BrowserAct has open-sourced two AI-agent Skills on GitHub that enable agents to interact with the live web, bypass common automation barriers, and generate reusable web automation tools without rewriting code for every site.
BrowserAct, developed by ECOCREATE TECHNOLOGY PTE. LTD., has open-sourced two AI-agent web automation Skills — browser-act and browser-act-skill-forge — aimed at giving AI agents reliable access to the live web and the ability to create reusable automation tools independently.
Available free on GitHub, the release positions BrowserAct as an open execution and tool-creation layer for AI agents. The company says existing AI agents “can think, but they can’t really act on the live web,” citing website bot detection, excessive webpage token complexity, and brittle site-specific automation code as major barriers.
browser-act, described as “A Browser Built for AI, Not Adapted For It,” includes stealth browsing, fingerprint isolation, CAPTCHA solving, session isolation, Chrome Takeover, and human-in-the-loop remote-assist capabilities. BrowserAct says the open-source runtime is designed to bypass anti-bot systems from companies including Cloudflare and DataDome.
The second release, browser-act-skill-forge, is positioned as “An AI That Builds Tools for Itself.” The tool enables agents to explore websites, discover APIs or DOM patterns, package reusable Skills, and reuse them indefinitely without rewriting automation logic.
BrowserAct claims the tools can reduce error-and-retry loops by up to 90% and cut token consumption by 93% compared with raw HTML workflows. Integrations are available for Claude Code, Cursor, and Codex.
