OpenCreator
Local AI workspace for video editing, translation, and generation powered by Codex CLI.
Combine visual creator tools, reusable Skills, and Codex Agents in a unified local workspace.
OpenCreator is an open-source local AI workspace that integrates visual creation tools and Codex-powered agents for video translation, dubbing, scripting, and media generation. It suits video producers and developers who prefer running creative pipelines locally with Git-like project versioning.
What it is
It wraps the Codex CLI execution engine in a desktop and web host, offering specialized tools for video downloading, Whisper transcription, bilingual subtitle alignment, AI image and video generation, and smart dubbing. You can execute tasks either through dedicated visual dashboards or via natural language Agent conversations that maintain background runs and shared state.
Who it's for
It suits solo creators, editors, and developers who want local control over their media pipelines and prefer interacting with AI via CLI-backed agents. It does not suit non-technical users who expect a zero-configuration cloud SaaS without local runtime dependencies.
Key features
Codex-Powered Agent Workspace
Run creative and development tasks using the native Codex Agent loop and custom MCP configuration.
Bilingual Video Translation
Import local or public videos, transcribe via Whisper, and translate with LLM-guided context alignment.
Dual-Mode Workflow
Switch seamlessly between visual creator dashboards and background Agent conversations sharing a unified state.
Revision Versioning
Preserve earlier settings and outputs with automatic version creation for every workflow revision.
Managed Runtime Components
Inspect bundled dependencies like yt-dlp and handle manual updates while keeping fallback working versions.
Up and running in 3 steps
Our honest verdict
What's great
- Integrates both visual tools and natural language agent conversation in a single local runtime.
- Preserves earlier inputs and outputs via built-in revision versioning for easy comparison.
- Supports multi-format media pipelines including video translation, scriptwriting, and stick figure animations.
- Keeps data, attachments, and logs local by default with redacted diagnostics and approval controls.
Where it falls short
- Requires managing a local Codex environment, bundled runtimes, and potential source platform cookies for media downloads.
- Relies on external AI service settings and local model availability for feature execution.
- Advanced features like video generation and auto-clips depend on specific local capabilities and active development statuses.
Pricing & license
Free under its open-source license, with the only cost being your own local machine resources and any external AI service or model API fees you incur.
Open remote AI-training roles
876 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
What happened to KrillinAI?
OpenCreator is the new name for KrillinAI, maintaining the same open-source local AI workspace focus.
Can I run it on the web?
Web serves as the frontend implementation, but Desktop is required for operating system capabilities like directory selection and tray behavior.
How does it handle yt-dlp updates?
OpenCreator inspects active yt-dlp versions, checks for periodic updates, and allows manual updates while keeping older working binaries.
