Browser Use

https://browser-use.com/

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-use.com. Project is one of the most-starred browser-agent OSS repos.

Active · Verified 2026-10-31 · fresh as of 2026-10-31 · 68 cited facts, 5 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Tier
T1
License
MIT repo fix
Freshness
2026-10-31 fix
Layer
agent-infra repo fix
Licensing
open-core vendor fix
Deployment locus
computer-use vendor fix
Platform vs product
platform vendor fix
Accelerator
yc-w25 third-party fix
SDK languages
python, rest, typescript vendor fix
Protocols
mcp-server vendor fix

When to use

Optimised for: LLM-driven browser automation as a primitive — DOM + screenshot mode

Anti-fit: Not for desktop apps (browser-only); not a SaaS — caller builds product on top

Pros & cons

Pros

Most-starred browser-agent OSS in 2025; permissive MIT license; Felicis-backed; works on top of any major LLM.

Cons

Not a finished app — caller builds product on top; compliance / SOC 2 still maturing on Cloud.

Claims & capabilities

One of the most-starred AI agent repos of 2025; $17M seed Mar-2025 (Felicis lead); WebVoyager SOTA per maintainer claim

Technical surface

API surface
Python SDK + Cloud REST API
Backend storage
Local Playwright state; Cloud uses managed Postgres
Deployment
Both (self-hosted + managed cloud) — OSS Python library + Browser Use Cloud; on-prem via sales
Embedding model
not applicable — not a memory product
Multi-tenancy
Cloud is multi-tenant; OSS is single-tenant per process
MCP
yes — first-party hosted MCP server (api.browser-use.com/v3/mcp) plus local stdio browser-harness-mcp
A2A
searched not found
OpenTelemetry
searched not found

Compare Browser Use with…

Similar systems

Other computer-use & desktop agents in the catalog, ranked by inbound references.

  • Stagehand T1

    Open-source browser-automation framework by Browserbase (TypeScript core plus Python and Go SDKs). Mixes Playwright-style code with natural-language act/extract/observe; pairs with Browserbase Cloud.

  • Hyperbrowser T2

    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 but don't want to run their own Chromium fleet.

  • UI-TARS T2

    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 release; weights on HuggingFace.

  • Anthropic Computer Use T1

    Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.

  • Skyvern T2

    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; cloud version on skyvern.com.

  • Bytebot T3

    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.

Sources (67 cited facts, 5 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-26
    • Latest release “Active weekly releases (PyPI: browser-use)” → “v0.13.11 (2026; release date not confirmed)” source
    • Pricing “OSS free; Cloud tiers (usage-based)” → “OSS library free; Cloud pay-as-you-go: $1 free credit, $5 min top-up, browsers $0.02/hr, agents = model price +20%; on-prem via sales” source
    • Deployment “Pip self-host + Browser Use Cloud” → “Both (self-hosted + managed cloud) — OSS Python library + Browser Use Cloud; on-prem via sales” source
    • MCP support “Browser Use MCP server (community + first-party)” → “yes — first-party hosted MCP server (api.browser-use.com/v3/mcp) plus local stdio browser-harness-mcp” source
    #258

Related systems

References (3)

  • Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: Playwright; Anthropic / OpenAI / Gemini APIs; Browserbase / Hyperbrowser substrates
  • Google Gemini 3 family depends on at runtime — adjacent-infrastructure cell: Playwright; Anthropic / OpenAI / Gemini APIs; Browserbase / Hyperbrowser substrates
  • OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — adjacent-infrastructure cell: Playwright; Anthropic / OpenAI / Gemini APIs; Browserbase / Hyperbrowser substrates

Referenced by (4)

  • Browserbase integrates with — Browserbase docs have a Browser Use integration page. (verified 2026-10-29)
  • Laminar integrates with — Laminar integrations docs have a Browser Use observability page. (verified 2026-10-29)
  • LangChain (framework) integrates with — LangChain docs have a Browser Use integration provider page (Browser agents and cloud browsers for AI applications). (verified 2026-10-29)
  • Pydantic-AI integrates with — Pydantic AI harness docs have a Browser Use integration page. (verified 2026-10-29)