CLAUDEZILLA от Boot Industries

Claudezilla brings native Firefox browser automation to AI coding harnesses: Claude Code, Hermes Agent, Pi Agent, omp, and standard mcp clients.

Control Firefox directly from your terminal: navigate pages, click elements, fill forms, capture screenshots, and analyze page content. A Google-free, telemetry-free alternative to Chrome-based browser automation.

FEATURES:
- Multi-harness support: Out-of-the-box integration with Claude Code, Hermes Agent, Pi Agent, and omp
- Eager & lazy tool discovery: Full catalog exposure for single-discovery harnesses (Hermes, Pi, omp) or lazy on-demand loading for token savings
- Page navigation and full DOM interaction (click, type, scroll, press keys)
- Attach to existing user tabs: Drive open browser tabs in place with explicit agent-initiated attach
- Screenshot capture to temporary paths with dynamic readiness detection and image compression
- Annotated screenshots with numbered element badges for precise visual interaction
- Structured page analysis via JSON with configurable limits and explicit truncation metadata (faster and cheaper than screenshots)
- Accessibility tree snapshots for semantic page understanding
- Page state diffing to detect changes between interactions
- Cookie and consent banner auto-dismissal (GDPR overlays, CMP platforms)
- Domain allowlists for agent sandboxing
- Flexible element waiting (CSS selector, text content, or URL pattern)
- Network request and console log monitoring
- Multi-agent and multi-harness safety: Tab ownership tracking, screenshot mutex, and slot reservations
- Session-scoped focus loops for persistent iterative development across sessions
- Orphaned tab cleanup with configurable timeout (CLAUDEZILLA_AGENT_TIMEOUT_MS) for human-in-the-loop workflows
- Per-operation timeouts (5s–300s, default 150s)

REQUIREMENTS:
- Supported AI harness: Claude Code, Hermes Agent, Pi Agent, omp, or standard mcp client
- Native messaging host (one-command installer with --target flag)
- Firefox 140+
- macOS, Linux, or Windows 10/11

PRIVACY & SECURITY:
- All communication is local via Unix socket / Windows pipe (no network exposure)
- Zero telemetry: No data collected or transmitted to external servers
- Page content accessed only on explicit tool invocation
- Console capture and JavaScript evaluation are strictly opt-in (off by default in popup settings)
- Request bodies are never captured
- Per-agent tab ownership prevents cross-session and cross-harness interference
- Community supported
- Open source (MIT license)

Setup & docs: claudezilla.com