Nao
7.2K posts

Nao
@NaoThread
Tu scroll, j’analyse Tech • IA • business 1 thread/jour 📩 Collab en DM





Introducing Buzzy's vibe video agent! Stop typing your prompt anymore! With Buzzy's vibe agent, scrolling social media is the new prompt. Infinite inspiration powered by an agent that learns your taste, helps you scale your creations, and lets you refine your content to perfection with AI video editing. Buzzy is beyond the prompt box: it's system that thinks with you.

Introducing Buzzy's vibe video agent! Stop typing your prompt anymore! With Buzzy's vibe agent, scrolling social media is the new prompt. Infinite inspiration powered by an agent that learns your taste, helps you scale your creations, and lets you refine your content to perfection with AI video editing. Buzzy is beyond the prompt box: it's system that thinks with you.











Your next campaign? It's one prompt away. Meet Campaign Director — the end of "AI tools" and the start of AI campaigns. 🎬 Forget stitching together five apps to make one reel. Forget casting calls, revision loops, and three-week timelines. Forget "good enough" outputs that still need a designer to fix. Type your brief. Walk away. Come back to a finished campaign. ✦ AI influencers so real you'll double-take ✦ Cinematic video with actual direction — shots, pacing, movement ✦ Your brand, locked in across every frame ✦ Audio that actually matches the vibe No casting. No editing marathons. No "we'll fix it in post." Just a brief in → a campaign out. Ready to publish. Ready to perform. Built for the people shipping content weekly, not quarterly. The piecemeal era is over. This is what comes next.

Every product team has a 30-line file in their codebase called pick_model.py. Nine if/else branches. Three retry decorators. A hardcoded fallback to gpt-3.5. A comment that reads "TODO: this should not exist." We open-sourced OrcaRouter-Lite, a self-hosted LLM router with a prompt cache that works on every provider you plug in — OpenAI, Anthropic, Google, Groq, anything. Your keys. Your cache. MIT. • OpenAI-compatible drop-in (any SDK) • BYOK, single workspace, no Postgres/Redis required • model="auto" → cheapest capable model per request • Send the same deterministic request twice → second call returns in milliseconds for $0 • 100+ models, 127 tests docker compose up and you're routing. github.com/Continuum-AI-C… Hosted version drops later this week.



