Browser agents · agent infrastructure component
CloakBrowser: review, pricing, security and alternatives
CloakBrowser is an open-source agent infrastructure component published by CloakHQ, in the browser agents family. CloakBrowser provides a modified Chromium browser compatible with Playwright for programmatic web browsing automation. Its repository has 32,455 stars and its last commit is from October 24, 2026.
What CloakBrowser does
CloakBrowser belongs to the browser agents family: agents that open pages, click, fill in forms and extract information in place of a human. On our grid it ranks #6 of the 21 projects of this family listed in the directory.
It is not an agent in itself: it is a component other agents use (memory, isolated execution, web access, model gateway or monitoring). You pick it based on the agent or framework it has to equip.
You use it from: developer SDK. It can run on your own machine or server.
Who is CloakBrowser for?
It helps people who spend time on websites without an API: it clicks, fills in and reads pages for you. Typical tasks people give it:
- fill in repetitive forms
- collect prices or information across several sites
- test a website's user flow
- fetch documents from a customer portal
It is a good candidate if your data must stay on your machines.
Access and human control
According to its documentation, CloakBrowser can:
- drive a web browser
We could not establish whether it asks for human approval before sensitive actions: test it first on an unimportant account or folder.
CloakBrowser pricing
The code is free, under the MIT licence.
Getting started with CloakBrowser
- Install it: the project ships as a Python package (install with
piporuv). The exact command is in the repository README. - Start with the minimal example from the docs, then add one tool at a time and check what the agent does with it.
- Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.
Security: risk level
Every page visited may hide instructions: do not leave a browser agent logged into sensitive accounts without action approval.
Points found for CloakBrowser:
- Outside content: it reads web pages or API responses, which may contain booby-trapped instructions (prompt injection).
Three habits: least privilege (minimal rights, dedicated keys), human approval for irreversible actions, a sandbox for code execution. The AI agent security check reviews your setup in a few minutes.
Project activity and releases
Created on February 22, 2026, the CloakHQ/CloakBrowser repository has 32,455 stars, 2,692 forks and 135 open issues, with 366 commits in total. It received changes this month.
Over the last 52 weeks: 362 commits, an average of 7 per week.
31 releases in total; 30 in the last twelve months. Latest release: chromium-v155.0.8059.39.1-pro, on October 20, 2026.
CloakBrowser vs other browser agents
GitHub stars of the best-rated open-source projects in the browser agents family. Stars measure attention, not quality: a heavily promoted project collects them fast, a specialised tool will have few.
CloakBrowser and other browser agents at a glance
The 7 best-ranked agents in the same family, 7 of them open source. The score out of 100 only applies to open-source projects; for proprietary services we show the published entry price. A dash marks information the documentation does not state.
| Agent | Model | Score | Stars or entry price | Self-hostable | Human approval |
|---|---|---|---|---|---|
| CloakBrowser | open source | 78 | 32.5K ★ | yes | – |
| Browser Use | open source | 92 | 119K ★ | yes | – |
| Stagehand | open source | 84 | 25.8K ★ | yes | – |
| Skyvern | open source | 83 | 23.3K ★ | yes | – |
| BrowserOS | open source | 81 | 14.1K ★ | yes | – |
| OpenCLI | open source | 80 | 30.6K ★ | yes | – |
| Invisible Dots | open source | 78 | 32.2K ★ | yes | – |
| Moli | open source | 78 | 20.5K ★ | yes | – |
How we rated it
Score: 78/100, computed only from public, verifiable data, with no subjective testing or partnership:
- Adoption 30/40: 32,455 stars on a log scale (40 points from about 200,000).
- Activity 28/30: last commit less than a month ago, 16 releases in six months, 362 commits in a year.
- Framework 20/30: licence, default human approval, self-hosting, model choice and documentation site.
The score does not say whether the agent will succeed at your tasks: it measures how solid the project is. The full grid is on the method page.
Verdict
CloakBrowser is a serious option; check the limitations below before granting it access.
Strengths
- Widely followed: 32.5K stars
- Very active development
- Frequent releases (30 in a year)
- Can run on your side: data under control
- Permissive licence (MIT)
Alternatives
- Browser Use119K ★
- Stagehand25.8K ★
- Skyvern23.3K ★
- BrowserOS14.1K ★
- OpenCLI30.6K ★
- Invisible Dots32.2K ★
Learn more
Frequently asked questions
Is CloakBrowser free?
The software is free (MIT licence). You still pay for the model calls, unless you use a local model.
Is CloakBrowser safe?
Our risk level: mid. Points found: outside content. Give it minimum rights and approve irreversible actions.
Which models does CloakBrowser use?
Its documentation does not specify the supported models.
Can CloakBrowser be installed on your own server?
Yes, from the CloakHQ/CloakBrowser repository. Data then stays with you, but security and updates are your job.
What are the alternatives to CloakBrowser?
In the same family: Browser Use, Stagehand, Skyvern, and BrowserOS.
CloakBrowser or Browser Use: what is the difference?
Both belong to the browser agents family. CloakBrowser has 32.5K stars against 119K for Browser Use. The right choice mostly depends on the access you are willing to give it.
Related articles
- Open source or proprietary AI agent: how to decideOctober 25, 2026
- AI agent vs. chatbot: what's the difference?October 24, 2026
- Autonomous AI agents: how much should you let them do?October 12, 2026
- AI agent memory: how agents remember (and forget)October 11, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score