claude-video: Multimodal Video Analysis for Claude Code and AI Agents

Repositorybradautomates/claude-videoTool

The open-source tool claude-video provides the /watch command for Claude Code, Cursor, Copilot, and other agent hosts. It downloads videos from URLs or local files, extracts keyframes and transcripts, and feeds visual and audio context directly into the language model.

Key points

  1. Integrates with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and 50+ Agent Skills hosts.
  2. Solves the limitation where LLMs can only interpret videos using titles or text-only transcripts lacking visual context.
  3. Relies on yt-dlp for downloading, ffmpeg for scene-aware frame extraction, and public captions with a Whisper API fallback.
  4. Popular use cases include diagnosing bugs from screen recordings, content breakdowns, and generating structured notes.
  5. High project maturity with over 16,700 GitHub stars and active maintenance as of September 2026.

Why it matters

Screen recordings and video walkthroughs are common for bug reports and tutorials, but LLMs cannot natively ingest video files without pre-processing. claude-video automates frame extraction and transcription into an actionable multimodal prompt, eliminating manual preparation.

Analysis

Developed by bradautomates, claude-video closes a practical gap in developer-focused agent workflows. Instead of requiring users to capture screenshots or search transcripts manually, the /watch command automates the entire ingestion pipeline: yt-dlp fetches only necessary segments, ffmpeg generates scene-aware frames, and audio transcripts are extracted using free captions or the Whisper API when needed. With broad integration across Agent Skills platforms and Claude Code marketplaces, coupled with nearly 17,000 GitHub stars, the repository provides a mature, turnkey utility for developers, content analysts, and technical support engineers.

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • X post:Corey Haines

    Maker Skills for Claude Code: Automated Video Analysis with /watch-video

    Corey Haines has released the /watch-video skill as part of Maker Skills, an open-source collection for Claude Code. The tool processes video content from various sources, analyses transcripts alongside visual frames via vision models, and saves structured notes into a second brain.

    4.7kbookmarks222.8kviews

    AI & LLMs· Tool

  • Repository:browser-use/video-use

    video-use: Automated Video Editing via Coding Agents

    The open-source project video-use enables automated video editing using coding agents such as Claude Code, Codex, or Hermes via natural language. Users place raw clips in a directory and instruct the agent to assemble, clean, subtitle, and render the final cut.

    23.8kstarsPython

    AI & LLMs· Tool

  • Repository:calesthio/OpenMontage

    OpenMontage: Open-Source Agentic Video Production System

    OpenMontage is an open-source video production framework designed to turn AI coding assistants such as Cursor or Claude into automated video production studios. Built with Python, it provides 12 production pipelines, over 100 tools, and 700+ skill and knowledge files connecting speech, image, and video generation services with programmatic editing engines.

    56.2kstarsPython

    AI & LLMs· Tool

  • Repository:anthropics/claude-code

    Claude Code: Terminal-Based Agentic Coding Tool

    Claude Code by Anthropic is an agentic coding tool that operates in the terminal. It understands codebases, executes routine development tasks, explains complex code, and handles Git workflows using natural language commands.

    144.1kstarsPython

    AI & LLMs· Tool

  • Repository:anthropics/skills

    Anthropic Skills: Reference Repository and Specification for Claude Agent Skills

    Anthropic provides a public repository containing example skills, templates, and specifications for Claude's Agent Skills standard. Skills package instructions, scripts, and resources inside folders with a central SKILL.md file to enable repeatable workflows ranging from document generation to technical testing.

    174.3kstarsPython

    AI & LLMs· Resource

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.