#9696th of 102 in Agent platformsFor image, video and design, video and animation

firered-openstoryline

Chat-driven video editor that finds media, writes scripts, adds music and voiceover

Stars
3.7k
License
Apache-2.0
Last commit
Jul 2026
Language
Python
Stars, last 29 weeks+1,546
25 Apr 2026: 2,160 stars2 May 2026: 2,373 stars9 May 2026: 2,544 stars16 May 2026: 2,636 stars23 May 2026: 2,715 stars30 May 2026: 2,775 stars6 Jun 2026: 2,827 stars13 Jun 2026: 2,871 stars20 Jun 2026: 2,932 stars27 Jun 2026: 2,974 stars4 Jul 2026: 3,013 stars11 Jul 2026: 3,040 stars18 Jul 2026: 3,083 stars25 Jul 2026: 3,118 stars1 Aug 2026: 3,145 stars8 Aug 2026: 3,173 stars15 Aug 2026: 3,202 stars22 Aug 2026: 3,230 stars29 Aug 2026: 3,325 stars5 Sept 2026: 3,356 stars12 Sept 2026: 3,383 stars19 Sept 2026: 3,413 stars26 Sept 2026: 3,428 stars3 Oct 2026: 3,446 stars10 Oct 2026: 3,468 stars17 Oct 2026: 3,527 stars24 Oct 2026: 3,570 stars31 Oct 2026: 3,615 stars7 Nov 2026: 3,661 stars14 Nov 2026: 3,706 stars

2,160 on 25 Apr 20263,706 on 14 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

FireRed-OpenStoryline is a Python agent that edits videos through natural-language conversation. It searches and downloads media, segments clips, generates a script and narration, picks BGM, voiceover and fonts, and renders with MoviePy and FFmpeg. It runs behind an MCP server with a CLI or FastAPI web UI, and ships Skills for OpenClaw and Claude Code.

Who it is for: Creators and developers automating short-video editing with an LLM agent

Strengths

  • Edits are done by chat: cut, swap, reorder clips, adjust color, font and position
  • Saved editing workflows can be reused as Skills for batch creation with new media
  • Offers CLI, web UI, MCP server, plus OpenClaw and Claude Code Skills
  • Hosted HuggingFace demo available to try before installing

Weaknesses

  • Requires API keys set in config.toml; supported LLM providers are not listed
  • AI transitions need third-party video generation services, which the README calls costly
  • Default open-source fonts and music are basic; better results need a custom asset library
  • Setup needs Conda, downloaded model and resource archives, and a separately started MCP server

What it needs

  • Docker
  • Needs Python 3.11+, FFmpeg, MoviePy, LangChain, Conda, third-party LLM API keys, third-party AIGC video service (AI transitions)
  • port 8005

Also in Agent platforms

See all 102
Also in Agent platforms
RankProjectScore
1AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder Live demo ↗ (opens in a new tab)188.1k starscustom license95 out of 100
2daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps73.1k starsMIT95 out of 100
3LangflowVisual builder for AI agents and workflows, served as API or MCP server156.7k starsMIT94 out of 100
#4deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills85.5k starsMIT93 out of 100
#5DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs Live demo ↗ (opens in a new tab)161.4k starscustom license92 out of 100