Agent frameworks & harnesses · Browser Use
EditorialBrowser Use
Open-source browser agent. Version 1.0 writes Python in a persistent REPL on Chrome DevTools Protocol, on Pydantic AI. Browser() starts a cloud browser.
Last verified:
Updated
Is this your tool? Claim / update this listing
For the maker
Complete your listing
These five fields are read from the listing. Missing items go to the claim form, which emails the desk. There is no login. 2 of 5 on file.
- Add screenshots
ScreenshotsMissing
No product screenshot is in the listing yet. A logo is not a screenshot.
- Add demo video
Demo videoMissing
No demo video link is on this listing yet.
- Add pricing
PricingMissing
The pricing model is listed, but there is no starting price or pricing-page URL.
Use casesOn file
At least one use case is on the listing.
LinksOn file
At least one social or profile link is on file besides the website.
Optional HTML link
Paste this on your own site if you want to. It is not required, and it is not a rating or a review.
<a href="https://www.aiagentsinfo.com/directory/browser-use">Featured on AI Agents Info</a>
Pricing
The library is MIT licensed. The pricing page, read November 11, 2026, lists the open-source harness at $0 and cloud browsers at $0.02 per browser hour, with no monthly subscription. A home-IP proxy is $5 per GB. Your own proxy or a direct connection is $0.20 per GB.
Vendor pricing checked November 11, 2026.
Best fit
Libraries and harnesses for building agents: the loop, tools, memory, and permissions around a model. Listed use: agents. Listed audience: Builders.
Quick facts
- Category
- Agent frameworks & harnesses
- Pricing
- Open source, Paid
- Status
- Editorial
- Vendor
- Browser Use
- Last verified
- November 11, 2026
- Use
- agents
Features
- The agent writes Python against raw CDP instead of picking one action from a DOM dump
- Browser() starts a Browser Use Cloud browser. Browser('chromium') stays local
- MIT license on the GitHub repository, read November 11, 2026
- Exact dependency pins, including pydantic-ai-slim 2.66.0 on the 1.0.2 release
Pricing
The library is MIT licensed. The pricing page, read November 11, 2026, lists the open-source harness at $0 and cloud browsers at $0.02 per browser hour, with no monthly subscription. A home-IP proxy is $5 per GB. Your own proxy or a direct connection is $0.20 per GB.
Open source · Paid
Social
Browser Use 1.0 is a harness change, not a patch. GitHub published 1.0.0 at 2026-11-10T02:04:48Z. PyPI’s latest on the morning of November 11 was 1.0.2, and that release requires pydantic-ai-slim==2.66.0. The pins, the bench table, and the cloud-browser default are AI agent framework release November 2026.
The term for this kind of tool is browser use. Downloads through November 8, before 1.0, are Browser Use had 6,423,201 PyPI downloads. Desktop agents are Best computer use agents.
Tags
Alternatives
Other listings that share a category, use, or tag. Not a ranking.
- Google ADKGoogle
Same category, Agent frameworks & harnesses; also listed for agents.
- Microsoft Agent FrameworkMicrosoft
Same category, Agent frameworks & harnesses; also listed for agents.
- OpenAI Agents SDKOpenAI
Same category, Agent frameworks & harnesses; also listed for agents.
Directory
See where you rank
These are real pages on this site. Nothing here is a traffic count, a star rating, or a paid slot.
Category: Agent frameworks & harnesses
Best-of and comparison pages
Compare yourself with the top 3 in Agent frameworks & harnesses
Browser Use is not a row on Best AI agent harness yet. The first rows of that sourced table are below. Order is not a quality score. Last verified November 2026.
From our reports
Original reports, benchmarks, and notes on this site that discuss this product or its category.
Report
AI agents in the next 12 months (Nov 2026 to Nov 2027)What is already dated for AI agents from November 2026 through November 2027: coding agents, computer use, harnesses, and regulation, including the August 2027 EU sandbox date and the MCP deprecation window through July 2027. Checked November 7, 2026.
Benchmark
Agent harness benchmark, November 2026Agent harness benchmark for November 2026: public SWE-bench and Terminal-Bench scores for coding agents, each with the date on the official source.
Report
AI agents in the next 6 months (Nov 2026 to May 2027)What is already dated for AI agents from November 2026 through May 2027: coding agents, computer use, harnesses, and regulation. Checked November 5, 2026.