An Agent Skill that turns a topic into a narrated explainer video with voiceover, hard subtitles and cover images, rendering HTML frames locally to MP4.
- Stars
- 13,759
- Forks
- 1,509
- Open issues
- 42
- Last commit
- 18 hours ago
What is it?
OpenCreator (formerly KrillinAI) is a local-first workspace for creators who want video, image, voice and writing work in one place. Instead of building its own agent loop, it uses Codex CLI as the execution engine and adds a local Runtime, a visual workspace and a desktop host around it.
The content workspace includes tools for video translation with subtitle editing and dubbing, downloading public videos from platforms such as YouTube, Bilibili, TikTok and Instagram, and generating images, videos, thumbnails and voiceovers. Writing tools produce articles, Xiaohongshu posts and short-video scripts, and a stick figure animation tool turns text into a rendered video.
An agent conversation mode lets users describe tasks in natural language, run them in the background, and manage approvals, Skills, MCP, schedules and memory. The visual tools and the conversation share the same task state, and each revision is saved as a new version.
Key features
- 01Video translation with subtitle transcription, translation, dubbing and SRT, audio or video export
- 02Video downloader for public links from 10 platforms, with format comparison
- 03Image, video, thumbnail and text-to-speech generation from one workflow
- 04Agent conversation built on Codex CLI, with Skills and MCP support
- 05Versioned revisions that keep earlier settings and outputs
- 06Local data storage with approvals and redacted logs
Use cases
- Translating and dubbing YouTube or short-video content into other languages
- Producing subtitled, portrait-format clips for social media platforms
- Drafting articles, social posts or short-video scripts from source material
- Batch-generating thumbnails and images for content publishing
Things to know
- Several creator tools depend on external AI services, models, or a configured local Codex environment, so they need your own service setup.
- Some video sources may require platform cookies to download.
- Auto Clips and Digital Avatar are still in development and not yet available.
Topics
FAQ
- What is OpenCreator?
- Open-source AI workspace for creators that combines video translation, downloading, image and video generation, voiceovers and scripting, built on Codex CLI. OpenCreator (formerly KrillinAI) is a local-first workspace for creators who want video, image, voice and writing work in one place. Instead of building its own agent loop, it uses Codex CLI as the execution engine and adds a local Runtime, a visual workspace and a desktop host around it.
- Is OpenCreator free to use? What license does it have?
- OpenCreator is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is OpenCreator still maintained?
- Actively maintained. The last commit to OpenCreator was on Oct 20, 2026.
- What can I use OpenCreator for?
- Translating and dubbing YouTube or short-video content into other languages Producing subtitled, portrait-format clips for social media platforms Drafting articles, social posts or short-video scripts from source material Batch-generating thumbnails and images for content publishing
- Where can I get OpenCreator?
- The source code and installation instructions are on GitHub: https://github.com/krillinai/OpenCreator
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
AI video agent for macOS and Windows that edits videos on an editable timeline: transcribe, subtitle, translate, dub, cut and animate.
An open-source agentic video production system that turns an AI coding assistant into a pipeline-driven video studio for research, scripting, asset generation, editing and rendering.
A browser built for AI agents and you to share: agents run tasks in isolated Spaces while your own tabs and logins stay untouched.
Windows-focused Gradio web app bundling text-to-speech, voice cloning, Whisper transcription, YouTube download, vocal separation and translation for dubbing.
A TypeScript CLI and terminal UI for defining, launching and running persistent teams of Claude Code and Codex agents in tmux.