Russet

What it does

Russet elevates local AI to a 1st-party experience on Apple silicon. It combines Apple Intelligence and hardware-optimized MLX models with pre-configured tuning and simple interfaces like Flow which summarizes, translates, and debates input text. Agent tools sync with your calendar, contacts, and files, while Speech (Mac-only) lets you generate natural, expressive speech in custom voices. Like its namesake russet potato, Russet is the reliable and versatile AI staple you can always count on.

• 
  Thinkbuddy AI2024 · thinkbuddy.ai · ▲725

  Native ChatGPT for MacOS

• 
  Raycast AI2023 · ▲621

  The magic of AI, right on your Mac

• 
  Aident AIDec 2025 · aident.ai · ▲324

  Build automations with natural language, not workflows

• 
  Parrot Speech-to-text APIMay 2026 · ringg.ai · ▲194

  Fast, accurate STT for production-grade voice agents

• 
  Chat by Copy.ai2023 · ▲463

  A smarter ChatGPT to help you get more done

• 
  Baron AI2023 · ▲332

  Use ChatGPT in any app, natively on Windows, Mac and Linux

• 
  I trained a 125M model to autocomplete piano on-device▲598

  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 · 18d ago · simedw.com

• 
  Astute▲585

  Automate your B2B brand going viral, with new media creators

  AI · 19d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 26d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  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

• 
  Monid▲475

  One wallet, every paid tool your agent needs

  AI · 7d ago · monid.ai

• 
  Clara AI SDR▲460

  Turn website visitors into qualified pipeline

  AI · 20d ago · clarasdr.ai

• 
  Lightfield▲891

  AI-native CRM that builds itself and does work for you

  AI · Mar 2026 · lightfield.app

• 
  Tobira.ai▲730

  A network where AI agents find deals for their humans

  AI · Mar 2026 · tobira.ai

• 
  Claude Import Memory▲725

  Switch from ChatGPT to Claude with import memory feature

  AI · Mar 2026 · claude.com

• 
  Littlebird▲712

  The AI assistant that already knows your work

  AI · Mar 2026 · littlebird.ai

• 
  Viktor.com▲701

  Your AI Coworker that proactively executes tasks

  AI · Mar 2026 · viktor.com

• 
  Jupid▲664

  File your taxes with Claude Code

  Commerce · Mar 2026 · jupid.com