Browser Use vs invisible_dots
Which should you use? A side-by-side look at what each one does, who it suits, what it costs, how hard it is to set up, and where each falls short.
Open source · MIT
Open-source Python library that lets an AI agent control a web browser to complete tasks.
Open source · MIT
Self-hosted AI agent that runs on its own virtual computer and browser, with permission controls.
The short answer
Choose Browser Use if you need…
- Python developers who want to prototype an AI agent that operates websites
- Teams automating repetitive multi-step web tasks such as lookups or form filling
- People who want to run the agent locally with their own LLM API key
- Users who need a cloud browser for environments without Chrome, such as Docker or CI
Choose invisible_dots if you need…
- Developers who want a self-hosted agent and are comfortable with a command-line setup
- People who want an agent to do recurring browser-based tasks on their own machine
- Users who want to control which tools the agent may use through allow, ask or deny permissions
- Hobbyists experimenting with local-first agent setups on Linux or Windows
Side-by-side
| Browser Use | invisible_dots | |
|---|---|---|
| Type | Library | AI model / agent |
| Price | Free and open source | Free and open source |
| Licence | MIT | MIT |
| GitHub stars | 120k | 32.4k |
| Setup difficulty | Intermediate | Intermediate |
| How you get it | Install with a package manager | Clone and build from source |
| Main language | Python | TypeScript |
| Last code update | 4 days ago | 6 days ago |
What each one is
Browser Use
Browser Use is a Python library that connects a language model to a web browser so an AI agent can click, type, and navigate pages to finish a task you describe in plain language. You can run it locally with your choice of model, or use a cloud browser service from the same project. The README's example task is looking up a repository's star count, and a demo shows the agent booking a driving test.
invisible_dots
invisible_dots is a self-hosted AI agent. You give it tasks in a chat, and it works on a virtual Linux computer it runs itself, with a Firefox browser that keeps its own logins. It can save notes and reusable steps, ask for your approval before sensitive actions, and run recurring jobs. The README says it is an alternative to commercial products such as OpenAI Dots and Grok Bot, and that it is built to avoid anti-bot detection.
Best for
Browser Use
- Python developers who want to prototype an AI agent that operates websites
- Teams automating repetitive multi-step web tasks such as lookups or form filling
- People who want to run the agent locally with their own LLM API key
- Users who need a cloud browser for environments without Chrome, such as Docker or CI
invisible_dots
- Developers who want a self-hosted agent and are comfortable with a command-line setup
- People who want an agent to do recurring browser-based tasks on their own machine
- Users who want to control which tools the agent may use through allow, ask or deny permissions
- Hobbyists experimenting with local-first agent setups on Linux or Windows
Strengths
Browser Use
- Works with a chosen LLM provider, and the README shows OpenAI as an example
- Same agent code runs locally or on a cloud browser with a single change
- MIT licensed and actively pushed
invisible_dots
- Self-hosted, with an MIT license and the code publicly available
- Permission controls let you approve or block each tool, and pending asks wait in an Inbox
- Tasks and messages are kept across restarts and crashes, according to the README
Not ideal for
Browser Use
- Non-programmers who want a no-code tool; the README's main path is Python code or an agent prompt
- Projects needing fully deterministic scripts, since the agent's behavior depends on a language model
- Anyone unwilling to pay for cloud browsers or manage API keys for the hosted options
invisible_dots
- Non-technical users, since setup requires Node.js, Go, Git, and a hardware-virtualization-capable CPU
- Anyone on hardware without x86-64 virtualization support, which the quickstart lists as required
- People who need a production-stable tool, since the badge in the README says status: alpha
- Anyone who wants to automate sites without permission, since the README's disclaimer asks users to respect site terms and robots.txt
Trade-offs
Browser Use
- Depends on a paid or API-keyed language model and, for cloud features, a Browser Use API key
- Cloud browser pricing and hosted features are described by the vendor and sit outside the open-source code
- The README is truncated, so some details of setup and configuration are not confirmed here
invisible_dots
- The README marks the project as alpha, so behavior may change or break
- Setup needs several tools and an OpenRouter API key, and it depends on hardware virtualization
- The README does not clearly explain how the anti-bot evasion claims are verified or their limits
Getting started
invisible_dots
Clone the repository
git clone https://github.com/feder-cr/invisible_dotsInstall dependencies
npm ciFrequently asked questions
What is the difference between Browser Use and invisible_dots?
Browser Use: Open-source Python library that lets an AI agent control a web browser to complete tasks. invisible_dots: Self-hosted AI agent that runs on its own virtual computer and browser, with permission controls. Browser Use suits python developers who want to prototype an ai agent that operates websites, while invisible_dots suits developers who want a self-hosted agent and are comfortable with a command-line setup.
Are Browser Use and invisible_dots free?
Browser Use: Free and open source. invisible_dots: Free and open source.
Is Browser Use or invisible_dots more popular?
Browser Use has more GitHub stars (120k) than invisible_dots (32.4k). Popularity isn't the same as fit — check which one matches your use case above.
What are other alternatives to Browser Use and invisible_dots?
Other options people compare them with include Stagehand, Browser Harness, CloakBrowser, Page Agent, LangGraph.
Keep comparing
Built from our catalogue entries for both products: open-source details come from each project's README (AI-assisted, refreshed weekly) and GitHub data; AI-tool details are editorial. Spotted something wrong? Let us know from either product's page.