Local
Zero (!) friction local AI for your Mac
What it does
Local is a macOS app that runs fully private AI directly on your own machine. We built it for completely frictionless setup. It tunes itself to your hardware, so chat, coding agents and meeting notes run up to 5.4x faster on the same hardware, without your data ever leaving the device. No cloud. No accounts. No cost. "Office Mode" let's you run AI on the fastest machine in the office and every laptop can connect to it.
Local is a macOS app that runs AI on your own machine. It tunes itself to your chip with BaseRT, so chat, coding and meeting notes run faster on the same hardware, without your work leaving the device.
Local : AI that runs on your machine. No cloud, no accounts, zero $ per token. Ask questions, draft writing, drop in a PDF and get it summarised. Point it at a project and it reads, edits and runs code in place. Your codebase is never uploaded. A short list of lasting facts about you, all of it visible and editable. Mark one sensitive and it never leaves the Mac. Local reads your chip and memory, then recommends what to run. Tokens, speed per model, and what the same work would have cost through a cloud API. One device does the work, the office shares it. Run the big model on the most capable machine you own and reach it from Local on every laptop in the room. Some jobs want a frontier…from basecompute.co
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 · 27d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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