LLM Hub — Computer-Use & Browser Agents

Computer-Use & Browser Agents

Anthropic Computer Use, OpenAI Operator, Gemini Mariner, plus browser-only agents (Browser-Use, Playwright). Action schemas, screen vs DOM grounding, sandboxing, evals.

Computer UseOperatorMarinerBrowser-UseWebArena

Presentations in This Series

  1. Computer-Use Architectures →
    Anthropic Computer Use, OpenAI Operator, Gemini Mariner; action schemas (click x,y vs accessibility-tree vs CSS selectors); screenshots vs DOM vs accessibility tree; containers and VMs; OSWorld, WebVoyager, AgentBench.
    live
  2. Browser Agent Patterns →
    Browser-Use, Playwright agents, Steel; DOM extraction strategies; screen vs DOM trade-offs; WebArena and Mind2Web evals; captcha & anti-bot; stateful sessions; pricing; failure recovery.
    live