rea-video
rea-video is an Apache-2.0 CLI and agent skill that reverse-engineers a video shot by shot, judging whether each part was filmed, AI-generated or coded, and explaining how to remake it; you ask Claude Code, Codex or another agent to install it and break down a file, and it needs ffmpeg and Python 3.10 or later.
Updated
✨ Try AgentScout's free AI image generator →Good for: writing code, coding in the terminal
Use cases
About rea-video
rea-video is listed in our vision category and is aimed at builders. rea-video is an Apache-2.0 CLI and agent skill that reverse-engineers a video shot by shot, judging whether each part was filmed, AI-generated or coded, and explaining how to remake it; you ask Claude Code, Codex or another agent to install it and break down a file, and it needs ffmpeg and Python 3.10 or later. Pricing, as the maker states it: Open source. Maturity: Mature. We last checked the official link on 2026-11-10.
rea-video at a glance
- Category: Vision
- Built for: Developers and teams building with AI agents
- Pricing: Open source (as the maker states it)
- GitHub: JuneYaooo/rea-video · 6,112 stars (as of Nov 10, 2026)
- Official site: reavideo.ai/en
- Listed on AgentScout: Nov 10, 2026
rea-video FAQ
What is rea-video?
rea-video is an Apache-2.0 CLI and agent skill that reverse-engineers a video shot by shot, judging whether each part was filmed, AI-generated or coded, and explaining how to remake it; you ask Claude Code, Codex or another agent to install it and break down a file, and it needs ffmpeg and Python 3.10 or later.
How much does rea-video cost?
rea-video's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Where can I find rea-video's source code?
On GitHub at JuneYaooo/rea-video, which had 6,112 stars as of Nov 10, 2026.
What are alternatives to rea-video?
Similar tools include Roboflow Agent, NVIDIA TAO Agent Skills, Groundlight, Encord Agents, SearchByVideo and CVAT AI Agents.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
rea-video ratings and reviews
Be the first to rate rea-video: tap 1 to 5 stars below. A written review is optional.
rea-video alternatives
Other vision tools in our directory. See all vision tools →
Roboflow Agent
Computer-vision agent that picks models and builds/deploys vision apps; plugs into Claude Code, Codex, Cursor via MCP.
NVIDIA TAO Agent Skills
NVIDIA's vision-model post-training toolkit, now packaged as agent skills so Claude Code or Codex can fine-tune, optimize and export vision foundation models from plain-English prompts.
Groundlight
Turns any camera into a vision sensor: you ask a yes/no question in plain English and Groundlight builds and tunes the model, backed by human review, with edge deployment.
Encord Agents
Encord's agents that plug foundation models or your own models into labeling workflows to pre-label, segment, track, route and QA image, video and multimodal data, with a no-code catalog and an open-source SDK.
SearchByVideo
SearchByVideo searches inside your own videos with AI: you describe a moment, an object or on-screen text and it returns the matching scenes with timestamps ranked by confidence, including on silent footage, so you can jump straight to them. You can try a live sample free; Pro costs $24.99 a month or $99.99 a year.
CVAT AI Agents
CVAT feature that runs your own detection, segmentation or tracking model as an agent on your infrastructure and feeds its auto-annotations back into CVAT tasks.
Get your badge
Built rea-video? Optional. Showing this badge does not change your rank or earn a Featured spot. It links to this page. About badges