#2828th of 50 in Data and scraping for AIFor image, video and design, video and animation
rea-video
Agent skill and CLI that breaks a video into shots and judges how each was made
- Stars
- 6.9k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Language
- Python
246 on 27 Oct 20266,931 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
rea-video splits a video into shots and decides for each whether it was filmed, AI-generated or built in code, using frame cadence, sensor noise, metadata AIGC tags and audio analysis. It outputs a remake plan and a report.html with per-shot evidence, prompts, camera and lighting notes, and an audio breakdown. It is designed to be driven by Claude Code, Codex or a similar agent, and can optionally use Gemini or Doubao for better accuracy.
Who it is for: Video creators and engineers analyzing and remaking videos with coding agents
Strengths
- Offline tools-only mode needs no paid model; README reports 98–99% accuracy on original files
- Judges each shot separately as live, AI, 3D or code, then reassembles on the original timeline
- Exports captions to SRT/ASS and reports BPM, cuts and sound effect placement
- Remake plan batches shots by target video model limits such as clip length and reference images
Weaknesses
- Accuracy on re-encoded platform videos drops to 88.6% without a vision model or agent review
- Does not render video; automatic regeneration needs the separate capsule-cinema project
- Docs are in Chinese only for now
- Built around an agent workflow; no standalone UI or hosted demo
What it needs
- Needs ffmpeg, Python 3.10+
- Models: Gemini, Doubao
Quick answers
Is rea-video open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in Data and scraping for AI
See all 50| Rank | Project | Score |
|---|---|---|
| 1 | doclingPython library that converts PDFs, Office files and more into structured text | 92 out of 100 |
| 2 | mineruParses PDFs, images and Office files into Markdown and structured JSON | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 90 out of 100 |
| #4 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 88 out of 100 |
| #5 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 87 out of 100 |