FireRed OpenStoryline

Solves Turning a pile of clips into a scripted, scored short video by chatting, then refining it

Works with
Agent native editors
Setup
Hard setup
Price
Free
Type
Open-source editor (MCP)

View on GitHub → How to set it up

Helps with cut silences and rough cuts, turn long videos into shorts

Ideas to try

Ideas to try

These are our ideas, not reports from real users. We haven't found a public example of someone using this tool yet. Know one?

  • Ask for a conservative first pass that keeps full sentences, then send notes with timestamps for the parts that still drag
  • Save the rules that worked in a short text file so the next video starts from your style
  • Give the agent shot rules: full screen face for punchlines, split screen for explanations, screen capture when the screen matters

What it does

Open-source AI video editing agent you talk to: it finds and organizes clips, writes a script and narration, suggests music, voiceover and fonts, and lets you cut, swap and restyle clips by chat. Includes a speech rough cut skill that removes filler words and repeated sentences, and lets you save an edit style as a reusable skill. Runs as an MCP server with a CLI or web chat.

The project describes itself as: "FireRed-OpenStoryline is an AI video editing agent that transforms manual editing into intention-driven directing through natural language interaction, LLM-powered planning, and precise tool orchestration. It facilitates transparent, human-in-the-loop creation with reusable Style Skills for consistent, professional storytelling."

How to set it up

  1. Clone the repo and create a Python 3.11 environment (the README suggests Conda/Miniforge).
  2. Run sh build_env.sh on macOS or Linux, or follow the manual download steps on Windows. Docker is an alternative.
  3. Add your API keys to config.toml.
  4. Start the MCP server with PYTHONPATH=src python -m open_storyline.mcp.server.
  5. Open the chat with python cli.py, or the web interface with uvicorn, and describe the video you want.

This is a plain English summary of the project's own instructions. Commands and versions change, so always follow the current README at the source link

Safety notes

  • You must add API keys to config.toml before the first run (see the project's API key doc).
  • The AI transition feature calls third-party video generation services and the README warns the cost is relatively high.
  • It can search online and download images and clips for you, so check the rights before you publish.

General rule: open a duplicate of your project before letting any agent make changes, and read what a script does before approving it

Other tools for cut silences and rough cuts

MCP Bridge for Adobe Premiere Pro

Solves Cutting pauses, building rough cuts and doing timeline busywork in Premiere by asking an AI

Premiere Pro

Medium setupFree2 real examples

SmartCut MCP (CapCut talking-head)

Solves Cutting silences and repeated takes out of talking head videos in CapCut

CapCut

Medium setupFree
 Demo clip

FCPXML MCP

Solves Rough cuts, markers and timeline checks in Final Cut Pro through FCPXML

Final Cut Pro

Easy setupFree

Wasserman's Unofficial DaVinci MCP

Solves Cutting to the beat, tightening dialogue and hitting loudness specs in Resolve, even on the free version

DaVinci Resolve, FFmpeg

Medium setupFreeFree + Studio
 Demo clip

ffmpeg-skill

Solves Captions, 9:16 crops, silence removal and exports done on your own computer by an AI

FFmpeg

Easy setupFree1 real example

EditAssist (MCP)

Solves Searching transcripts and footage and assembling rough cuts inside your editor

DaVinci Resolve, Premiere Pro, After Effects, Final Cut Pro

Easy setupPrice unclear

Compare all 7 Agent native editors tools →

The AgentCut weekly

New AI connectors for After Effects, Premiere, Resolve and CapCut, tested setup notes, and what broke after app updates. One email a week.