- Developers building agents that need to operate websites
- Teams prototyping browser automation before committing to a larger agent platform
- Researchers evaluating web task completion and browser action safety
MIT · Agents
browser-use
Open-source browser automation agent framework that makes websites accessible to AI agents.
88K stars 10.2K forks MIT license 2026-04-19 verified
$
pip install browser-use Open sourceSelf-hosted
Overview
What is browser-use?
browser-use is an MIT-licensed Python project for connecting AI agents to browser actions, making it useful for teams prototyping web automation, browser agents, and task execution over real websites.
Browser-first agent surface
browser-use focuses on making websites actionable for AI agents.
Most business workflows still cross web apps, forms, dashboards, and authenticated pages.Python developer workflow
The project is built for developers who want to compose browser automation into agent code.
A focused framework can be easier to adopt than a full agent operating environment.Strong fit for narrow automation tests
It is useful for validating whether a browser task can be represented as an agent workflow.
Narrow tests reveal site failures, credential needs, and reliability issues before a team scales automation. Install
One command to start
$
pip install browser-use Use cases
What teams use it for
Ecosystem
Tags & capabilities
Comparison
How it stacks up
Choose browser-use for browser automation primitives
vs full action-agent platformsOpenClaw and OpenHands cover broader agent workflows. browser-use is more focused when the core problem is browser operation itself.
FAQ
Questions
What should I check before using browser-use?
Start with one safe workflow for browser-use. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.
Is browser-use open source?
browser-use is listed with MIT based on the official source links in this profile. Re-check the repository, model card, or docs before production use.
Who should evaluate browser-use?
browser-use is most worth evaluating for developers building agents that need to operate websites.
Is browser-use the same as a full agent platform?
No. It is more focused on browser automation. You may still need memory, scheduling, permissions, and workflow orchestration around it.
Decision brief
JSON
Should you use browser-use?
- Users who want a complete no-code automation product
- Teams that cannot manage credentials, browser sessions, and site-specific failure cases
- Verified 2026-04-19
- License: MIT
- Repo: browser-use/browser-use
- Open-source signal
Deployment
self hosted, cloud
Permission surface
browser
Decision signals
Self-hostable
Agent packet
Structured decision data for browser-use
This packet is the compact machine-readable view agents should use before following source links or taking action.
Capabilities
browser automation, browser, workflow orchestration, tool calling
Constraints
open source, self hosted
Deployment
self hosted, cloud
Permission surface
browser
Recommended workflows
Browser automation, Coding agent workflow
Overview
What browser-use does
What it is
browser-use is an open agent resource to evaluate by action surface: what software it can operate, which tools or browser steps it touches, and how much supervision it needs before it can run real work.
Why it matters
If action agents are going to be useful, they need to work where real work happens. Browser-based systems are still the front door to many tools, CRMs, dashboards, stores, and internal apps. browser-use is useful because it isolates that problem and lets teams test it directly.
How to evaluate it
Start with one safe workflow for browser-use. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.
Facts
Known metadata and operating surface
These fields are separated from editorial interpretation so agents can reason over facts and missing checks.
Resource type agent
Category Agents
Maturity active
Difficulty Unknown
License MIT
Pricing open source
Verified 2026-04-19
Source confidence high
Risk level elevated
Fit matrix
Where browser-use fits in an agent stack
strong
Browser automation
browser-use has multiple signals for browser automation, including matching tags, capabilities, category, or positioning.
- Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
strong
Coding agent workflow
browser-use has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning.
- Run a small repository change and inspect the diff, tests, and rollback path.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial
Evaluation and observability
browser-use has at least one signal for evaluation and observability, but should be checked against a real task before adoption.
- Add one repeatable test case and confirm results can run again in review or CI.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial
Local or private AI stack
browser-use has at least one signal for local or private ai stack, but should be checked against a real task before adoption.
- Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial
Reusable skill workflow
browser-use has at least one signal for reusable skill workflow, but should be checked against a real task before adoption.
- Run one skill end to end and check whether it produces evidence or structured output.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
weak
Connector or protocol layer
browser-use is not primarily positioned for connector or protocol layer in the current metadata.
- Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
Inputs and outputs
What an agent should inspect
Likely inputs
- Web pages, DOM state, screenshots, forms, or browser sessions
- Repositories, files, issues, terminal output, and test results
- Official setup instructions and a small real workflow
Likely outputs
- Action traces, changed pages, extracted data, or completed browser steps
- Diffs, commits, explanations, test results, or review notes
- Scores, traces, regression results, dashboards, or failure cases
- A decision on whether this resource fits the target workflow
Evidence
Sources, claims, and missing checks
Claims are marked separately from source links so future crawlers and reviewers can update them without rewriting the page.
GitHub github
Repository source for code, license, issues, releases, and implementation details.
Homepage homepageOfficial or project-controlled source for this resource profile.
Docs docsDocumentation source for setup, API shape, and operational behavior.
browser-use is listed as open source.
License metadata: MITbrowser-use has a recorded GitHub repository: browser-use/browser-use.
Resource facts and GitHub source link.browser-use supports these recorded deployment modes: self hosted, cloud.
OpenAgent decision signal metadata.browser-use is tagged with browser automation, browser, workflow orchestration, tool calling capabilities.
OpenAgent capability taxonomy.- Repository freshness has not been recorded.
Next action
How to start evaluating browser-use
Inspect repository
Check license, recent activity, issues, examples, and security-sensitive code paths.
Open sourceOpen Homepage
Start from the official source before adopting third-party instructions.
Open sourceRead setup docs
Use docs as the source of truth for installation and supported interfaces.
Open sourceInstall browser-use
Use the official package path, then follow the docs for model provider and browser setup.
pip install browser-use Compare
Alternatives and nearby resources
Use related resources to compare category fit, license, deployment model, and first-workflow behavior.
FAQ
Common questions about browser-use
What should I check before using browser-use?
Start with one safe workflow for browser-use. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.
Is browser-use open source?
browser-use is listed with MIT based on the official source links in this profile. Re-check the repository, model card, or docs before production use.
Who should evaluate browser-use?
browser-use is most worth evaluating for developers building agents that need to operate websites.
Is browser-use the same as a full agent platform?
No. It is more focused on browser automation. You may still need memory, scheduling, permissions, and workflow orchestration around it.
Who should try browser-use?
Developers who need to test whether web tasks can be represented as reliable AI agent workflows should start here.