pinchtab
A small standalone server that gives AI agents control of Chrome through an HTTP API. It can manage multiple browser instances for automation and scraping.
Share on XLicense: MIT
Overview
PinchTab is a small standalone server written in Go that lets AI agents control Chrome through an HTTP API. It can be installed as a background daemon so several agent tools share the same browser control layer, and it starts a default headless Chrome instance. It is meant mainly for local, single-user use, and it can also manage multiple browser instances for automation and scraping.
Key features
- HTTP API for controlling Chrome from AI agents
- Installs as a user-level background daemon
- Starts a default headless Chrome instance
- Manages multiple browser instances
- Includes stealth injection and a real-time dashboard
Best for
Developers who want agents to drive a browser on their own machine. Remote setups are possible but advanced, and you must handle tokens and network security yourself.
- Upstream
- pinchtab/pinchtab
- Fork on GitHub
- Guo-astro/pinchtab
- Upstream stars
- 10k
- Category
- AI agents and LLM tools
- Language
- Go
- License
- MIT
- Forked
- 2026-03-01
- Sync status
- In syncLast synced 2026-09-29
More in AI agents and LLM tools
A free desktop app where children in non-English-speaking countries practice English speaking and listening by talking with an AI companion. It can run locally and offline.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
An agent skill for Chinese patents. It helps find patentable points, write disclosure documents, explain patents in plain language, follow policy changes and assist with examination replies.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
A minimal Python library from Hugging Face for building AI agents that write and run code to solve tasks. It lets you set up capable agents in a few lines.
Forked 2026-09-28Last synced 2026-09-29License: Apache-2.0AI agents and LLM toolsGitHub
An open-source benchmark that measures how well AI agents handle realistic legal work. It provides tasks and evaluation for improving legal agents.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub