BrowserAct Skills is a Python-based CLI for browser automation tailored for AI agents, enabling multi-session, multi-account, and cross-platform handoffs with anti-bot capabilities. It emphasizes agent-oriented interactions and concurrency, with activity documented in the README and repository metadata.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
BrowserAct Skills provides a browser automation CLI designed for AI agents. It supports breaking through anti-bot blocks, handoffs to humans across platforms, parallel multi-task execution, independent multi-session operation, and isolated multi-account browsing.
How it works
The project describes multiple browser modes (chrome, stealth privacy mode, stealth fixed identity) and concurrency approaches (cross-browser parallel, same-browser multi-session, privacy mode). It includes command patterns for extracting content and controlling sessions, and notes that sessions have ownership and naming to avoid conflicts. It also mentions layers for environment, execution, and human handoff as part of its design.
Getting started
Install browser-act. Skill source: https://github.com/browser-act/skills/tree/main/browser-act . Verify it works after installation.
Quick Start examples from README
# Extract protected page content (zero config)
browser-act stealth-extract https://example.com
# Full browser automation
browser-act --session my-task browser open <id> https://example.com
browser-act --session my-task state # See clickable elements
browser-act --session my-task click 3 # Click by index
browser-act --session my-task input 2 "hi" # Type into a field
The agent runs get-skills at the start of each session — gets environment state, browser list, and commands in one call:
browser-act get-skills core --skill-version 2.0.2
Recent releases
RELEASES (latest 0): - none
Traction
Stars: 5160 (no d/l data for recent changes provided in FACTS). Open issues: 8. Languages: Python. License: MIT.
Behind the repo
Not applicable here as no linked startup/company information is provided in the FACTS.
Caveats
License: MIT. Created: 2026-02-06. Last push: 2026-07-21. Open issues: 8. No release entries listed in RELEASES (latest 0).