AI Potluck
Product / UX / Agent tools & protocols

Browser Use

Browser Use

Open-source agent framework that makes websites accessible to AI agents, enabling autonomous web browsing, form filling, data extraction, and multi-step online task completion. Built on Playwright, it provides a structured way for LLMs to observe page state, plan actions, and execute browser interactions. 95K GitHub stars with 315 contributors, one of the fastest-growing projects in the agent space, filling the crucial gap of web-native agent capabilities.

Browser Use, verified live June 2026 (GitHub + PyPI). OSS Python library making websites accessible to AI agents (navigate/click/fill/extract). MIT license. Recategorized into agent_tools_protocols (browser/scrape sub-segment) per assignment. Managed Browser Use Cloud tier also exists.

Openness

4 high confidence
4.0
license
MIT(OSI, library core fully open)
source
public
managed-tier
Browser-Use-Cloud(proxies/stealth/captcha/hosted browsers, proprietary)
core-gated
gated

Core library is fully MIT/OSI open (no feature-gated core); a separate proprietary Browser Use Cloud adds managed infra. Scored open_core at 4 because the OSS core is complete and the cloud is optional hosting, not a gated core.

Adoption

4 high confidence
4.0

~27M PyPI downloads in the last month (browser-use), strong real install/usage volume, not stars. 97.2k GitHub stars corroborate but are not the basis. Solidly in the 1-10M+ monthly-download band; one of the most-used agent browser-automation libraries.

Capability

4 medium confidence
4.0

Leading OSS browser-automation-for-agents library with broad action coverage and a production cloud tier; widely adopted as the default agent browsing layer. Rated 4 on feature_matrix (multi-step web tasks, structured extraction, anti-block infra); no standard benchmark applies to a browser-control library.

Unchanged since 2026-07-30 (last edited, not re-checked)