Cortex – OS-wide AI with instant context input
Hey HN! I’m Andrew, and I’ve been building Cortex (https://cortexdesktop.com/) for the last few weeks. Cortex is my attempt to reimagine how we interact with computers - starting with a simple interface, but aiming for something deeper: an AI layer over your OS that understands what you’re doing, remembers it, and helps you dynamically. Right now, Cortex is just a floating overlay you can summon anywhere on your Mac. It works like an inline ChatGPT, but it lets you instantly send that context into the chat by highlighting text - so you don’t have to explain what you’re doing.…
What it does
In the maker’s words, at launch
Hey HN! I’m Andrew, and I’ve been building Cortex (https://cortexdesktop.com/) for the last few weeks. Cortex is my attempt to reimagine how we interact with computers - starting with a simple interface, but aiming for something deeper: an AI layer over your OS that understands what you’re doing, remembers it, and helps you dynamically. Right now, Cortex is just a floating overlay you can summon anywhere on your Mac. It works like an inline ChatGPT, but it lets you instantly send that context into the chat by highlighting text - so you don’t have to explain what you’re doing. Here is a demo: https://www.youtube.com/watch?v=fZEbpysqH2w&feature=youtu.be That’s all it does today but the reason I’m building it is because I think that the current way we use computers is kind of antiquated - the OS is relatively dumb and memoryless. I feel like it would be so much better of an experience to work with a computer that is contextually and semantically smart. This started as a tool I was hacking together for myself while context-switching between projects, tabs, and apps. I was using ChatGPT a lot, but every time I wanted to ask something, I had to re-explain what I was doing. “I’m building this project with (these) specs, and (this) stack, help me plan etc etc” I realized that firstly, it was super tedious to constantly go back to GPT to query, and secondly that it was annoying that I constantly had to feed it context to make it work the way I wanted. Granted, Chat GPT does have a certain amount of memory nowadays but I mean something far more granular - file diffing, text changes, differences in entire workflows, etc. I feel that the OS should have memory. It should be able to understand semantically, not just react to commands. Eventually, I want Cortex to become the operating system’s memory. A system that watches what you do across apps (files, text, window titles, tabs), builds a real-time semantic timeline of your work, and lets you ask questions like “What was I working on Thursday before lunch?” Or say “Open the Figma file I was editing after that Zoom call”. I am technically getting ahead of myself, as right now I’m just trying to test the one use case of having access to AI anywhere in the OS. This is definitely an early-stage product. It’s glitchy in spots. But if you like trying new interfaces and imagining what comes next - I’d love your feedback. You can use it free for 7 days — no signup needed. I’d love to hear your feedback, ideas, critiques, or even thoughts on how you’d want your computer to "remember." Thanks! -Andrew
Does the same job
all alternatives →
Cortex by SKYNETLAB13d ago · skynetlab-cortex.com · ▲85The memory layer that decides what's worth remembering
- IFI feed all my daily entries to an AI (ChatGPT)2023 · ▲8
Hello there! I hope you're doing well today! I wanted to share something with you. Recently I was on the hunt for the best way to journal daily. Well, I had this idea - what if I could feed all my daily entries to an AI (ChatGPT), and create a friendly, supportive character like Socrates or Simon Sinek? This way, I could ask any questions about my life and mental health, and get some amazing advice on how to improve myself! The results have been absolutely mind-blowing ! I even made a short GIF to show you how it works - check it out! - https://gifyu.com/image/SdHLH I've…
- CACreated an AI for myself to achieve goals, it might help you guys tooJan 2026 · zropi.com · ▲6
I'm a Machine Learning engineer. Struggled with consistency for months on my goals, life etc, so I built something to help myself (zropi.com) but that surprised me or shocked me literally. It’s an AI companion that feels alive: chats like a person. Pauses, emotions, personality. Sends voice notes when it's excited about something or whenever it wants (has its like own mind). Shares photos of itself. But the memory It remembers EVERYTHING. Not just facts context, preferences, random things I mentioned. Last week I asked "how's that thing I told you about going?" and it knew exactly what I…
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 · 27d ago · cactuscompute.com
Launched alongside, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca