Computer use · agent platform
OpenBot: review, pricing, security and alternatives
OpenBot is an open-source agent platform published by CopilotKit, in the computer use family. A platform giving agents their own computer with a browser, files and tools while recording their actions. Its repository has 7,035 stars and its last commit is from October 24, 2026.
| Adoption (stars) | 22/40 | |
|---|---|---|
| Activity (commits, releases) | 30/30 | |
| Framework (licence, control, models) | 20/30 |
What OpenBot does
OpenBot belongs to the computer use family: agents that see the screen and drive the keyboard and mouse of a computer or phone. On our grid it ranks #5 of the 17 projects of this family listed in the directory.
You use it from: web app. It can run on your own machine or server.
Who is OpenBot for?
It is for people who want to automate desktop software with no API, by driving the screen as a person would. Typical tasks people give it:
- chain actions in legacy business software
- copy data from one application to another
- test a desktop application
It is a good candidate if you prefer doing everything in a browser, with no install and your data must stay on your machines.
Access and human control
According to its documentation, OpenBot can:
- drive a web browser
- read and edit files
- control the screen, keyboard and mouse
We could not establish whether it asks for human approval before sensitive actions: test it first on an unimportant account or folder.
OpenBot pricing
The code is free, under the MIT licence.
Getting started with OpenBot
- Install it: the project ships as a Node.js package (install with
npm, or run directly withnpx). The exact command is in the repository README. - Create an API key with the model provider and put it in an environment variable, never in a shared or versioned file.
- Give it a first playground with nothing at stake: a test folder, a secondary account or a throwaway project. Only open your real accounts once you have seen how it behaves.
- Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.
Security: risk level
An agent that controls the computer has the same rights as you: run it in a dedicated virtual machine.
Points found for OpenBot:
- Sensitive access: it can control the screen, keyboard and mouse, with no established default human approval.
- 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 August 17, 2026, the CopilotKit/OpenBot repository has 7,035 stars, 960 forks and 22 open issues, with 562 commits in total. It received changes this month.
Over the last 52 weeks: 561 commits, an average of 10.8 per week.
19 releases in total; 19 in the last twelve months. Latest release: v0.2.0, on October 12, 2026.
OpenBot vs other computer use
GitHub stars of the best-rated open-source projects in the computer use family. Stars measure attention, not quality: a heavily promoted project collects them fast, a specialised tool will have few.
OpenBot and other computer use 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 |
|---|---|---|---|---|---|
| OpenBot | open source | 72 | 7K ★ | yes | – |
| Midscene | open source | 81 | 15.4K ★ | yes | – |
| Cua | open source | 80 | 30.9K ★ | yes | – |
| Mobilerun | open source | 79 | 9.8K ★ | yes | – |
| GenericAgent | open source | 73 | 14.3K ★ | yes | – |
| UI-TARS Desktop | open source | 71 | 39.4K ★ | yes | – |
| OpenMausBot | open source | 71 | 5.5K ★ | yes | – |
| Observer | open source | 70 | 1.7K ★ | yes | – |
How we rated it
Score: 72/100, computed only from public, verifiable data, with no subjective testing or partnership:
- Adoption 22/40: 7,035 stars on a log scale (40 points from about 200,000).
- Activity 30/30: last commit less than a month ago, 19 releases in six months, 561 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
OpenBot is a serious option; check the limitations below before granting it access.
Strengths
- Very active development
- Frequent releases (19 in a year)
- Can run on your side: data under control
- Permissive licence (MIT)
Limitations
- Broad access without default approval
Avoid if…
- You cannot isolate it (container, virtual machine)
Alternatives
- Midscene15.4K ★
- Cua30.9K ★
- Mobilerun9.8K ★
- GenericAgent14.3K ★
- UI-TARS Desktop39.4K ★
- OpenMausBot5.5K ★
Learn more
Frequently asked questions
Is OpenBot free?
The software is free (MIT licence). You still pay for the model calls, unless you use a local model.
Is OpenBot safe?
Our risk level: high. Points found: sensitive access and outside content. Give it minimum rights and approve irreversible actions.
Which models does OpenBot use?
Its documentation does not specify the supported models.
Can OpenBot be installed on your own server?
Yes, from the CopilotKit/OpenBot repository. Data then stays with you, but security and updates are your job.
What are the alternatives to OpenBot?
In the same family: Midscene, Cua, Mobilerun, and GenericAgent.
OpenBot or Midscene: what is the difference?
Both belong to the computer use family. OpenBot has 7K stars against 15.4K for Midscene. 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