Creators combining documented visual tools, reusable templates and agent conversation in one workspace.
Key capabilities
Visual tools and creation templates for video translation and downloading, image and video generation, voiceovers, article and social post writing, short-video scripting, and stick figure animation
Analyze public videos from YouTube, Bilibili, X, TikTok, Instagram, Douyin, Facebook, Xiaohongshu, and Pinterest, compare formats, and download video or audio
Generate images from prompts and reference images, generate videos from prompts and reference images, and turn scripts into voiceovers with selectable voices, pacing, and emotion controls
Browse featured templates by category and start creating from a template instead of building prompts and settings from scratch
Limitations and risks
Real model tasks require a usable ChatGPT sign-in or API key setup
Inclusion of Skills in the repository does not mean every Skill is automatically installed or every external service is bundled
Getting started
Download installer for your platform; Install and open the Desktop app; Confirm a usable ChatGPT sign-in or API key; Enter a request in the composer
Evidence and sources
GitHub project description: Open-source AI workspace for creators, powered by Codex. Create videos, images, voice, avatars, video translation, and edits with Agents in one place.
README: Instead of reimplementing an Agent loop, it uses Codex CLI as the execution engine and adds a stable local Runtime, a visual workspace, and a Desktop host around it.
README: Keep data, attachments, and logs local by default, with approvals and redacted diagnostics.
README: The current release includes ten creator tools. Available models and services depend on your local Codex environment and AI service settings.
README: Import local or public videos; transcribe with cloud or local Whisper services; use LLM context for subtitle segmentation, alignment, terminology, and translation