Introducing frame.md, a spec built for videos & motion design.md kept your brand consistent across screens but when applied to videos, agents translated it back into webpages and decks frame.md teaches your agents how to make branded video turn your design.md into frame.md ↓ https://t.co/TZpTUBajhq
HeyGen releases frame.md to teach AI agents branded motion design
- Format
- Markdown .md
- Core Parameters
- Pacing, scale, dwell, and motion
- Input Support
- design.md translation
- Framework
- HyperFrames
- Availability
- Open source via GitHub
While the DESIGN.md standard helped agents follow brand rules, they often defaulted to static layouts like webpages. By adding a motion layer, HeyGen ensures agents understand how a brand moves, not just how it looks. This benefits systems like Hermes Agent that manage autonomous video production.
Users can upload a design.md file to the HyperFrames platform to generate a corresponding frame.md spec. This file directs compositions within the open-source HyperFrames framework. The specification is available via a web interface and GitHub for immediate use in agentic workflows.
Still wondering? A few quick answers below.
Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →


