Want to prototype a voice-first desktop assistant without starting from an empty…
This is a dev post classified by Jev as Mobile & desktop (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Want to prototype a voice-first desktop assistant without starting from an empty Electron app? IRIS-AI is a public desktop AI assistant project for builders exploring voice input, desktop automation, and AI-powered utilities. It helps you study a desktop-assistant setup by combining a public Electron/React UI shell with documented integrations and extension points, while keeping the core orchestration layer private. Key features: • Voice-first interface – the README describes real-time, bidirectional audio processing through WebRTC • Desktop controls – documents workflows for opening apps,
Posted by Dan Kornas (99.2k followers) 44 min ago · 3 likes · 501 views · view the original post on X. Kept by the Dev Radar as Mobile & desktop.
More dev work like this
- Parallel React Native work gets messy fast. Stim keeps each agent in its own lane. — @DanKornas
- One CLI. More of your Windows app development lifecycle in one place. ⚡ — @windowsdev
- The Publishing Portal got a sweet update. — @solanamobile
- Teams can share plenty of code and still run iOS and Android as separate products. — @callstackio
- Aether another third party virtual machine as a universal native app for HarmonyOS… — @LivingInHarmony
- A new version of my "Retina Screenshot" plugin for Omarchy Linux is here! — @mark_k
- Cool to see my Expo UI examples auto-magically adapting to the iPhone Duo without any… — @nater02
- Desktop automation on macOS shouldn’t start with a pile of one-off scripts. — @DanKornas
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 21.4k posts from 5k X accounts over the last 21 days, 2.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 19:56 UTC. Full method.