... scores, apply in one undoable step. Also in this release - Visual footage search powered by local CLIP embeddings (shipped earlier this spring) - Thumbnail A/B testing and YouTube virality scoring - New model support: Sarvam AI, Smallest AI, Kimi K2, Google Gemma - Hardened upload endpoints, stabilized VPS deployment, and a repaired build/CI pipeline community contributions from @MikyJ05 and @interfluve-wav landed in this release. Open source works. Why it matters Every other "AI video editor" asks you to upload raw footage ...

... decide to launch product tomorrow. Launch URI: https://www.producthunt.com/prod... Description: [airespaker] considers AI respones as notes, storing them & managing them. Users can save AI responses copied from clipboard, loaded from cache or taken directly from Google Gemma model. Users can not modify saved AI responses but can delete them. Users can filter & display AI responses by code, AI and tags. The format of responses are quite beautiful. Users can query AI responses from cache or directly from ...

... Product Hunt I made a feature [ AI Response Cache Chatbot ] of [ airespaker ] AI Response Taker. Users can take AI response from system's cache, user's cache or directly from AI (Google Gemma). Users can take URIs of displaying AI response or screenshot of it. By tapping 'C' button, URI of displaying AI response is copied to clipboard. By tapping 'S' button, URI of screenshot of AI response is copied to clipboard. You can review new feature at: https://airespaker.is-best.net ...

... dark: Offline SOS distress signaling and location tools that don t need a network Global emergency numbers the right number for any country, no data required Survival guides in 10 languages first aid, shelter, water, signaling On-device AI (Gemma) ask survival questions with zero connection Privacy-first everything runs on your device. No servers, no account, no tracking. Airplane mode, a dead zone, a mountain pass with no bars it all still works. I d love your honest feedback ...

... your disk. No accounts, no cloud sync, no telemetry. If Folio disappears tomorrow, your manuscript is still just a folder of `.md` files. What v0.1.9 brings: - Panel-visibility settings (hide/show inspector, plan, AI panels per project) - Split IDE-wide vs. book-scoped settings (theme/font global, status flow per book) - Plan timeline + beats improvements for outliners - Smaller polish: status bar cleanup, settings gear moved out of the way The bigger picture (in case you're new to it): - Codex / world-bible ... ... characters, places, lore as Markdown entries with front matter. Wikilink-style chapter entry linking, quick-open. - On-device AI codex extraction runs a local Gemma

... Hunters We just shipped Google Gemma 4 support, paired with our TurboQuant KV-cache compression engine. That means you can now run Google's any-to-any multimodal models directly inside your editor no API keys, no cloud, no data leaving your machine. What's new in this drop: Full Gemma

... improvements based on your feedback: What s new in v1.2.0 Advanced Model Management browse, download, and delete local AI models directly in the app. Aside from LLama as its default, you can now download and use Qwen and Gemma as well Session Persistence your chats and filters now auto-restore on restart Export to Markdown turn your AI + log analysis sessions into shareable .md reports Saved Filters bookmark complex queries and load them instantly Live Stream Alerts get real-time ...

... chrismessina): @ryanfenwick  say the word! Happy to be your hunter ! Comment from derrick carvey(@doliver1966): I am amazed by the features and the improvements that you have made. Congratulations Comment from Chris Burke(@christoburke): Trust Cards has another alternative using Google Embedding Gemma