Computer use · AI agent
Andee: review, pricing, security and alternatives
Andee is an open-source AI agent published by KuafuAI, in the computer use family. An agent for phones and Macs that operates applications through their interfaces and keeps its memory on the device. Its repository has 2,728 stars and its last commit is from October 24, 2026.
What Andee does
Andee 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 #11 of the 17 projects of this family listed in the directory.
You use it from: mobile app and desktop app. Usable models: any OpenAI-compatible model. It can run on your own machine or server.
Who is Andee 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 your data must stay on your machines.
Access and human control
According to its documentation, Andee can:
- 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.
Andee pricing
The code is public but the repository declares no licence: reuse is not formally allowed. The real cost comes from model calls: each loop step sends the whole context back to the model, and a task of several dozen steps can cost far more than a single question. The LLM price calculator estimates it for the chosen model.
Getting started with Andee
- Install it by following the repository README (project written in Kotlin).
- 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 Andee:
- Sensitive access: it can control the screen, keyboard and mouse, with no established default human approval.
- No licence: legally shaky for company use.
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 September 17, 2026, the kuafuai/andee repository has 2,728 stars, 142 forks and 8 open issues, with 227 commits in total. It received changes this month.
Over the last 52 weeks: 204 commits, an average of 3.9 per week.
7 releases in total; 7 in the last twelve months. Latest release: v0.5.3, on October 22, 2026.
Andee 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.
Andee 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 |
|---|---|---|---|---|---|
| Andee | open source | 60 | 2.7K ★ | 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 | – |
| OpenBot | open source | 72 | 7K ★ | yes | – |
| UI-TARS Desktop | open source | 71 | 39.4K ★ | yes | – |
| OpenMausBot | open source | 71 | 5.5K ★ | yes | – |
How we rated it
Score: 60/100, computed only from public, verifiable data, with no subjective testing or partnership:
- Adoption 17/40: 2,728 stars on a log scale (40 points from about 200,000).
- Activity 28/30: last commit less than a month ago, 7 releases in six months, 204 commits in a year.
- Framework 15/30: 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
Andee is a serious option; check the limitations below before granting it access.
Strengths
- Very active development
- Frequent releases (7 in a year)
- Can run on your side: data under control
- Free choice of model
Limitations
- Broad access without default approval
- No licence declared
Avoid if…
- You cannot isolate it (container, virtual machine)
Alternatives
- Midscene15.4K ★
- Cua30.9K ★
- Mobilerun9.8K ★
- GenericAgent14.3K ★
- OpenBot7K ★
- UI-TARS Desktop39.4K ★
Learn more
Frequently asked questions
Is Andee free?
The software is public, with no declared licence. You still pay for the model calls, unless you use a local model.
Is Andee safe?
Our risk level: high. Points found: sensitive access and no licence. Give it minimum rights and approve irreversible actions.
Which models does Andee use?
According to its documentation: any OpenAI-compatible model.
Can Andee be installed on your own server?
Yes, from the kuafuai/andee repository. Data then stays with you, but security and updates are your job.
What are the alternatives to Andee?
In the same family: Midscene, Cua, Mobilerun, and GenericAgent.
Andee or Midscene: what is the difference?
Both belong to the computer use family. Andee has 2.7K 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