Radar / AI media tools / HyperFrames
HyperFrames
HeyGen's open-source framework that turns HTML/CSS/GSAP into deterministic MP4 video via 21 agent skills and a router skill - video rendering built for AI coding agents.
Why it matters
Video is the new docs-to-video pipeline: agents author plain HTML and get broadcast-grade renders; HeyGen open-sourced it, and it's #9 on GitHub trending today with 54k stars.
What you could build with it
A docs team could turn markdown docs into release videos automatically: an agent authors HTML compositions from changelogs and renders deterministic MP4s in CI.
Does it hold up?
Proven in production by its own creators - the website-to-hyperframes launch video was rendered entirely with it (deterministic, frame-for-frame reproducible); third-party writeups confirm the init/preview/render CLI loop works, though heavy compositions take minutes on a laptop.
Built with HyperFrames
- website-to-hyperframes-demo: launch video built entirely with HyperFramesgithub · 41.8s 1080p30 launch video - HTML compositions plus GSAP plus captured clips, rendered deterministically with npx hyperframes render.
- HyperFrames deep-dive writeupgithub · Third-party deep dive into HyperFrames' composition model and deterministic rendering pipeline.
- Write HTML, Not JSON: HeyGen's Visual-Grounding Trickmedium · Analysis of HyperFrames' HTML-as-canvas design and why it suits LLM visual grounding.
- heygen-com/website-to-hyperframes-demogithub · 71 ★ · Official demo: full launch video authored as HTML compositions.
- liu294100/code-doctor-skillsgithub · 6 ★ · Third-party agent skills repo integrating HyperFrames for html2video.
- js0980420/code-to-video-hyperframesgithub · 1 ★ · Community repo building code-to-video workflows on HyperFrames.
Learn more
First spotted on github: source.
More AI media tools
Meshy crosses $100M ARR and launches official iOS/Android appsMeshy announced Sep 30 that ARR surpassed $100M (up 100x in under two years, first AI-3D company at that milestone)…media · JEV 0.61Tencent Hy Image 3.5 PreviewTencent's latest image model with multi-turn conversational editing, direct 4K output, and up to 20 reference images.media · JEV 0.43PixVerse R2: real-time world model with persistent, playable worldsUpgrade to PixVerse's real-time world model: a generated world keeps running live, remembers earlier user actions, and…media · JEV 0.4Hunyuan3D World Model 1.0Open-source model generating explorable, interactive 360-degree 3D worlds from text or image input.media · JEV 0.38Qwen-Image-2.17B open-weights image model with unified text-to-image generation and editing, day-0 Diffusers and ComfyUI support.media · JEV 0.34Airbrush Studio: AI portrait retouching desktop appAirbrush launched a free desktop photo editor (Windows/Mac) with one-click AI portrait tools: open-eye fix for group…media · JEV 0.24
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.