# OpenCreator: Create with Agents in a Codex-Powered Workspace This repository profile is provided by osrepos.com, an open source repository discovery platform. Source: osrepos.com Repository profile: https://osrepos.com/repo/krillinai-opencreator Generated for open source discovery and AI-assisted research. OpenCreator is a Web and Desktop creative workspace built around OpenAI Codex CLI, bringing Agent conversations and visual tools together for video, images, voice, writing, and translation. It suits creators and teams who want to manage these workflows locally in one place. GitHub: https://github.com/krillinai/OpenCreator OSRepos URL: https://osrepos.com/repo/krillinai-opencreator ## Summary OpenCreator is a Web and Desktop creative workspace built around OpenAI Codex CLI, bringing Agent conversations and visual tools together for video, images, voice, writing, and translation. It suits creators and teams who want to manage these workflows locally in one place. ## Topics - typescript - ai-agents - desktop-app - video - video-translation - text-to-speech - agent-skills ## Repository Information Last analyzed by OSRepos: Tue Oct 20 2026 17:28:28 GMT+0100 (Western European Summer Time) Detail views: 4 GitHub clicks: 1 ## Safety Notice OSRepos shares public repositories for knowledge and discovery only. Review source code, dependencies, licenses, and security implications before running or installing anything. ## Content ## Overview OpenCreator is a Web and Desktop AI workspace for creators, built around OpenAI's Codex CLI as its Agent execution engine. It combines a local Runtime and visual workspace so creators can work on scripts, video, images, voice, translation, and editing through either visual tools or natural-language conversations. It is aimed at individuals and teams who want creative work and its project data to stay local by default. The shared workspace supports both browser use and a desktop app, with the desktop adding operating-system features rather than a separate creative workflow. ## Key Features - Combine Agent conversations with visual creator tools, with both interfaces sharing workflow state and results. - Translate videos with transcription, subtitle editing, translation, optional dubbing, and video or subtitle export. - Download and inspect public video links from supported platforms, with format selection and optional caption downloads. - Generate images, videos, thumbnails, voiceovers, articles, social posts, short-video scripts, and stick-figure animations. - Use reusable creation templates and Codex Skills, or add local Skills for custom workflows. - Keep project data and attachments in a local Runtime, with approvals, redacted diagnostics, and versioned creative revisions. ## Use Cases - A creator can translate a video, refine subtitle timing, add dubbing, and export a localized version in one workflow. - A social media producer can turn source material into platform-oriented posts or scripts, then generate supporting images or voiceovers. - A small creative team can organize Agent tasks, approvals, files, and revisions alongside visual editing tools in a shared project workspace. - A developer or technically confident creator can extend repeatable workflows with Codex Skills and use the local Runtime from a browser or desktop app. ## Our Take OpenCreator is an actively maintained, broad creator workspace for people comfortable configuring Codex and external AI services, rather than a standalone media editor with all models included. **Good fit if:** - You want Codex CLI to power Agent workflows alongside visual tools for media creation and translation. - You prefer a local-first project workspace available through Web or Desktop, and can provide the required Codex setup and any service credentials. - You value an active project with regular commits and releases, contributions from multiple people, and no measured dependence on a single contributor. **Look elsewhere if:** - You need a self-contained app that works without a Codex login or configured model and media services. - Your workflow depends on automatic clipping or digital-avatar generation, which the README lists as in development. - You need a narrowly focused video editor rather than a workspace spanning Agents, writing, image generation, voice, and translation. ## Project Health | Signal | Value | |---|---| | Status | **Active**: regular commits and releases | | Last commit | 2026-10-19 (1 day ago) | | Commits, last 90 days | 100+ | | Releases, last 12 months | 17 (latest v3.2.8, 2026-10-18) | | Contributors | 26 (top contributor: 46% of commits) | | Issues closed, last 90 days | 8 (typically closed in 54 days) | | Pull requests merged, last 90 days | 16 (typically merged in 2 days) | | Project age | 22 months | Checked on 2026-10-20 with the GitHub API. ## Project Facts - Language: TypeScript - License: Apache-2.0 - Stars: 13.8k - Forks: 1.5k - Topics: agent-skills, codex-cli, deskop-app, dubbing, image-generation, localization, skills, tts - Website: https://www.open-creator.ai - Archived: no ## What You Need Detected in the repository: - Node.js (from package.json) - Automated checks on GitHub Actions ## Getting Started For the Desktop app, download an installer from the [latest releases](https://github.com/krillinai/OpenCreator/releases/latest). For Web development, the repository documents a Node.js 22+ and pnpm setup with Codex CLI available: ```bash git clone https://github.com/krillinai/OpenCreator.git cd OpenCreator corepack enable pnpm install pnpm web:dev ``` Then open `http://127.0.0.1:19861/`. See the [README](https://github.com/krillinai/OpenCreator#readme) for setup and configuration details. ## License in Plain Words **Apache-2.0** (permissive). - Commercial use: yes - Modify and redistribute: yes - You must keep: the license, the NOTICE file and a note of your changes - Share your changes: no - Includes an explicit patent grant from the contributors A summary, not legal advice: the LICENSE file is what applies. ## Considerations - Real model tasks require a usable Codex sign-in or API-key setup. Image, video, voice, and transcription capabilities also depend on configured services, credentials, and model availability. - The Web-from-source path requires Node.js 22 or later, pnpm, and a Codex CLI executable. The Desktop installer includes Codex CLI, but still requires usable model access. - Some video sources may require platform cookies, and language support varies by service and model. The README's language catalog does not guarantee every model supports every language. - Auto Clips and Digital Avatar are identified as in development, so they should not be assumed available for production workflows. - The project is active, with recent commits and releases and contributions from multiple contributors. Issue handling is less immediate: the measured median time to close an issue is about 54 days.