Skylight – Run computer-use agents on Windows VMs
Hey all! We're Skylight, a team founded by Maria (DeepMind Scholar in AI) and Adam (PhD researcher focused on LLMs). We’re building Windows virtual machines that can be operated by computer-use agents (CUAs). You can spin up persistent Windows instances in seconds and operate them with CUAs. We’ve created a built-in agent, or you can plug in your own with the API + SDK. Skylight works best to automate apps and legacy software that don’t have APIs, such as Microsoft Office and ERP systems. We built this because deploying CUAs in production is way harder than it should be, and we packed in all…
What it does
In the maker’s words, at launch
Hey all! We're Skylight, a team founded by Maria (DeepMind Scholar in AI) and Adam (PhD researcher focused on LLMs). We’re building Windows virtual machines that can be operated by computer-use agents (CUAs). You can spin up persistent Windows instances in seconds and operate them with CUAs. We’ve created a built-in agent, or you can plug in your own with the API + SDK. Skylight works best to automate apps and legacy software that don’t have APIs, such as Microsoft Office and ERP systems. We built this because deploying CUAs in production is way harder than it should be, and we packed in all the things we needed ourselves: - Persistence – pause and resume VMs without losing progress - Interactive Live Streaming – watch agents work in real time and take control if needed - Multiple Instances – run multiple VMs at once and coordinate across them - File Downloads – pull files from VMs to your local machine - Knowledge Base – agents retain context of past actions - Human-in-the-Loop – guardrails for important and irreversible actions If you need to run agents that use desktop software (not just browsers), come check us out (for free).
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
