- 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.
- 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…
- The first run without a key opens Browser Use login and continues after approval; cloud browsers print their live-view link.
- Judge gotchas stay grounded in what the run observed.
Browser Use
Open-source Python library and hosted cloud that let LLM agents control a real browser to complete web tasks, with a CLI, a cloud API for hosted agents and browsers, and its own BU 2.0 model option.
Use it in: API / SDK CLI Works with: Local models Own API key Multi-agent Headless / CI
On this page
Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:28 UTC. Date of each number
What Browser Use does
Browser Use is a browser automation library from Browser Use, first released in November 2024. You use it through an API and a command-line tool. Its documentation covers subagents or parallel agents, a non-interactive mode for scripts and CI, your own API key and local models. It can run models from OpenAI, Anthropic, Google, Azure, Amazon Bedrock and DeepSeek and others. It is used from Python and TypeScript. It is free and open source (MIT); you pay only for the models it calls.
Key facts
| Maker | Browser Use |
|---|---|
| Type | Browser automation library |
| First released | November 2024 |
| License | MIT |
| Interfaces | API, CLI |
| Models | Any LLM of your choice (OpenAI, Anthropic, Google and others) plus its own BU 2.0 model via the cloud |
| Bring your own API key | Yes |
| Main language | Python |
| Open issues and PRs | 594 |
| Docker Hub pulls | 305,337 |
Pricing
Open-source library is free (MIT). Cloud is pay-as-you-go with no subscription: $1 free signup credit, browsers $0.06/hour, home-IP proxies $5/GB, direct/custom proxies $0.20/GB. Hosted agents and models billed at per-token rates (ranging from $0.12–$12/1M input tokens depending on model). Browser concurrency unlocked by cumulative spending: 50 browsers at $100 total paid, 250 at $1,000, 500 at $5,000, 1,000 at $25,000.
Source: official pricing page, checked Nov 16, 2026. Prices change often; confirm before you buy.
Browser Use pricing history since 2024 · Compare prices of all agents
Quick answers
- Free to start?Yes
- Open source?Yes (MIT)
- Bring your own API key?Yes
- Where you use itAPI, CLI
- Model providersopenai, anthropic, google, azure, amazon, deepseek, mistral, qwen, openrouter, any OpenAI-compatible, local
- Subagents / multi-agent?Yes
- Runs in scripts / CI?Yes
- Feature comparisonAll agents
- Closest alternativeBrowser Harness · all alternatives
What's new in Browser Use: November 2026 so far
November brought Browser Use to version 1.0 with major breaking changes, stricter defaults, and new safety features. The release includes a built-in judge to verify task completion and improved support for running without a dedicated browser.
- Version 1.0 removes all 0.x imports and changes how browsers are configured; see MIGRATING.md for required changes.
- Each run now includes an automatic judge that checks whether the task succeeded using your own model.
- Browser Use can now drive its own Chromium on servers and containers where Chrome is unavailable.
- Default max_steps reduced from 500 to 100, and run() returns errors instead of raising exceptions.
7 releases this month · summarised from the official release notes · all months
AgentGid articles about Browser Use
LangGraph, Mem0, Browser Use and Langfuse: The 4-Layer Agent Stack
A viral post says four repos turn a chatbot into a real agent. We checked LangGraph, Mem0, Browser Use and Langfuse on AgentGid's live data: how much each is used, what the hosted versions cost, the license detail and a better prompt.
Best AI Browser Agents in 2026: Browser Use, Stagehand, Claude in Chrome and AI Browsers
AI agents that use a web browser, compared: developer libraries for browser automation, agents that work in your own browser, and AI browsers. Live usage, prices and how to choose.
Best AI Agents in 2026: Live Rankings by Category
The leading AI agents for coding, design, research, data, marketing, sales, support, HR, finance, legal, DevOps and security, ranked by public usage data that refreshes daily, with prices and free options.
Get started with Browser Use
| npm | npm install browser-use-sdk |
|---|---|
| PyPI | pip install browser-use |
| Docker | docker pull browseruse/browseruse |
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Browser Use alternatives
Best Browser Use alternatives compared · All browser and computer-use agents
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 16 |
Browser HarnessBrowser Use |
61 | 2.2M | down 0.3% | up 26.5% | 19.2K+19/day | 0.1.132mo ago | Free (OSS) | |||
| 18 |
agent-browserVercel Labs |
60 | 2.5M | up 3.7% | up 29.9% | 52.7K+386/day | 0.43.08d ago | Free (OSS) | |||
| 21 |
StagehandBrowserbase |
57 | 2.9M | down 13.3% | up 39.5% | 26.1K+14/day | 3.7.42d ago | Free + $20/mo | |||
| 76 |
ARTEMISGoogle |
422/4 | — | — | — | 17.7K+66/day | — | Free (OSS) | |||
| 77 |
Ego LiteCitroLabs |
42 | — | — | — | 23.6K+152/day | 2.2.14d ago | Free (OSS) | |||
| 93 |
Open-AutoGLMZ.ai |
392/4 | — | — | — | 26.6K+9/day | — | Free (OSS) | |||
Head to head: Browser Use vs Browser Harness · Browser Use vs agent-browser · Browser Use vs Stagehand · Browser Use vs ARTEMIS · Browser Use vs Amazon Nova Act · Browser Use vs BrowserSkill · Browser Use vs Perplexity Comet · Browser Use vs Skyvern
Tools used with Browser Use
What 283 public GitHub projects that depend on Browser Use use with it, from their dependency files.
- python-dotenv51.9%
- Playwright (Python)47.3%
- LangChain43.8%
- Pydantic42.8%
- OpenAI Python Library35.7%
- Uvicorn33.6%
- Requests32.9%
- FastAPI29.7%
- Pillow29.0%
- TypeScript27.2%
Used far more often here than in AI-built projects overall: what sets Browser Use projects apart.
- markdownify14.5% · 100.7×
- html2text13.8% · 95.8×
- PostHog12.7% · 88.4×
- backoff12.7% · 79.6×
- duckduckgo-search12.7% · 37.9×
- Ollama15.2% · 29.7×
- distro12.7% · 22.7×
- tiktoken (Python)17.7% · 18.7×
Ratings from people who use Browser Use
No ratings yet. Used Browser Use? Rate it and say what it is good and bad at.
Browser Use news
-
Browser Use 1.0.6 released
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.; 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…
-
Browser Use 1.0.5 released
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…; The judge sees the trace, the run's last screenshots and the…
-
Browser Use downloads up 26% in a week
2.2M npm and PyPI downloads in the 7 days to Nov 12, against 1.7M the week before.
What changed: recent Browser Use releases
13 stable releases in the last 90 days · Monthly summary · Full changelog
- 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…
- The judge sees the trace, the run's last screenshots and the final page (unless use_vision=False).
Earlier releases
- The agent drops old screenshots in one batch once 20 tool results carry one, instead of on every new screenshot.
- BU_NAME callers get their own Chromium when Chrome can't be used.
- When a browser setup error may be fixed in a newer release, the CLI and MCP tell the agent to upgrade.
- 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.
- 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…
- 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.
- 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.
Browser Use prices over time
Browser Use popularity and usage data
Browser Use was downloaded 2.2M times from npm and PyPI in the week ending Nov 17, 2026, up 10.9% on the week before and down 5.8% over the last 30 days compared with the 30 before. The GitHub repository has 121K stars, 3,205 of them added in the last 30 days. The latest stable release is 1.0.6, published Nov 16, 2026; there were 8 stable releases in the past 30 days. It was mentioned in 11 Hacker News posts and comments over the last 30 days.
Download the raw daily series: browser-use.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 17, 2026 | Nov 19, 06:24 UTC |
| GitHub stars | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Docker pulls | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Website rank (Tranco) | Nov 18, 2026 | Nov 19, 06:28 UTC |
| Hacker News mentions | Nov 18, 2026 | Nov 19, 06:26 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
Browser Use FAQ
How much does Browser Use cost?
Open-source library is free (MIT). Cloud is pay-as-you-go with no subscription: $1 free signup credit, browsers $0.06/hour, home-IP proxies $5/GB, direct/custom proxies $0.20/GB. Hosted agents and models billed at per-token rates (ranging from $0.12–$12/1M input tokens depending on model). Browser concurrency unlocked by cumulative spending: 50 browsers at $100 total paid, 250 at $1,000, 500 at $5,000, 1,000 at $25,000.
Is Browser Use open source?
Yes. Browser Use is open source, released under the MIT license.
How popular is Browser Use?
Browser Use was downloaded 2.2M times from npm and PyPI in the week ending Nov 17, 2026, up 10.9% on the week before and down 5.8% over the last 30 days compared with the 30 before. The GitHub repository has 121K stars, 3,205 of them added in the last 30 days. The latest stable release is 1.0.6, published Nov 16, 2026; there were 8 stable releases in the past 30 days.
What is the latest version of Browser Use?
The latest stable release we track is 1.0.6, published on Nov 16, 2026.
What are the alternatives to Browser Use?
The closest alternatives in the same category by Gid Score are Browser Harness, agent-browser, Stagehand, ARTEMIS.
For the makers of Browser Use badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/browser-use/)
[](https://agentgid.com/agents/browser-use/)
[](https://agentgid.com/agents/browser-use/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
npm: browser-use-sdk. PyPI: browser-use. GitHub: browser-use/browser-use. Site rank: browser-use.com on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: github.com, raw.githubusercontent.com, pypi.org, registry.npmjs.org, browser-use.com, hub.docker.com, discord.com.