Browser control for AI agents. Small Go binary. HTTP API. Accessibility-first. 🦀
Pinchtab is a browser control project for AI agents, built as a small Go binary with an HTTP API and an accessibility-first design. Its skills let an agent open sites, inspect and click through interactive flows, fill forms, scrape page text, export screenshots or PDFs, and manage multiple browser instances, through either direct API calls or an MCP server. Notable here are a stealth-score sweep against fingerprinting and bot-detection sites and an optimization loop that benchmarks several browser providers, alongside the core automation skills.
Pinchtab
5 skills · 10,560 stars · MIT
Pinchtab Use this skill when a task needs browser automation through PinchTab: open a website, inspect int…
Pinchtab Dev Develop and contribute to the PinchTab project.
Pinchtab Mcp Use this skill when a task requires browser automation through PinchTab's MCP server connected to…
Pinchtab Opt Run the PinchTab optimization loop (Docker, 3 blind subagents on the runner's HIGH model, 108 ste…
Pinchtab Stealth Score Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, reb…