Záboj
Voice AI for your car that gets things done
What it does
Záboj is a voice AI assistant for your car - CarPlay, iPhone and web. It answers in 30+ languages, searches the web and acts through your tools via MCP: calendar, email, Slack, CRM. Debrief a meeting while driving - the note and follow-up land on their own.
Talk while you drive and things get done - a meeting in the calendar, an email, a CRM note. Záboj understands 30+ languages, answers out loud and acts through your tools. CarPlay, iPhone and browser.
Záboj is a voice AI assistant for the car. It understands you in 30+ languages, answers out loud and acts on the spot - your hands stay on the wheel, your eyes on the road. Admin work eats about 21% of a salesperson's week - CRM entry most of all. Záboj handles it on the road: tell it how the meeting went and it finds the right deal in Pipedrive or Attio, logs the activity and drafts the follow-up. You just left the client. The details are fresh - and your hands are on the wheel. Say who you met and what you agreed on. Záboj asks about what matters and finds the record in your CRM. The activity lands on the right deal and a follow-up draft is waiting. Nothing to retype tonight. Log my…from zaboj.app
Does the same job
all alternatives →
Zavi AI - Voice to Action OS Feb 2026 · ▲152Voice that types, edits, sees and takes action in every app.
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 · 16d 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, 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 · 16d ago · simedw.com