motlab
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
- OpenMotion 0.2.0 adds seven studios for images, voice, video and 3D; plus LTX's SDR-to-HDR comparison, Kling Image 4.0 in ComfyUI and HyperFrames 0.9.72
- Claude Code Video Toolkit makes 3D character films in Blender from one JSON file; plus Higgsfield's Claude-built Blender cities, Mesh2Motion Release 14 and HyperFrames 0.9.73
- kinetograph renders Remotion and HyperFrames projects fast
- HyperFrames: HeyGen's bet that agents should write video as HTML
- GTA VI launch day turned stream clipping into an agent job: gtavi-claudecode, HyperFrames Stream Clips, PeakCut and Clips Kitty
Similar skills & repos
- Claude Code Video Toolkit · Skill, Code-to-video engine
- Kinetograph · Repo, Code-to-video engine
- story-to-handdrawn-video · Skill, Code-to-video engine
- kinetograph · Repo, Code-to-video engine
- free247editor · Skill, Code-to-video engine
- HyperFrames skills · Skill, Code-to-video engine