Category
Browser & computer-use agents — let AI drive web and desktop apps
Browser Use, Skyvern, Claude Computer Use, OpenAI Operator, Manus and more—models that click pages, fill forms, and run workflows.
This lane, “**drive the GUI instead of only calling APIs**”, broke out in 2025. Three shapes are common: **in-browser extensions** (Comet, etc.), **hosted virtual desktops** (Operator, Claude Computer Use), and **open-source self-hosted** (Browser Use, Skyvern, Reworkd). Ask three questions up front: does it run in the user’s live environment, how do wrong actions **roll back and audit**, and how are **credentials** (cookies, 2FA, SSO) scoped down?
Editorial / GSC add-ons
Browser agents vs RPA
RPA is scripted against fixed widgets/coords. Browser agents plan with an LLM and adapt better but are less deterministic. Use RPA for 100%-fixed flows and browser agents when pages shift or data is semi-structured.
Can I trust Operator/Claude Computer Use with sensitive accounts?
Use ephemeral credentials, least-privilege sessions, and sandboxed VMs. Read retention and training clauses; gate critical actions behind a human confirm.
Who should self-host (Browser Use, Skyvern)?
Teams that need custom policies, keep credentials on-prem, or run high-volume scraping/ticket work. Stability and anti-bot resilience still take engineering.
Tools in this category
Summaries and official links live on each tool page—browse related picks in-category.
General-purpose autonomous assistant product from Manus AI: delegates multi-step browser and research-style tasks behind a chat interface—check the site for task limits, regions, and data handling.
Open-source browser agent framework that drives web pages through structured DOM actions—a self-hostable alternative to Operator/Computer Use for developers who want control.
Skyvern: popular AI product—see the official site for features, pricing, supported regions, data handling, and latest model lineup.
MultiOn: popular AI product—see the official site for features, pricing, supported regions, data handling, and latest model lineup.
Anthropic’s Claude capability to see the screen and operate a computer via API—best used with sandboxed VMs, scoped credentials, and human confirm on critical actions.
OpenAI’s cloud browser agent (evolving into ChatGPT Agent) that operates websites remotely on your behalf—check current product name, regions, and data rules on the site.
Reworkd: popular AI product—see the official site for features, pricing, supported regions, data handling, and latest model lineup.