NeoSignal
← Back to agents
B

Browser Use

Agents
80

AI agent for browser automation using vision models and Playwright

Growing browser automation agent with Playwright integration

Metrics

licenseMIT
providerOpen Source
agent typebrowser
github stars8,500
base model requirementsgpt-4-vision, claude-3-sonnet
tool integrations count8

Score Breakdown

adoption82
tool use88
memory context75
self reflection76
planning reasoning78

Compatibility

111111118811111111851111111180

Scoring Methodology

planning_reasoning25% weight

Task decomposition and strategic execution capabilities

Source: AgentBench, WebArena, SWE-bench Verified

tool_use25% weight

Intent recognition, function selection, and execution accuracy

Source: ToolBench, API-Bank, Berkeley Function Calling Leaderboard

memory_context20% weight

Long-context handling and information retention

Source: LongBench, RULER, InfiniteBench

self_reflection15% weight

Error recognition and behavior adjustment

Source: ReAct benchmark, Reflexion evaluation

adoption15% weight

GitHub stars, community usage, ecosystem maturity

Source: GitHub API, PyPI downloads, Stack Overflow activity

Data Sources

github.combrowser-use.com
Last updated: December 24, 2025