Back to directory

FireRed-OpenStoryline

An AI video-editing agent that turns natural-language directions into edited video, planning shots, generating scripts and applying reusable editing styles.

FireRed-OpenStoryline

FireRed-OpenStoryline is an AI agent for video editing that works through natural-language conversation instead of manual timeline editing. It searches for and downloads matching images and video clips, segments and understands the footage it is given, and combines a user's theme with visual understanding and emotion recognition to construct storylines and narration, including few-shot style transfer that replicates the tone and rhythm of a reference text.

It also recommends background music, voiceovers and fonts based on a described mood, generates transitions between clips from their start and end frames plus a natural-language description, and lets a user rapidly cut, swap or resequence clips and adjust visual details conversationally. A completed editing workflow can be saved as a reusable Style Skill and reapplied to new media for consistent output.

It is written in Python, uses LangChain and MCP, and is released under the Apache 2.0 license.

More in Generative media

See all 146
  • Blender Copilot

    github.com

    A Copilot-style AI chat panel inside Blender that runs its agent loop in Blender's own Python process, executes the model's generated code against the live scene, and wraps every conversational turn in a single undo step.

  • A ComfyUI add-on that patches ComfyUI-GGUF so Qwen-Image-2.1 models can run fully as GGUF files, fixing a text-encoder mismatch and missing architecture detection until upstream support arrives.

  • A ComfyUI node that expands a short prompt into a full styled prompt, negative prompt and aspect ratio for Qwen-Image-2.1, using one of 17 photographic styles.