AIAny
AI Client2024
Icon for item

OpenCreator

Unifies visual creator tools, reusable Skills, and a Codex-powered Agent to handle video translation, image/video generation, voiceovers, and editing in one local multimodal workspace. Desktop and web clients share a synchronized state machine and keep data local by default.

Introduction

Creators today juggle transcripts, translations, voice, shots, and multiple generation models across fragmented tools. OpenCreator addresses this by binding an Agent execution loop (Codex CLI) to a visual workspace, templates, and Skills so conversational prompts and GUI edits operate on the same reproducible workflow state—without sending project files to a third-party server by default.

What Sets It Apart
  • Codex-native Agent loop: Reuses Codex CLI, Skills, sessions and MCP rather than implementing a separate execution engine — so what? you get full agent reasoning, tool calls, and Skill-driven workflows with minimal glue work.
  • Multimodal creator tools in one workspace: video translation/downloader, image/video generation, Smart Dubbing, thumbnails, article and short-video script generation — so what? you can iterate across subtitles, audio, visuals and exports without context loss or manual file juggling.
  • Local-first runtime and versioning: runs a local daemon, optional desktop app, and preserves every revision as a distinct version — so what? projects are reproducible and sensitive data stays under your control while still supporting cloud providers for models if you choose.
  • Template + Skill extensibility: includes creation templates and a skills/ SKILL.md system for custom Agent workflows — so what? teams can standardize repeatable pipelines (subtitle → TTS → render) and share them across projects.
Who it's for and tradeoffs

Great fit if you are a solo creator or small team that needs an integrated, local-first workflow for multilingual video and short-form content (transcription, translation, dubbing, thumbnails, clips) and you want reproducible Agent-driven runs and template-based generation.

Look elsewhere if you require a fully managed cloud SaaS (OpenCreator expects a local runtime and optional Codex sign-in), need a pure single-purpose, highly-optimized video editor, or must run entirely offline without any model-provider configuration (some features expect configured ASR/TTS or provider access for best results).

Information

  • Websitegithub.com
  • Organizationskrillinai
  • Authorswulien, DLe-kb, xiaheyuan, krillinai, hbxugang
  • Published date2024/12/17

More Items

GitHub
AI Client2025

Private, local-first desktop assistant for voice and text conversations that runs models on your hardware. Uses local model servers (Ollama or OpenAI-compatible endpoints), offers personal memory, dictation, TTS/STT, MCP integrations and automatic redaction; free for personal use.

GitHub
AI Coding2025

Runs many shells inside one terminal and treats coding agents as first-class panes. Combines daemon-backed persistent sessions, vim-style modal control, BSP tiling, a session rail and an Inbox that surfaces approvals, questions and finished turns from LLM-based coding agents — useful when you run and manage agent workflows alongside shells.

GitHub
AI Agent2026

Audits deployed AI agents for governance and operational misalignment, running up to 60 inspections that detect deception, manipulation, fabrication, unpredictability and opacity; outputs JSON/Markdown scorecards, a graded A–F score, and optional Pro reports and dashboards.