Hey HN! We've just open-sourced Agent, our framework for running computer-use workflows across multiple apps in isolated macOS/Linux sandboxes.After launching Computer a few weeks ago, we realized many of you wanted to run complex workflows that span multiple applications. Agent builds on Computer to make this possible. It works with local Ollama models (if you're privacy-minded) or cloud...
Also, appreciate you linking the previous discussion! We'll make sure to address common questions more clearly in our docs and updates.
https://github.com/trycua/computer
We just open-sourced Computer, a Computer-Use Interface (CUI) framework that enables AI agents to interact with isolated macOS and Linux sandboxes, with near-native performance on Apple Silicon. Computer provides a PyAutoGUI-compatible interface that can be plugged into any AI agent system (OpenAI Agents SDK , Langchain, CrewAI, AutoGen, etc.).Why Computer?As CUA AI agents become more capable,...
https://github.com/trycua/pylume
Building on the momentum of lume, we’re excited to share pylume, a new Python library that makes it easier to manage macOS and Linux virtual machines (VMs) on Apple Silicon directly from your Python code.pylume extends lume's command-line functionality to Python, giving developers the ability to integrate VM management into their Python scripts or applications.Why pylume?While lume makes...
We're currently working out the details. It was left out of the initial release, but it’s feasible starting from a Windows on ARM image. I'll create an issue to track this work. Thanks for the feedback!
Interestingly, we left out the screenshot and exec features from this initial release so the CLI wouldn’t get too cluttered. We’re rolling out another update next week that will let you request screenshots programmatically, stream the VNC session in your browser via noVNC, run commands remotely over SSH, add clipboard support (finally!), and more.
As for cloning, you can indeed clone a running VM. However, suspending a VM isn’t supported in this release yet, even though it’s possible with the Apple Virtualization.framework. I’ll open an issue to track that work. Thanks again for the suggestions!
I'll definitely document the option in the README, thanks!
On Lima:
- Lima focuses on Linux VMs and doesn't support managing macOS VMs.
- It is more of a container-oriented way of spinning up Linux VMs. We're still debating whether to go in that direction with lume, but the good news is that it would mostly require tweaking the hooks to expose lume’s core to adopt the containerd standard. I’d love to hear your thoughts - would you find it useful to have a Docker-like interface for starting macOS workloads? Similarly to: https://github.com/qemus/qemu-docker
- Still many dependencies on QEMU, which doesn't play well with Apple silicon - while we opted to support only M chips (80-90% of the market cap today) by relying on the latest Apple Virtualization.Framework bits.
On Tart:
- We share some similarities when it comes to tart's command-line interface. We extend it and make it more accessible to different frameworks and languages with our local server option (lume serve). We have also an interface for python today: https://github.com/trycua/pylume
- Going forward, we'd like to focus more on creating tools around developers, creating tools for automation and extending the available images in our ghcr registry. Stay tuned for more updates next week!
- Lastly, lume is licensed under MIT, so you’re free to use it for commercial purposes. Tart, on the other hand, currently uses a Fair Source license.