows via WSL
• ❌ PowerShell/Git Bash (not yet)

bdg example.com # Start session bdg cdp --search cookie # Discover commands bdg cdp Network.getCookies # Run any CDP method bdg dom query "button" # High-level helpers bdg stop # End session

Raw CDP access is complete. All 644 protocol methods (53 domains) work now. High-level wrappers (bdg dom, bdg network) are being added for common operations. See Commands for full reference.

# Agent explores what's possible (no docs needed) bdg cdp --list # 53 domains bdg cdp Network --list # 39 methods bdg cdp Network.getCookies --describe # Full schema + examples bdg cdp Network.getCookies # Execute # Search across all domains bdg cdp --search screenshot # Find relevant methods bdg cdp --search cookie # 14 results

📖 Wiki - Guides, command reference, recipes

• Getting Started
• Commands
• For AI Agents
• Recipes
• Quick Reference
• Architecture
• Troubleshooting

This tool implements Agent-Friendly Tools:

• Self-documenting - Tools teach themselves via --list, --describe
• Semantic exit codes - Machine-parseable error handling
• Structured output - JSON by default, human-readable optional
• Progressive disclosure - Simple commands, deep capabilities

Issues for bugs, Discussions for ideas. PRs welcome.

See docs/ for architecture and contributor guides.

MIT