veedstudio/open-edit

Open-source, agent-driven editing pipeline: create subtitles, motion graphics, slides, edit and render videos.

What it solves

OpenEdit provides a way for coding agents to perform video editing tasks without a graphical user interface or timeline. It allows users to describe the desired edits—such as adding subtitles, cutting footage, or creating motion graphics—using natural language prompts, which the agent then executes as a production pipeline.

How it works

The system functions as a "skill" that can be installed into AI agents like Claude Code, Codex, or Gemini CLI. It uses a CLI package (@veedstudio/openedit-cli) to manage the flow: transcribing audio with per-word timings (via WhisperX locally or VEED's hosted service), designing styles using HTML and CSS, and rendering the final MP4 file using a dedicated renderer. The renderer runs locally on the machine, requiring a desktop session rather than a headless browser.

Who it’s for

Developers and users of AI coding agents who want to integrate video production capabilities directly into their terminal-based workflows.

Highlights

  • Agent-Driven Workflow: No GUI; edits are performed via prompts to a coding agent.
  • Flexible Transcription: Supports local transcription via WhisperX or hosted services from VEED.
  • Broad Editing Capabilities: Handles captions, cutting, reframing, and the creation of motion graphics from scripts or brand books.
  • Multimodal Integration: Can pull in AI video/image generators or MCP servers (e.g., Figma) to inform design and visual elements.
  • Local Rendering: Uses a source-available renderer that runs on Apple Silicon Macs or Windows x64 PCs.

Related

  • Project
    Vincentwei1021/anything2explainer

    An AI-driven pipeline that converts topics or documents into narrated motion-graphics explainer videos by using AI agents to write Remotion code.

  • Project
    pexoai/pexo-skills

    A set of open-source agent skills that automate the full video production pipeline, transforming text, images, or URLs into finished multi-shot videos with music and subtitles.

  • Project
    0xsline/OpenChatCut

    An open-source, local-first AI video editor that combines a professional multitrack timeline with conversational agents for editable, agent-driven video production.

  • Project
    hassancs91/claude-youtube-editor

    An open-source pipeline that automates YouTube video editing by turning raw talking-head recordings into polished videos with AI-generated visuals, audio cleaning, and automated uploads.

  • Project
    Orkas-AI/Orkas-VideoStudio

    A toolkit that enables AI coding agents to compose, edit, and generate videos via a readable plan file, providing a deterministic pipeline for automated video production.