# FireRed OpenStoryline

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

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.

* Page: https://agentcut.dev/tools/firered-openstoryline/
* Source: https://github.com/FireRedTeam/FireRed-OpenStoryline
* Works with: Agent native editors
* Type: Open-source editor (MCP)
* Setup difficulty: hard
* Supported versions: Python 3.11 recommended; macOS, Linux and Windows; Docker image available
* Price: free
* License: Apache-2.0
* GitHub stars: 3536
* Last updated: 2026-07-31
* Checked: 2026-10-19

Setup steps:

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.

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.

More Agent native editors tools: https://agentcut.dev/ai-video-editors/

---
AgentCut: https://agentcut.dev/ · All tools as JSON: https://agentcut.dev/tools.json · Overview for agents: https://agentcut.dev/llms.txt