#163 · Primary category: Video & Animation

FableCut

ai-agent canvas claude ffmpeg javascript llm mcp nle reels video-editing video-editor zero-dependency

Zero-dependency browser video editor that AI agents can drive — JSON timeline, MCP + REST, live-reloading UI

Project last updated:08/28/26

GitHub Stars

643

Forks

68

Contributors

10

License

MIT

Why we included this project

FableCut is worth a look if you build workflows where an AI agent needs to produce finished video rather than just text. It's a full non-linear editor that runs in the browser with no npm dependencies, and the entire timeline is exposed as a single JSON document. The interesting part is that any process that can write JSON can drive it, whether through the built-in MCP server, a REST call, or direct file editing. Agents can cut, trim, and arrange clips, and the open UI hot-reloads so you watch the edit happen live. Teams prototyping agent-driven content pipelines or automated social reels will find a concrete, inspectable way to hand editing control to a model while a human can still work on the same timeline. It's a practical bridge between LLM tool use and real video production.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category