#1212th of 17 in Agent platforms

openmontage

Agent-driven video production pipelines run from your AI coding assistant

Stars
68.3k
License
AGPL-3.0
Last commit
Oct 2026
Language
Python
Stars, last 28 weeks+68,092
1 Apr 2026: 195 stars8 Apr 2026: 887 stars15 Apr 2026: 1,992 stars22 Apr 2026: 2,914 stars29 Apr 2026: 3,189 stars6 May 2026: 3,401 stars13 May 2026: 3,591 stars20 May 2026: 3,764 stars27 May 2026: 3,908 stars3 Jun 2026: 4,200 stars10 Jun 2026: 4,509 stars17 Jun 2026: 5,441 stars24 Jun 2026: 19,942 stars1 Jul 2026: 30,539 stars8 Jul 2026: 35,188 stars15 Jul 2026: 38,372 stars22 Jul 2026: 40,802 stars29 Jul 2026: 43,429 stars5 Aug 2026: 44,833 stars12 Aug 2026: 47,336 stars19 Aug 2026: 48,570 stars26 Aug 2026: 51,137 stars2 Sept 2026: 55,396 stars9 Sept 2026: 56,583 stars16 Sept 2026: 59,290 stars23 Sept 2026: 60,839 stars30 Sept 2026: 61,865 stars7 Oct 2026: 65,057 stars14 Oct 2026: 68,287 stars

195 on 1 Apr 202668,287 on 14 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

OpenMontage is a set of pipelines, tools and stage skills that let a coding assistant (Claude Code, Cursor, Copilot, Windsurf, Codex) research, script, generate assets, edit and render a video. Rendering uses Remotion or HyperFrames plus FFmpeg. It works with no API keys using Piper TTS and free footage from Archive.org, NASA and Wikimedia, and adds paid image, video and voice providers when keys are set.

Who it is for: Creators and developers producing videos through a coding assistant

Strengths

  • Works with zero API keys: Piper TTS, free archival footage, Remotion/HyperFrames, FFmpeg
  • Many providers via optional keys: fal.ai, Atlas Cloud, Kling, Runway, ElevenLabs, Suno, Google
  • Backlot local board shows pipeline progress, costs, and a storyboard approval gate before render
  • Can start from a reference YouTube, TikTok or local video and give cost estimates first

Weaknesses

  • Needs an external AI coding assistant to drive it; no standalone prompting UI
  • AGPL-3.0 license restricts closed-source network use
  • Setup needs Python 3.10+, Node.js 18+ and FFmpeg; no Docker image
  • Local video generation needs a GPU; VRAM requirements are not stated in the README

What it needs

  • GPU optional
  • Needs Python 3.10+, FFmpeg, Node.js 18+, AI coding assistant, Remotion, HyperFrames
  • Models: wan2.2-ti2v-5b, wan2.1, hunyuan-1.5, ltx2-local, cogvideo-5b

Also in Agent platforms

See all 17
Also in Agent platforms
RankProjectScore
1LangflowVisual builder for AI agents and workflows, exposed as API or MCP server155.7k starsMIT80 out of 100
2daily_stock_analysisDaily LLM stock analysis for A-share, HK, US and other markets, pushed to chat apps66.4k starsMIT77 out of 100
3deer-flowAgent harness that runs sub-agents, memory and sandboxed skills for long tasks83.9k starsMIT75 out of 100
#4DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs Live demo ↗ (opens in a new tab)158.5k starscustom license74 out of 100
#5MulticaIssue board where AI coding agents take assignments like teammates52.8k starscustom license72 out of 100