Browser Use logo

Browser Use

Emerging

Browser Use is an open-source Python library that enables AI agents to control web browsers, making it easy for LLMs to interact with any website through a clean, model-agnostic API.

42
AI Score
Grade C↑ Trending
AI Visibility Score (Beta)
Developer ToolsWebsiteUpdated November 2026

Company Overview

About Browser Use

Browser Use is an open-source project that provides a Python library allowing AI agents and large language models to control web browsers as a tool. The library sits between LLM APIs and browser automation frameworks like Playwright, providing a clean, model-agnostic interface that makes it straightforward for AI agents to navigate websites, fill forms, extract information, and complete multi-step web tasks without requiring developers to write custom browser control code.

Business Model & Competitive Advantage

The project gained rapid adoption in the AI agent developer community because it solves a fundamental challenge in building practical AI agents: the web is the most comprehensive source of real-world information and services, but giving AI agents reliable web access requires careful handling of dynamic content, authentication flows, modal dialogs, and page state management. Browser Use's library handles these complexities so that developers can focus on their agent's task logic rather than browser automation mechanics.

Competitive Landscape 2025–2026

Browser Use represents the open-source infrastructure layer of the AI agent ecosystem—similar to how libraries like LangChain and LlamaIndex emerged as standard building blocks for LLM applications. The project is maintained with commercial support and enterprise licensing, allowing it to sustain development while keeping the core library freely available to the developer community.

Curated content • Fact-checked and verified

Recent Activity

View all →
release
browser-use 1.0.6

`pip install 'browser-use==1.0.6'` - **BU 4.0 is the default model.** `Agent(task)` and `ChatBrowserUse()` now run `bu-4.0` on the Browser Use gateway instead of `bu-fast`. Pass `llm='bu-4.0-mini'` for simple tasks at the lowest cost, or `llm='bu-4.0-pro'` for the hardest tasks (#6430). - **This costs more if you pass no `llm`.** BU 4.0 tokens cost 15 times as much as `bu-fast` ($1.80 / $9.00 per 1M input / output tokens, against $0.12 / $0.60), and it runs at high instead of medium reasoning in the default mode. A short test task cost $0.022 instead of $0.0014. To keep the previous model and price, pass `llm='bu-fast'`. Prices: https://docs.browser-use.com/open-source/models - The first run without a key opens Browser Use login and continues after approval; cloud browsers print their live-view link (#6425). - Judge gotchas stay grounded in what the run observed (#6418). PRs: https://github.com/browser-use/browser-use/pull/6430, https://github.com/browser-use/browser-use/pull/6425, htt

blog_post
Browser Use agents can now check out without ever seeing your card, with Evervault

Evervault Browser Tokens let a Browser Use agent fill checkout forms with stand-in card numbers. Evervault swaps in the real card only in the request to the payment host you allow.

blog_post
Log In Once: Reuse Cookies and Profiles Across Browser Use Runs

Reuse a login across separate Browser Use runs with profiles. Save Playwright authentication state, handle expired cookies, and keep user accounts separate.

release
browser-use 1.0.5

`pip install 'browser-use==1.0.5'` - Every run is judged by your own model: one more low-effort request checks the run against the task and fills `result.judgement` with `success`, `failure_reason`, `description`, `prompt_injection_detected`, `bot_block_or_captcha_detected` and `gotchas`. `judge_context=` gives it your criteria; `judge=False` turns it off; the 0.x `use_judge` / `ground_truth` work again (#6398). - The judge sees the trace, the run's last screenshots and the final page (unless `use_vision=False`). It writes gotchas whenever the site rejected input, errored, blocked or rate-limited the agent, also on a successful run, e.g. "The form requires phone numbers in (###) ###-#### format" (#6403). 13 real runs, each judged 3 times: gotchas on 15/15 verdicts where the site pushed back (6/15 before), 2/24 on clean runs, success verdicts unchanged. PRs: https://github.com/browser-use/browser-use/pull/6398, https://github.com/browser-use/browser-use/pull/6403, https://github.com/bro

release
browser-use 1.0.4

`pip install 'browser-use==1.0.4'` - The agent drops old screenshots in one batch once 20 tool results carry one, instead of on every new screenshot. Each prune rewrote an earlier message and broke the provider's prompt cache, so screenshot-heavy runs paid full input price on almost every step (BU Bench 1.0.3: one 705-step task read 27.8M input tokens, 1.6M from cache). - `BU_NAME` callers get their own Chromium when Chrome can't be used (#6387). - When a browser setup error may be fixed in a newer release, the CLI and MCP tell the agent to upgrade (#6388). BU Bench v2.1 (200 tasks), vs 1.0.3: same score (76.1 vs 76.0), model cost per task $0.208 vs $0.434. PR: https://github.com/browser-use/browser-use/pull/6394

release
browser-use 1.0.3

`pip install 'browser-use==1.0.3'` - `--cli-mcp` exits cleanly when the client closed the pipe before the reply (was exit 1 with `ExceptionGroup`). - The CLI runs its own Chromium when no browser has remote debugging on or there is no display, like `--cli-mcp`. It persists across calls; `browser-use --reload` closes it. - A `BU_CDP_URL` nothing listens on fails in 3 s with one message naming the value and both ways out (was a 30 s wait). - Chrome in another pid namespace (containers, Cursor on Linux) is accepted via its DevToolsActivePort. - A cancelled cloud run copies downloads within 10 s instead of holding the browser up to 300 s per pass. - `ActionResult` drops and warns about every ignored 0.x field, not only the first (#6379). PR: https://github.com/browser-use/browser-use/pull/6383

release
browser-use 1.0.2

Fixes on 1.0.1. - **MCP with Chrome's remote debugging off:** `browser-use --cli-mcp` now drives its own Chromium instead of stopping at the chrome://inspect steps, and tells your agent how to switch to your Chrome (tick "Allow remote debugging" at chrome://inspect/#remote-debugging, restart the MCP server). - **Slow pages:** CDP calls from the CLI and MCP wait 20 s, like the agent. A page frozen by a JS dialog fails fast with an error that says to handle the dialog. - **Windows:** `open()` in MCP `browser_exec` code reads and writes UTF-8. - **Feedback:** tell us what broke with `browser-use feedback "..."` or `browser_use.feedback("...")`. The agent can call `report_issue(...)` and MCP clients get a `browser_feedback` tool. Text is scrubbed before it leaves. ```bash uv add 'browser-use==1.0.2' ```

blog_post
How to Use Custom Proxies with Browser Use

Connect your own proxy to Browser Use Cloud, verify the browser's exit IP and country, and reuse the setup with local or cloud Playwright.

release
browser-use 1.0.1

Fixes on 1.0.0. - **MCP without Chrome:** `browser-use --cli-mcp` on servers, containers and CI boxes now drives its own Chromium, installed on first use. When no browser can run, you get one clear error. - **`http_get`** in the CLI and MCP always fetches from your machine. - **`--mcp` with `allowed_domains`** can no longer be bypassed through a cloud browser. - **Windows:** piped CLI code and long MCP output are UTF-8. - **Read-only HOME:** the error names the env var to set. - **`timeout=`:** the final answer arrives before the deadline, and provider retries respect it. - **0.x feature detection:** `hasattr(browser_use, '<removed 0.x name>')` returns `False`. - **Isolation:** each run gets its own browser-harness workspace. ```bash uv add 'browser-use==1.0.1' ```

release
browser-use 1.0.0

<img src="https://github.com/browser-use/browser-use/releases/download/1.0.0/browser-use-1.0-vs-0.x-bench.png" alt="browser-use 1.0 vs 0.x: higher score, cheaper, faster, 80% less code" width="100%"> ## −136,866 lines. 80% of the library deleted. We started over. The agent now writes Python in one persistent REPL, straight on Chrome DevTools Protocol. No DOM serializer, no action schema, nothing in between. Simplicity wins: it is now the [state-of-the-art web agent](https://browser-use.com/benchmarks). ``` ● task │ ● model writes a cell new_tab(url); bu.click(41); js(...) │ ● REPL runs it on Chrome (CDP) → output back to the model │ ✓ finish(result) ``` **Same models: up to 33 points higher, 2.7–5.2x cheaper, 2–3x faster.** ```bash uv add 'browser-use==1.0.0' export BROWSER_USE_API_KEY=bu_... # cloud.browser-use.com/new-api-key ``` ```python from browser_use import Agent print(Agent('Find the number of stars of the browser-use repo').run_sync().final_result()) ``` Pin with `==`. We shi

blog_post
Autofill Passwords with 1Password and Browser Use

Connect 1Password to Browser Use, give an agent read-only vault access through a service account, and automate and verify a login.

blog_post
Best Proxy Providers for AI Agents (2026)

Compare eight residential proxy providers for browser automation and AI agents, with hands-on task tests, entry prices, and sticky-session trade-offs.

Key Differentiators

Emerging Innovator

Browser Use is an emerging player bringing innovative solutions to the Developer Tools market.

Frequently Asked Questions

Estimated Visibility Trend (Beta)

Simulated 8-week rolling score

42
↑ Trending

Based on estimated brand signals. Historical tracking coming soon.

Similar Brands

Supabase logo

Supabase

Developer Tools
B2bDeveloper ToolsPlatformSaasScaleupStartup

Supabase is an open-source backend-as-a-service platform that provides developers with a fully managed PostgreSQL database alongside a suite of backend services—authentication, file storage, edge func

Claude Code logo

Claude Code

Developer Tools
B2bDeveloper ToolsPlatformSaas

Claude Code is Anthropic's agentic software engineering tool, launched in February 2025 as a command-line interface that operates directly in developer terminals. Unlike IDE-based coding assistants (C

GitHub Copilot logo

GitHub Copilot

Developer Tools
B2bDeveloper ToolsPlatformSaas

GitHub Copilot is an AI-powered coding assistant developed by GitHub (Microsoft) in partnership with OpenAI, providing real-time code suggestions, function completions, documentation generation, and w

Cursor logo

Cursor

Developer Tools
B2bDeveloper ToolsPlatformSaasUnicorn

Cursor is an AI-first code editor founded in 2022 by a small team of MIT researchers, built as a fork of Visual Studio Code with native large-language-model intelligence woven directly into the editin

Replit logo

Replit

Developer Tools
B2bDeveloper ToolsPlatformSaasScaleupUnicorn

Replit is a San Francisco-based AI-powered coding platform — backed with $97.4 million raised at a $1.16 billion valuation from a16z, Y Combinator, and others — providing browser-based development env

Kubernetes logo

Kubernetes

DevOps
B2bCloud NativeDeveloper ToolsOpen SourcePlatformSaas

Kubernetes (K8s) is the dominant open-source container orchestration platform — originally developed by Google engineers (Joe Beda, Brendan Burns, Craig McLuckie) in 2014, donated to the Cloud Native

Compare Browser Use with Competitors

Side-by-side AI visibility scores, platform breakdown, and market position.

For Browser Use

Claim This Profile

Are you from Browser Use? Verify your company email to claim this profile and keep its description, products, and FAQs up to date.

Claim Browser Use Profile →
For competitors & analysts

Track AI Visibility in Real Time

Monitor how ChatGPT, Gemini, Perplexity, and Claude mention Browser Use vs competitors. Get alerts when AI recommendations shift.

Start Free Tracking →