0xsline/OpenChatCut

Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.

What it solves

OpenChatCut is a local-first AI video editor that bridges the gap between precise manual timeline editing and one-shot AI video generation. It allows users to use conversational agents to perform complex editing tasks—such as cutting, adding transitions, and generating captions—while keeping the project fully editable on a professional multitrack timeline, rather than producing an immutable final video.

How it works

The system integrates a professional video editing workspace with AI agents. Users can either edit manually or describe their goals in natural language. The built-in agent (or external agents via MCP) reads the project context and proposes verifiable edits. These edits are written to real tracks, clips, and effects on the timeline, which the user can then preview, adjust, or undo. It uses a local-first approach where projects and media stay on the user's machine, while AI model API keys are managed server-side.

Who it’s for

It is designed for content creators, social media producers, and developers who want AI to automate the tedious parts of video editing (like rough cuts and captioning) without losing professional control over the final output.

Highlights

  • Agent-native workflow: Built-in and external agents (like Codex or Claude Code) share the same editing tools to modify the timeline.
  • Professional Timeline: Supports multitrack editing, keyframes, ripple edits, and production-ready exports (MP4, FCPXML).
  • Transcript-driven editing: Word-level transcription allows for text-based cuts and automatic caption generation.
  • Visual Intelligence: Includes in-browser person segmentation and face-safe zones to ensure captions and graphics don't overlap speakers.
  • Extensible Resources: A community library for reusable motion graphics, LUTs, and sound effects.
  • MCP Integration: Exposes a Streamable HTTP MCP endpoint for deep integration with external AI coding agents.

Related

  • Project
    ChatCut-Inc/agent-plugin

    A plugin that connects AI agents like Codex and Claude Code to ChatCut, enabling users to edit video projects, generate assets, and manage timelines using natural language.

  • Project
    ronak-create/FableCut

    A browser‑only, non‑linear video editor whose timeline is a JSON file that can be edited live by humans or AI agents via MCP, REST or direct file writes. Zero npm dependencies, optional ffmpeg for fast export, and built‑in AI background removal.

  • Project
    krillinai/OpenCreator

    OpenCreator is an open‑source, locally‑run AI workspace that combines a Codex‑based conversational agent with a visual dashboard for multimodal content creation (video translation, downloading, thumbnail and image generation). It offers versioned workflows, local data storage, and a desktop client built on the same web UI. Supports many LLMs, Whisper, GPT‑Image, and other voice/translation services. Designed for creators and small teams who want AI‑assisted media production without relying on cloud‑only platforms.

  • Project
    jub0t/Concat

    An open-source, local-first video editor that provides a free alternative to CapCut with built-in local AI features like auto-captions and text-to-speech.

  • Dispatch
    FableCut: A Zero-Dependency Browser Video Editor for AI Agents

    FableCut is a browser-based non-linear video editor that exposes its entire timeline as a JSON document, allowing AI agents to perform edits via MCP, REST, or direct file modification with live UI updates.