Oval
Native macOS client for your self-hosted Open WebUI
What it does
Oval is a native macOS client for your self-hosted Open WebUI. Instead of running AI in a browser tab or Electron wrapper, Oval provides a fast and private experience built specifically for macOS. It supports streaming markdown chat, voice mode with on-device Whisper STT and Piper TTS, quick access via Ctrl+Space (like Spotlight for AI), web search, citations, and tool calls. Open source (GPL-3.0), no analytics, and all traffic goes directly to your own server.
Does the same job
all alternatives →- GPGhost Pepper – Local hold-to-talk speech-to-text for macOSApr 2026 · github.com · ▲467
I built this because I wanted to see how far I could get with a voice-to-text app that used 100% local models so no data left my computer. I've been using a ton for coding and emails. Experimenting with using it as a voice interface for my other agents too. 100% open-source MIT license, would love feedback, PRs, and ideas on where to take it.
- AMA macOS Client for HuggingFace Chat2024 · github.com · ▲108
- OAOliphaunt – A native Mastodon client for macOS2025 · testflight.apple.com · ▲105
I’ve been building Oliphaunt, a native Mastodon client for macOS, as a solo project — designed to be fast, lightweight and feel right at home on the Mac. It’s not built with Catalyst or Electron framework. Key features: • Native macOS UI using AppKit with some SwiftUI integration (not a web wrapper) • Core Data for local caching • Responsive, keyboard-friendly interface • UX tailored for desktop-class Mac computers • Supports multiple accounts, cross-instance timelines and search You can try it via TestFlight (macOS 14+ Sonoma): https://testflight.apple.com/join/Epq1P3Cw…
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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
