HTTP 200 verified twice
Finding your next stop…
Loading the latest directory information.
Loading the latest directory information.
Browser Use is an AI web agent platform offering browser task automation and managed browser infrastructure accessible via SDK, REST, CDP, or MCP. It features an Agency skill for proactive research, 82% on Internal Bench Hard, SOC 2 Type II compliance, and a $17M funding round.
Start here for the decision-making essentials: what Browser Use does, who it is for, how it is accessed, and the first-party sources behind this profile.
$0.02 per browser hour with no subscription required
Read-only public captures of Browser Use’s homepage and verified pricing page. Screenshots are dated, never live embeds, and open full-screen.
Short answers to the questions buyers and builders commonly ask about Browser Use. Each answer cites the shared ledger below, where every source is listed once.
Browser Use Agents complete browser tasks from a prompt · Browser Infrastructure gives existing agents and automations managed browsers through SDK, · Make websites accessible for AI agents; extract interactive elements and automate browser · Operates an AI agent that browses websites and performs tasks on a user's behalf
Browser Use Agents complete browser tasks from a prompt.
Make websites accessible for AI agents, extract interactive elements and automate browser · Web research across public records, regulators, clinical registries, academic publishers, · Replacing multiple browser tools with a single Browser Use driver (Hermes replaced 12 brow
Make websites accessible for AI agents. Extract interactive elements and automate browser interactions.
$0.02 per browser hour with no subscription required · 17¢ per solved task for Browser Use Agents · Proxyless / Bring Your Own Proxy: egress is billed at $0.20 / GB · Token-based pricing at 1.2× provider rates
Browsers cost $0.02/hour with no subscription required.
Connect your own agent to managed browser infrastructure through API, SDK, OpenAPI, or MCP · Stripe as third-party payment processor · Third-party login via Google or GitHub · Any general agent that can call a tool can use the Browser Use browser layer
connect your own agent to managed browser infrastructure through the API, SDK, OpenAPI, or MCP.
V4 agents can be scheduled via Scheduled Jobs with pause/resume controls · Supports both a local Chrome browser and a Cloud Managed browser through one interface
V4 agents can now be scheduled, with pause/resume controls, alongside legacy jobs in Scheduled Jobs.
Third-party audits conducted by Accorp Partners, with reporting period July 17, 2025 to Oc
The auditing was done by Accorp Partners, which has a track record of partnering with many SaaS companies. The reporting period is from July 17, 2025 to October 17, 2025.
This profile connects the jobs Browser Use is described as handling with its delivery model, access options and the subjects used to match it to related products in this directory.
Each fact points to a recorded source, making it easy to distinguish verified product information from claims that need checking.
HTTP 200 verified twice
Browser Use Agents & Browser Infrastructure | Browser Use
Browser Use Agents complete browser tasks from a prompt · Managed browsers accessible via SDK, REST, CDP, or MCP · Browsers cost $0.02/hour with no subscription required
Browser Use Agents complete browser tasks from a prompt
Browser Infrastructure gives existing agents and automations managed browsers through SDK, REST, or CDP
Make websites accessible for AI agents, extract interactive elements and automate browser interactions
$0.02 per browser hour with no subscription required
17¢ per solved task for Browser Use Agents
Proxyless / Bring Your Own Proxy: egress is billed at $0.20 / GB
Token-based pricing at 1.2× provider rates
Bring Your Own Key: connect Anthropic, OpenAI, or Google API key, pay provider directly plus a 0.2× orchestration fee
Managed browsers accessible via SDK, REST, CDP, or Browser Harness with per-minute billing
A concise view of the jobs, capabilities and integrations described in the recorded product sources.
Documented product formats, platforms and official distribution destinations. Availability can vary by region and plan.
A concise history of software releases and material product changes. Events appear only when a dated source supports what changed.
Showing the newest updates and meaningful milestones. Open an entry for its summary and source.
Sessions receive sharing and management upgrades, the Usage page is redesigned, and X402 top-ups are made cheaper.
View source [14]Client-controlled browser recording is now available on the Browser Harness API, alongside OAuth read access to browsers.
View source [14]Release 0.13.6 with Browser Harness 0.1.6 by @gregpr07 in https://github.com/browser-use/browser-use/pull/5245
View source [1]Update README.md by @ShawnPana in https://github.com/browser-use/browser-use/pull/5197 · feat: accept bu-qa-1 model alias in ChatBrowserUse by @Alezander9 in https://github.com/browser-use/browser-use/pull/5226 · support MCP registry by @laithrw in…
View source [1]The Browser Harness agent API became public, new models were added across the platform, and the pay-as-you-go top-up minimum was lowered.
View source [12]Launch Browser Use CLI 3.0 powered by Browser Harness. · Add browser-use skill so coding agents can install the Browser Use skill directly. · Pin Browser Harness to 0.1.4 and ship the Browser Use skill with the package.
View source [1]Browser Use 0.13.0 introduces a new Rust-backed beta agent. It gives modern models a more direct browser control loop, guided by robust helpers instead of brittle browser abstractions.
View source [1]another big cli update by @ShawnPana in https://github.com/browser-use/browser-use/pull/4514 · fix: security and correctness issues found in 4514 review by @sauravpanda in https://github.com/browser-use/browser-use/pull/4590 · fix: upgrade aiohttp to 3.13.4 to…
View source [1]Facts, answers, structured details, milestones and primary resource links cite this shared ledger. Each external page appears once; release tags from the same GitHub project are grouped under one release history.
These tools share a workflow, capability or audience with Browser Use. They may complement it rather than replace it, and are not presented as integrations or endorsements.
Connect your own agent to managed browser infrastructure through API, SDK, OpenAPI, or MCP
Maintains open-source Browser Harness, SDK, and MCP developer tools
82% on Internal Bench Hard
Make websites accessible for AI agents; extract interactive elements and automate browser interactions
Operates an AI agent that browses websites and performs tasks on a user's behalf
Agency skill enables agents to proactively research, prepare work, and return with follow-ups, asking for approval only before an external action like sending or publishing
Browser Use, Inc.
Stripe as third-party payment processor
Third-party login via Google or GitHub
Pages maintained on Facebook, X, Instagram, and YouTube
V4 agents can be scheduled via Scheduled Jobs with pause/resume controls
68 seconds per task on the published OnlineMind2Web workload vs 225-330s for Gemini, Claude, and OpenAI computer use models
53 tasks per dollar vs 2 for Sonnet 4.5
Enables AI to control browsers by extracting interactive elements and automating browser interactions
Connects to browsers over the Chrome DevTools Protocol (CDP) by executing Python written by a tool-calling model
Supports both a local Chrome browser and a Cloud Managed browser through one interface
Any general agent that can call a tool can use the Browser Use browser layer
Web research across public records, regulators, clinical registries, academic publishers, and city halls where the answer is multiple clicks deep in non-queryable forms
Replacing multiple browser tools with a single Browser Use driver (Hermes replaced 12 browser tools with one driver, reducing task tokens 48–66% across 204 live runs)
Community-led project with 80k+ GitHub stars achieved in four months
SOC 2 Type II compliant
Third-party audits conducted by Accorp Partners, with reporting period July 17, 2025 to October 17, 2025
Raised a $17M funding round
San Francisco
Small, hyper-focused team
Browser Use Agents complete browser tasks from a prompt · Browser Infrastructure gives existing agents and automations managed browsers through SDK, · Make websites accessible for AI agents; extract interactive elements and automate browser
Enable AI to control your browser
Extract interactive elements and automate browser interactions
Pass session id to judge LLM calls by @MagMueller in https://github.com/browser-use/browser-use/pull/4918 · fix(agent): skip screenshots on new tab pages by @MagMueller in https://github.com/browser-use/browser-use/pull/4920
View source [1]fix(daemon): restrict unix socket file to owner-only access by @sauravpanda in https://github.com/browser-use/browser-use/pull/4870 · docs: clarify integration example placement by @felix-windsor in https://github.com/browser-use/browser-use/pull/4856 ·…
View source [1]BYOK lets users bring their own LLM keys, Code Mode generates reusable automation scripts, and Sensitive Data enables passing secrets securely.
View source [12]fix: set default temperature to 1.0 for gemini-3 models by @markmcd in https://github.com/browser-use/browser-use/pull/4489 · fix bedrock structured output w SchemaOptimizer to flatten schema by @laithrw in https://github.com/browser-use/browser-use/pull/4524…
View source [1]Remove litellm from core dependencies in response to the litellm supply chain attack (versions 1.82.7 & 1.82.8 backdoored on March 24, 2026). · pip install browser-use no longer installs litellm · ChatLiteLLM wrapper is preserved — install litellm separately…
View source [1]Pinned litellm library version · fix: detect uv installed via curl script by @ishan0102 in https://github.com/browser-use/browser-use/pull/4478 · frozen litellm version by @sauravpanda in https://github.com/browser-use/browser-use/pull/4509
View source [1]Browser Use CLI 2.0 · The fastest browser automation for AI coding agents. 2x faster, 50% fewer tokens, and works with any CLI agent — Claude Code, Codex, and more.…
View source [1]don't explicitly pass newWindow: false to CDP createTarget by @laithrw in https://github.com/browser-use/browser-use/pull/4283 · Update documentation links in README.md by @Cheggin in https://github.com/browser-use/browser-use/pull/4308 · Delete docs directory…
View source [1]Fix proxy auth attach handler overwriting tab tracking by @laithrw in https://github.com/browser-use/browser-use/pull/4220 · fix(3523): storagestate restore (cookies + localStorage) by @laithrw in https://github.com/browser-use/browser-use/pull/4102 · patched…
View source [1]improved csv file generation by @sauravpanda in https://github.com/browser-use/browser-use/pull/4213 pin all dependency version in pyproject.toml by @sauravpanda in https://github.com/browser-use/browser-use/pull/4215
View source [1]updated laminar version by @sauravpanda in https://github.com/browser-use/browser-use/pull/4154 · updated navigateandwait by @sauravpanda in https://github.com/browser-use/browser-use/pull/4146 · fix radio button click occlusion when label overlaps input by…
View source [1]Fix CDP connectivity issues by @LarsenCundric in https://github.com/browser-use/browser-use/pull/4135 · feat: improve auth/real browser docs + add Browser.fromsystemchrome() by @laithrw in https://github.com/browser-use/browser-use/pull/3955 · Anthropic model…
View source [1]fix(3895): stop agent if browser closed by @laithrw in https://github.com/browser-use/browser-use/pull/4056 · fix(llm): handle missing choices in openai proxy response by @sudhanshu112233shukla in https://github.com/browser-use/browser-use/pull/3899 · fix:…
View source [1]Fix download monitoring issues with fetch requests and blob downloads by @sandeepsalwan1 in https://github.com/browser-use/browser-use/pull/3518 · Agent max clickable parameter by @MagMueller in https://github.com/browser-use/browser-use/pull/4107
View source [1]fix(3895): stop agent if browser closed by @laithrw in https://github.com/browser-use/browser-use/pull/4056 · fix(llm): handle missing choices in openai proxy response by @sudhanshu112233shukla in https://github.com/browser-use/browser-use/pull/3899 · fix:…
View source [1]added basic planing to agents by @sauravpanda in https://github.com/browser-use/browser-use/pull/4008 · align agent success with simple judge by @sauravpanda in https://github.com/browser-use/browser-use/pull/4009 · updated agent success with simple judge by…
View source [1]docs: add quotes around browser-use[cli] for shell compatibility by @ShawnPana in https://github.com/browser-use/browser-use/pull/4002 · schema enforcement in extract tool by @sauravpanda in https://github.com/browser-use/browser-use/pull/3996 · added…
View source [1]add grep tool to agent by @sauravpanda in https://github.com/browser-use/browser-use/pull/3997 · Revert "feat(cli): add --cdp-url flag to connect to existing browser … by @sauravpanda in https://github.com/browser-use/browser-use/pull/3998 · improved filename…
View source [1]fix(3264): clear agent eventbus, not just browser session's by @laithrw in https://github.com/browser-use/browser-use/pull/3964 · Increase LLM timeout to 75s for gemini and browser-use models by @MagMueller in…
View source [1]Release: 0.11.5 - Browser Use Model bu-2-0 🚀 · We're excited to announce bu-2-0 , our latest premium model for browser automation. · bu-2-0 delivers a significant leap in accuracy while maintaining the speed that made bu-1-0 the fastest web agent:
View source [1]Browser Use CLI + skill · Give your Claude Code/Codex agent access to local and remote browsers. Really helpful for local dev. · browser-use open https://example.com Navigate
View source [1]Buoss example flash mode by @mertunsall in https://github.com/browser-use/browser-use/pull/3774 · include axname for rerun history element hash by @sauravpanda in https://github.com/browser-use/browser-use/pull/3775 · Dont skip failrues by default by…
View source [1]We released an open source model specialized in Browser Use https://huggingface.co/browser-use/bu-30b-a3b-preview. · perf: lazy import for openai and reportlab to reduce startup latency by @hacking-racoon in https://github.com/browser-use/browser-use/pull/3764…
View source [1]docs: fix default action count in docs by @sauravpanda in https://github.com/browser-use/browser-use/pull/3741 · update system prompts by @mertunsall in https://github.com/browser-use/browser-use/pull/3746 · docs fix ChatOpenAI import path by @sauravpanda in…
View source [1]from browseruse import Agent, ChatBrowserUse skills=['skill-uuid-1', 'skill-uuid-2'], Specific skills (recommended)
View source [1]Release again because forgot to bump pyproject :) · Bump pyproject to 0.10.0 by @mertunsall in https://github.com/browser-use/browser-use/pull/3690 · Bump dependency to 0.10.1 by @mertunsall in https://github.com/browser-use/browser-use/pull/3691
View source [1]In this release, we merged many PRs from the community into Browser Use and made the library significantly more stable! more timeout for gemini 3 pro by @mertunsall in https://github.com/browser-use/browser-use/pull/3618
View source [1]Fix: Ignore Inert Carousel Elements by @PredictiveManish in https://github.com/browser-use/browser-use/pull/3564 · Revert "Fix: Ignore Inert Carousel Elements" by @mertunsall in https://github.com/browser-use/browser-use/pull/3598 · Configure screenshot size…
View source [1]
