- Home
- AI Computer Use Agents
- Computer Use OOTB
Computer Use OOTB
What it is
Computer Use OOTB is an open-source framework for automating tasks through a computer’s graphical interface. It works with API-based or locally running models and supports Windows and macOS. Its Gradio interface does not require Docker, and users can configure one model or separate models for planning and computer control. Model options include Claude 3.5 Sonnet, GPT-4o, Qwen models, ShowUI and UI-TARS. Local inference can avoid API costs, though a task using Claude 3.5 Computer Use may cost a few dollars. Setup requires Miniconda, Python 3.12 or newer, and dependency installation. ShowUI local runs call for a CUDA-enabled NVIDIA GPU with at least 6 GB of memory on Windows, or an M1-or-newer Apple Silicon Mac with at least 16 GB unified RAM. A mobile browser can send commands to the computer running the software. The project is licensed under Apache-2.0. Its authors warn that models may take harmful actions and that anyone with a generated public Gradio link may be able to control the computer.
For and against
For
- Free and licensed under Apache-2.0
- Supports API-based and local models
- Mobile browser can send commands to the computer
- Gradio interface does not require Docker
Against
- Setup requires Miniconda and Python 3.12 or newer
- ShowUI local runs have specified hardware requirements
- A public Gradio link may let others control the computer
- Claude 3.5 Computer Use tasks may cost a few dollars
The verdict
Computer Use OOTB offers model-based desktop automation with API and local options. Setup requirements, local-model hardware needs, and the public-link warning are important to weigh before using it.
Who it suits
It suits users who want to automate desktop or browser tasks on Windows or macOS and can install the required tools. Users considering local ShowUI runs should have the specified hardware.
Plans and prices
Open-source software
Apache-2.0 license · API-based or locally running models · Windows and macOS
Read 9 Oct 2026 · github.com
On the record
- Cost limit
- The README says a Claude 3.5 Computer Use task may cost a few dollars; local models can run without API costs.github.com · read 9 Oct 2026
- Installation
- The README instructs users to install Miniconda, use Python 3.12 or newer, install dependencies and start the interface with python app.py.github.com · read 9 Oct 2026
- Integrations
- The documented API model keys include Anthropic, OpenAI and Qwen; local model setup also references PyTorch and UI-TARS deployment options.github.com · read 9 Oct 2026
- Interface
- It provides a Gradio interface that runs locally and can be accessed through a browser.github.com · read 9 Oct 2026
- License
- The repository identifies its license as Apache-2.0.github.com · read 9 Oct 2026
- Local inference
- The README says local models can run on the user's device with no API costs.github.com · read 8 Oct 2026
- Local model hardware
- For ShowUI local runs, the README lists a CUDA-enabled NVIDIA GPU with at least 6 GB of GPU memory on Windows, or an M1-or-newer Apple Silicon Mac with at least 16 GB unified RAM.github.com · read 8 Oct 2026
- Local model requirements
- For ShowUI local runs, the README specifies a CUDA-capable NVIDIA GPU with at least 6 GB GPU memory on Windows or Apple Silicon M1 or newer with at least 16 GB unified RAM on macOS.github.com · read 9 Oct 2026
- Maker affiliation
- The project page identifies its authors with ShowLab at the National University of Singapore.computer-use-ootb.github.io · read 9 Oct 2026
- Model options
- The project supports API-based models and locally running models, including Claude 3.5 Sonnet, GPT-4o, Qwen models, ShowUI and UI-TARS.github.com · read 9 Oct 2026
- Model roles
- Users can configure a unified model or separate planner and actor models for high-level planning and low-level control.github.com · read 9 Oct 2026
- Models
- The README lists Claude 3.5 Sonnet, GPT-4o, Qwen models, ShowUI, and UI-TARS among supported GUI agent models.github.com · read 8 Oct 2026
- Operating systems
- The README lists Windows and macOS as supported systems.github.com · read 8 Oct 2026
- Public link risk
- The README warns that anyone with the generated public Gradio link may be able to control the computer and says not to share it.github.com · read 8 Oct 2026
- Purpose
- Computer Use OOTB is an out-of-the-box GUI agent framework for automating desktop tasks with API-based and locally running models.github.com · read 8 Oct 2026
- Remote access
- A user can issue commands from a mobile browser to control the computer running OOTB, without installing a mobile app.github.com · read 8 Oct 2026
- Remote access risk
- The README warns that anyone with a public Gradio link may be able to control the computer and says not to share that link.github.com · read 9 Oct 2026
- Remote control
- A device with internet access, including a mobile browser, can send commands to the computer running the software.github.com · read 9 Oct 2026