Skip to content

motlab

Type: SkillCategory: Code-to-video engine★ 192 (GitHub, when we checked)

motlab is an agent skill in our Code-to-video engine category. Stanyslaus Hary's MIT video-as-code engine (Nov 2026): each scene is a canvas page with renderAt(t), encoded to MP4 inside headless Chrome with WebCodecs (up to 4K). Ships agent skills for Claude Code, Codex, Cursor, Gemini CLI, Hermes and more that build scenes from your reference folder, a viewer where you leave notes on frames for the agent, and a motlab-assets skill for reusable icon/character/3D kits. Per the creator's single-scene benchmark, 2-4x faster than Remotion and HyperFrames on a GPU. Needs Node 24+, Chrome and ffmpeg.

Where it fits: HyperFrames, Remotion.

Listing isn’t endorsement. This is our summary of the project’s own docs. Check the licence and requirements at the source before you build on it.

Lab posts that cover motlab

Related Lab posts

Similar skills & repos