Browser Use
Also known as: browser-use, Browser Use Cloud
Open source browser agent library plus a cloud with hosted agents and stealth browsers for AI agents, priced by usage.
Browser Use makes software that lets AI agents operate a real web browser. It began as an open source Python library, in which a developer describes a task in plain language and the agent navigates, clicks, fills forms and extracts data on sites it has not seen before. The library is free, runs on the developer's own machine against a local or remote browser, supports many model providers including local models, and can be extended with custom tools, lifecycle hooks and tracing.
Browser Use Cloud sells two products on top. Browser Use Agents (API V4) takes a task and returns the finished result and files, running the agent and its browser in Browser Use's cloud; runs chain as follow ups in a session, and rerunnable scripts let a first run save tested code that later runs reuse and repair when a site changes. Browser Infrastructure rents managed stealth Chromium browsers, with CAPTCHA handling, residential proxies, saved profiles, live view and recordings, to any agent or to Playwright, Puppeteer, Selenium or CDP code.
The cloud documents a REST API with an OpenAPI file, Python and TypeScript SDKs, a CLI and an MCP server; a choice of models from OpenAI, Anthropic, xAI and MiniMax or the customer's own key; scheduled work and an iMessage channel; human checkpoints through the live view; an optional LLM judge that returns a verdict on each run; and a US or EU (Frankfurt) deployment. Enterprise terms add SOC 2 Type II, HIPAA support, a DPA, zero data retention and custom SLAs. The pages read do not document roles, SSO or a memory layer beyond session history and workspace files.
Vendor details
Canonical URL
https://browser-use.com/
Category
Browser / computer-use agent
Company status
independent
Use cases & customers
Target customers
Deployment options
Integrations
Custom tools in the open source library; connected integrations authorized through the Cloud API; MCP server for Claude Code and other clients; tutorials for n8n, Vercel, Claude Managed Agents, OpenClaw and Hermes Agent; Playwright, Puppeteer, Selenium and CDP on hosted browsers; x402 pay per request.
In practice
Your scraping and automation scripts break every time a target site changes its layout. Browser Use lets your agent reason from the live page instead of hardcoded selectors, so the automation self-heals across redesigns.
You want to automate a site that has no API and sits behind a normal web UI. Browser Use takes a plain-English task and navigates, clicks, fills forms, and extracts data against the real page, model of your choice.
You want Claude Code or Cursor to actually operate websites, not just describe steps. Browser Use ships an MCP server that exposes navigation, form-filling, data extraction, and tab management as native tools to your coding agent.
Sources & related URLs
Research sources
Agentic Index coverage score
11.5 / 14 capabilities · 82%
| Integrations & Tool Calling | Full |
|---|---|
|
The open source library documents adding custom tools to the agent, and the Cloud API lists integrations by category and authorizes and disconnects connected accounts for agent runs. Sourcedocs.browser-use.com/open-source/customize/tools/addread 2026-09-27 |
|
| Workflow Orchestration | Full |
|
Cloud runs chain as follow ups in one session with a message queue, and rerunnable scripts let a first run save tested code that later runs reuse deterministically and repair when the site changes; the open source library documents parallel agents, follow up tasks and Playwright steps mixed with agent steps. Sourcedocs.browser-use.com/cloud/agent/scriptsread 2026-09-27 |
|
| Knowledge Grounding & RAG | Not documented |
|
No retrieval index over the customer's knowledge is documented; workspaces hold files a run can read, and the hosted web search tool searches the web at run time. Sourcedocs.browser-use.com/cloud/agent/workspacesread 2026-09-27 |
|
| Human Oversight & Guardrails | Full |
|
A documented human checkpoint for approvals, authentication, payments or review: the run stops, a person acts in the live view, and a follow up run continues in the same session; the checkpoint is requested in the task rather than enforced by policy. Sourcedocs.browser-use.com/cloud/agent/human-in-the-loopread 2026-09-27 |
|
| Security, Identity & Governance | Partial |
|
SOC 2 Type II audited by an independent firm with the report under NDA, a DPA with EU SCCs, HIPAA support and zero data retention on enterprise plans; access is by project API keys and OAuth with a single mcp scope, and no roles, SSO or SCIM are documented. Sourcebrowser-use.com/enterpriseread 2026-09-27 |
|
| Observability & Auditability | Full |
|
Each run exposes a paged event stream and status through the API, browser sessions carry live view and recordings for debugging and audit, network events can be captured, and the open source library documents tracing through Laminar and OpenLIT plus cost tracking. Sourcedocs.browser-use.com/cloud/agent/observabilityread 2026-09-27 |
|
| Memory & State Persistence | Partial |
|
A V4 session holds conversation history across follow up runs and a workspace keeps files, including scripts the agent saved, across runs until deleted; that is stored files rather than a memory layer with a stated scope and lifetime, and saved browser profiles are browser state, not memory. Sourcedocs.browser-use.com/cloud/agent/workspacesread 2026-09-27 |
|
| Deployment & Data Residency | Full |
|
Customers choose the US deployment or the EU deployment in Frankfurt, each with its own API base URL and separate storage for runs, sessions, files and profiles, and the open source library self hosts on the customer's own machines. Sourcedocs.browser-use.com/cloud/eu-deploymentread 2026-09-27 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
The open source docs publish example apps for separate jobs (an ad generator, automated QA, a news monitor, a WhatsApp sender), code templates and agent skills, which the customer clones and runs; no packaged, ready to adopt agents are offered in the Cloud. Sourcedocs.browser-use.com/llms.txtread 2026-09-27 |
|
| Triggers & Channel Coverage | Full |
|
Cloud agents take scheduled work as well as API, SDK, MCP and n8n requests, and an iMessage group can be linked to an agent (US beta); schedules and webhooks are named among the US features not offered in the EU deployment. Sourcedocs.browser-use.com/cloud/which-productread 2026-09-27 |
|
| Model Flexibility & Routing | Full |
|
Each Cloud run takes a model ID from a published list spanning OpenAI, Anthropic, xAI and MiniMax models, with the customer's own OpenAI or Anthropic key as an option, and the open source library supports a documented list of providers including local models. Sourcedocs.browser-use.com/cloud/agent/modelsread 2026-09-27 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
A documented REST API (V4 runs, sessions, workspaces, profiles, browsers and integrations, with an OpenAPI 3.1 file), Python and TypeScript SDKs, a CLI and a hosted MCP server with OAuth. Sourcedocs.browser-use.com/cloud/api-v4-overviewread 2026-09-27 |
|
| Testing, Debugging & Optimization | Full |
|
A V4 run can request a judge, an LLM that evaluates the completed run against criteria the customer supplies and returns a verdict with the run, and sessions carry a feedback endpoint; no dataset or regression harness is documented. Sourcedocs.browser-use.com/cloud/faqread 2026-09-27 |
|
| Browser & Computer Use | Full |
|
Browser Use agents drive a real Chromium browser, either Browser Use's hosted stealth browsers with CAPTCHA handling, proxies, profiles and live view, or a local or remote browser through the open source library; hosted browsers also accept Playwright, Puppeteer, Selenium or CDP. Sourcedocs.browser-use.com/cloud/which-productread 2026-09-27 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Recent platform changes
Browser Use updated its Browser Harness v4 API to support client-controlled session recording, allowing API callers to explicitly enable or disable recording via the browserSettings.record parameter. The release also added a new v3:browsers:read OAuth scope that grants external applications read access to existing browser sessions.
Bears on: Observability / auditability
View sourceBrowser Use released the Browser Harness agent API to the public. The update also introduced new AI models across the platform and lowered the pay-as-you-go top-up minimum.
Bears on: MCP / tool calling / API
View sourcebrowser-use released 0.13.1, adding support for Claude Fable 5 and changing Anthropic behavior so tool choice is auto when using thinking. This is a dated compatibility release; current Fable 5 availability has not been separately verified.
Bears on: MCP / tool calling / API
View sourcePricing
Usage based: $0.02 per browser hour plus traffic and model tokens · one time $15 credit
usage
Included quota
Free: a one time $15 credit, 10 concurrent sessions, cost efficient models only. Pay as you go: $0.02 per browser hour metered by the minute, $5/GB managed residential proxy or $0.20/GB direct or own proxy egress, model tokens at each model's published rate (GPT-5.6 Luna $0.24 in and $1.44 out per million tokens), or the customer's own OpenAI or Anthropic key plus a 0.2x orchestration fee. Concurrency tiers at $200, $1,000, $5,000 and $25,000 lifetime spend. Enterprise: negotiated annual credit pool, 1,000+ sessions, custom SLAs, HIPAA support and zero data retention.
What is public
Browser Use publishes machine readable pricing: no subscriptions; a one time $15 signup credit; pay as you go at $0.02 per browser hour, $5/GB managed proxy or $0.20/GB egress, and per model token rates; concurrency set by lifetime spend; Enterprise by negotiated annual credit pool. The open source library is free.
Billing mechanics
One dollar denominated credit balance covers browser time, traffic and model tokens. Browser time is reserved for the requested timeout and unused credit is returned, with a one minute minimum. With the customer's own model key, the provider bills tokens and Browser Use adds a 0.2x orchestration fee. Legacy subscriptions can still be managed from the billing page.
Cost watchouts
Model tokens can outweigh browser time at $0.02 an hour, especially on premium models; managed proxy traffic at $5/GB; the 0.2x orchestration fee applies even with your own model key.
Variable cost rationale
Fully usage-based and multi-axis - spend scales with session minutes, proxy/bandwidth GB, and LLM token volume simultaneously; concurrency and run length are the big levers, and BYO-key (0.2x orchestration) vs their-LLM (1.2x) materially changes the token line
Additional watchouts
Three meters (browser time, traffic, model tokens) share one balance, so model choice drives most of the cost; free accounts are limited to cost efficient models until a first top up; concurrency depends on lifetime spend.
Overage / add-ons
No plan allowance to exceed: credits are bought as top ups ($5 to $100,000, or presets of $100, $500 and $1,000), never expire, and can auto recharge; concurrency rises with lifetime spend from 10 to 1,000 sessions.
Sales call required
Mixed (some tiers require a call)
Free / trial
One time $15 credit for eligible Google, GitHub or Microsoft signups; open source library free
Lowest paid plan
Pay as you go credit top up from $5
Commercial notes
Browser Use sells two cloud products, Browser Use Agents (API V4) and Browser Infrastructure, beside its open source library, CLI and MCP server. Enterprise terms add SOC 2 Type II under NDA, a DPA with EU SCCs, HIPAA support, zero data retention and EU residency on request.
Key ambiguities
Pricing is component based rather than a plan list, so a single monthly figure does not describe it; legacy subscription tiers are no longer sold.
Cancellation / refund
No subscription or commitment; top up credits never expire; Enterprise is a negotiated annual agreement.
Support SLA / resale
Docs and community for pay as you go; Enterprise adds dedicated support and custom SLAs.
Missing data
Enterprise pool pricing is negotiated; everything else is published.
Related vendors
- AgentQL — A self-healing query language for the web: natural language…
- AGI, Inc. — AGI, Inc
- Airtop — Cloud browsers for AI agents that compile plain English workflows…
- Asteroid — Healthcare portal integration platform: supervised browser and…
- Automat AI — AI agents that operate computers visually, sold as Automat Workforce…
- Autotab — General AI agent that learns a workflow from a demonstration and…
Alternatives to Browser Use
The closest documented capability profiles to Browser Use among browser and computer-use agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Skyvern11.5 / 14Fuller documented coverage on Security, Identity & GovernanceBrowser Use vs Skyvern →
- Automat AI11.5 / 14Adds documented Knowledge Grounding & RAG
- Axiom.ai10.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Browserbase10.0 / 14Fuller documented coverage on Security, Identity & GovernanceBrowser Use vs Browserbase →
- H Platform9.0 / 14A lighter documented profile than Browser Use
- Asteroid11.5 / 14Adds documented Knowledge Grounding & RAG
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded