Computer-use & desktop agents
13 systems in the computer-use & desktop agents category of the AI Agent Infrastructure Landscape, grouped by maturity tier.
Tier 1 — battle-tested (5)
- Browser Use OSS browser-agent library + Cloud (browser-use)
Python library that turns any LLM into a browser agent — extracts DOM into a structured representation the LLM can act on (rather than pure screenshot). Browser Use Inc. raised $17M seed Q1 2025 (Felicis); cloud product at cloud.browser-…
- Claude for Chrome Consumer browser-agent extension (Chrome) — Anthropic
Anthropic's Chrome extension that lets Claude act inside the user's existing browser (rather than a sandboxed one). Research preview launched August 2025 — limited to Claude Max tier. Distinct from Anthropic Computer Use (which is the AP…
- OpenAI Operator Consumer computer-use agent (browser-only)
OpenAI's general-purpose browser agent — research preview launched January 2025 (US Pro tier). Built on the Computer-Using Agent (CUA) model that processes screenshots and emits mouse / keyboard actions; runs inside an OpenAI-hosted brow…
- Project Mariner Google DeepMind browser-agent (research preview)
Google DeepMind's experimental browser agent built on Gemini 2.0 — Chrome extension that takes actions on the user's behalf. Research-preview launched Dec 2024. The Google answer to OpenAI Operator / Anthropic Computer Use; integrated in…
- Stagehand OSS browser-automation framework (Browserbase OSS)
Open-source TypeScript framework for browser automation, maintained by Browserbase. Hybrid of Playwright-style imperative APIs and AI-driven natural-language actions (e.g. page.act('click the sign-up button')). Used as the OSS substrate …
Tier 2 — production-ready (6)
- Highlight AI Desktop AI co-pilot (always-on context capture across apps)
Always-on desktop AI assistant that watches the user's screen (across all apps) and answers questions / takes actions based on what's currently visible. Mac + Windows. Founded by Mac Bishop (ex-Mixpanel); raised $13M Series A from Aspect…
- Hyperbrowser Cloud browser-infrastructure for AI agents (Browserbase competitor)
Cloud-hosted headless browser API tuned for AI agents — captcha solving, stealth mode, session recordings. Y Combinator S24; pitched as a faster / cheaper Browserbase alternative. Used as substrate by agents that need browser execution b…
- Lutra AI AI agent platform for SaaS automations (Gmail/Slack/Sheets)
AI agent platform that automates SaaS workflows across Gmail, Slack, Sheets, etc. — uses natural-language instructions that compile to durable 'playbooks.' Founded by ex-Google/Facebook engineers; raised seed funding 2024. Positions itse…
- Skyvern OSS browser-automation agent (Python; LLM-driven)
Open-source autonomous browser agent that uses computer vision + LLMs to navigate websites. Workflow-based: agents follow recorded plans that adapt to layout changes. Skyvern Inc. raised $4.5M seed (Sep-2024, Felicis lead). Self-hostable…
- Steel.dev OSS + cloud browser-infrastructure for AI agents
Open-source browser API ('the browser for agents') — Chromium fleet with stealth mode, session recordings, CDP. OSS repo + managed cloud. Compatible with Playwright / Puppeteer. Distinguishes itself as the 'OSS Browserbase'.
- UI-TARS OSS GUI-agent foundation model + desktop app (ByteDance)
ByteDance Seed's open-source GUI-agent foundation model — released Jan 2025; trained end-to-end on screenshot → action pairs. Comes with UI-TARS-Desktop (Electron app) that runs the model against the user's screen. SOTA on OSWorld at rel…
Tier 3 — emerging (2)
- Bytebot OSS desktop-control agent runtime (containerised Linux desktop)
Open-source desktop-agent runtime that runs an LLM-controlled Linux desktop inside Docker — uses xdotool / X11 capture for control. Pitched as the 'self-hosted Operator' alternative; agent sees a real desktop screen, not just a browser.
- Magnitude OSS browser-agent framework for web tests (YC)
Open-source browser-agent framework focused on AI-driven end-to-end testing — natural-language test cases that translate to Playwright actions. Y Combinator 2025; positions itself as 'Playwright + Claude for QA' rather than general auton…