OpenCreator

English | 简体中文 | 日本語 | 한국어 | Bahasa Indonesia | Español | Français | Deutsch | Português | Русский | العربية | ภาษาไทย | Türkçe | हिन्दी | বাংলা | اردو | Tiếng Việt | Filipino

Highlights · Creator Tools · Skills · Examples · Quick Start · Desktop · Docs · Community

Project Overview

OpenCreator is built for individuals and teams who want to keep creative and development work running locally. 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.

OpenCreator offers two connected ways to work:

• Content workspace: use 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.
• Agent conversation: start and guide creative or development tasks in natural language, organize conversations by project, keep Runs working in the background, and manage approvals, attachments, files, Skills, MCP, schedules, notifications, memory, and diagnostics from one place.

Web is the single frontend implementation. Desktop loads the same Web build and adds only capabilities that require the operating system, such as directory selection, window lifecycle, tray behavior, and native notifications. With the same data and content viewport, both platforms share the same general UI and Runtime behavior.

Project Highlights

• 🤖 Codex Native: Reuse the Codex Agent loop, models, reasoning, tool calls, conversations, Skills, and MCP without maintaining a second execution engine.

• 🚀 Ready-to-Use Desktop App: Launch OpenCreator directly from the desktop app with Codex CLI included; the local Runtime starts on demand and prepares a default project automatically.

• ⚙️ Desktop Setup That Reuses Codex: On first launch, scan your local Codex configuration and offer to reuse a working ChatGPT sign-in or API key setup. A guided form is available for other model providers.

• 🔄 Managed Runtime Components: Inspect bundled, active, and latest yt-dlp versions, check for updates periodically, and update manually while keeping the current working version available if an update fails.

• 🎨 Multimodal Creation: Create and manage video, images, audio, subtitles, and documents through one connected workflow.

• 🧩 Creation Templates: Start creating images and videos from reusable templates without setting up prompts and settings from scratch.

• 🔗 Dual-Mode Workflow: Work through either the visual workspace or Agent conversation while one shared state machine keeps steps, progress, and results synchronized.

• 🕘 Versioning: Every revision creates a new version while preserving earlier settings and outputs for review and comparison.

• 🧩 Reusable Skills: Use video workflow Skills, extend the Agent with your own Skills, and manage MCP through Codex-native configuration.

• 🧠 Memory: Keep global, project, and thread memory with summaries and reproducible Run input snapshots.

• 🔐 Local Security: Keep data, attachments, and logs local by default, with approvals and redacted diagnostics.

• 🌐 Localized Interface: Use Web and Desktop in 43 interface languages, with automatic system-language detection, manual selection, and right-to-left layouts for Arabic, Persian, Urdu, and Hebrew.

Creator Tools

The current release includes ten creator tools. Available models and services depend on your local Codex environment and AI service settings.

Open the Dashboard to write articles, Xiaohongshu posts, or short-video scripts; create stick figure animations; translate or download videos; generate thumbnails, images, or videos; and create voiceovers with Text to Speech.

More creator tools are continuously being added.

Video Translation offers 123 source languages and 124 target options, including Pinyin output. Search by native name, English name, Chinese name, or language code. Speech recognition and dubbing coverage depend on the selected service and model; the language catalog does not mean every model supports every language.

• Subtitle-only translation: Import and preview an SRT file, then translate it without a source video, dubbing, or video rendering.

• Advanced subtitle editing: Open an immersive editor with a playback-linked waveform and timeline, adjust subtitle timing, split or merge cues, and find and replace text. Preview subtitle styles on the video, adjust language, dubbing, and output settings, then generate a new version while retaining earlier results.

• One-step creation: Configure image generation, video generation, and Text to Speech on one page. Browse models, preview reference images, use model-specific image options, and find voices in a searchable voice library.

• Multilingual output and progress: Bundled fallback fonts improve complex-script and right-to-left subtitle rendering. Follow transcription, translation, dubbing, and rendering progress with completed and total item counts where available.

Creation Templates

Start creating from a template instead of building every prompt and setting from scratch. Browse featured templates by category, including video creation and image design, to find a starting point for your idea.

The collection brings together templates created by OpenCreator and by independent creators. Third-party templates credit their creators and link to the original source on the template detail page.

Open a template to preview its example result and inspect its prompt, settings, tags, author, and original source. Select Use this template to start creating with it, then adjust the inputs for your own work.

Skills

Creator tools provide visual controls; Skills give the Agent reusable instructions and tool workflows. OpenCreator includes video-production Skills in the repository, alongside support for managing local Codex Skills.

The repository's skills/ directory contains reusable instructions for Agents operating the embedded KrillinAI CLI.

Skill	Capabilities
KrillinAI CLI	Choose commands, check configuration, and interpret progress, manifests, outputs, and errors
Subtitle	Download platform captions or transcribe media, translate subtitles, and produce bilingual or short portrait subtitles
TTS	Generate target-language dubbing from subtitles and optionally produce a dubbed video
Landscape Render	Render landscape videos with bilingual subtitles or dubbed audio and target-language subtitles
Portrait Render	Compose portrait videos with titles, bilingual subtitles, or dubbing
Cover	Generate a cover image from a complete text prompt and save the image and final prompt
Pipeline Plan	Validate a multi-stage output plan in dry-run mode; execute actual work through the individual stage Skills

Extend with Your Own Skills

OpenCreator supports local Codex Skills defined by SKILL.md, so you can add your own methods and workflows rather than relying only on fixed creator tools. Skill availability depends on the active Codex home and installed Skills; video workflow Skills require the CLI and relevant services to be configured. Inclusion in the repository does not mean every Skill is automatically installed or every external service is bundled.

Conversation and workspace, moving together

Describe tasks naturally, then step into visual tools whenever you need precise control.

Fine-grained workspace controls

Adjust subtitles, shots, audio, and generation settings precisely.

Flexible conversational edits

Tell the Agent what to change and refine the result in natural language.

Synchronized state

Conversation and workspace share the current task state, so nothing needs repeating.

Independent versions

Each revision creates a separate version without overwriting earlier results or settings.

Models Supported

Language model availability follows the Codex model catalog or your OpenAI-compatible provider. Image, video, voice, and transcription models use the services configured in Settings → AI Services.

The providers and models shown are examples; actual availability depends on your credentials, provider account access, and platform.

Language models

Image

Video

Voice and transcription

Local transcription also supports faster-whisper, WhisperKit, and whisper.cpp where available.

Examples

Video Translation

The public examples below were produced when OpenCreator was still named KrillinAI. They demonstrate the established subtitle alignment, translation, dubbing, and portrait-video workflow that OpenCreator's Video Translation workspace brings into a wider Agent workflow.

The project generated the subtitle file below from a 46-minute local video in one run, without manual subtitle adjustments. The published result shows complete coverage, no overlapping lines, natural segmentation, and high-quality translation.

Subtitle Translation

https://github.com/user-attachments/assets/bba1ac0a-fe6b-4947-b58d-ba99306d0339

Dubbing

https://github.com/user-attachments/assets/0b32fad3-c3ad-4b6a-abf0-0865f0dd2385

Portrait Mode

https://github.com/user-attachments/assets/c2c7b528-0ef8-4ba9-b8ac-f9f92f6d4e71

These video examples and the subtitle alignment image were produced while OpenCreator still used the KrillinAI name.

Subtitle Editor

The built-in subtitle editor provides side-by-side original and translated text, synchronized video preview, a playback-linked waveform and timeline, and customizable subtitle styles.

Video Downloader

Analyze public video links from 10 supported platforms, compare available formats, and download video or audio directly to your project.

Supported video sources:

Availability varies by video and region; some sources may require platform cookies.

Video Generation

Generate an AI video from a text prompt or reference image with Seedance. Configure the model, aspect ratio, resolution, and duration, then preview, regenerate, or download each version from the project workspace.

Stick Figure Animation

OpenCreator developed this original character collection in collaboration with artist Harbor Hsia, creator of Stickman on Behance. The built-in cast keeps character identities consistent throughout the animation workflow.

Turn text or YouTube content into a complete animation through a guided workflow for script review, narration, timing, storyboard visuals, subtitles, rendering, and downloadable video output.

Quick Start

Install the Desktop App

Download the installer for your platform from the latest OpenCreator release (macOS Apple Silicon, macOS Intel, or Windows x64). Install and open the app; you do not need Node.js or pnpm to use the Desktop app. The Desktop package includes Codex CLI; real model tasks require a usable ChatGPT sign-in or API key setup.

On first launch, Desktop starts the local Runtime, prepares a default project, and checks your local Codex configuration. If it finds a usable sign-in or API key and model settings, confirm Use local Codex and continue to reuse them. You can also configure another provider in the same startup flow:

After setup, enter your request in the composer to start a task. If you run into trouble, see the user guide and troubleshooting.

Run Web from Source

For development or browser-based use, install:

• Node.js 22 or later
• pnpm 9.15.0, pinned through the repository's packageManager field
• A Codex CLI executable available in your terminal
• A valid Codex CLI login for real model tasks

Check your local environment first:

node --version
pnpm --version
codex --version

git clone https://github.com/krillinai/OpenCreator.git
cd OpenCreator
corepack enable
pnpm install
pnpm web:dev

Open http://127.0.0.1:19861/. The development server starts the local daemon on demand and injects a temporary Runtime token through a same-origin proxy, so no connection token needs to be copied manually.

On first launch, the Runtime prepares a default project and checks local Codex settings. Confirm an existing ChatGPT sign-in or API key to use local Codex, or select a provider and enter its model, endpoint, and API key. The composer is ready after setup. To work on the daemon only:

pnpm daemon:dev

The daemon listens only on a loopback address and prints its connection address and temporary token to stdout once.

Desktop

Desktop and the browser use the same React frontend from apps/web. General project, conversation, task, and settings behavior calls the same Daemon/API. Electron adds only real system paths, window controls, tray behavior, and native notifications.

Development Mode

pnpm desktop:dev

Local Packaging

Command	Output
pnpm desktop:package	A runnable directory for the current platform, intended for local verification
pnpm desktop:dist	An installer for the current platform
pnpm desktop:release	The formal release packaging entry point
pnpm --filter @opencreator/desktop verify:package	Verification for an existing Desktop package
pnpm krillinai:package	Separate KrillinAI Server and CLI archives for the selected platform

Desktop packaging rebuilds Web from the current workspace, records the commit, dirty state, platform, architecture, and Web hash, and compares apps/web/dist with the resources embedded in the application. Packaging fails if they differ. See the Desktop release runbook for signing, notarization, Windows builds, and release requirements.

Core Workflows

Conversations and Runs

1. Select a project or start a new conversation.
2. Enter a task and choose the permission level, Profile, model, and reasoning effort.
3. While a Run is active, queue follow-up tasks or interrupt it and continue immediately.
4. Use the Timeline to inspect reasoning summaries, tool calls, file changes, approvals, and final results.
5. Use the task center to track running, completed, failed, and approval-blocked tasks globally.

Skills and MCP

• Browse the Skill marketplace, installation history, and locally available Skills in the plugin center.
• Select a Skill from the composer with / or the add menu so the next task follows its workflow.
• MCP management passes through Codex-native commands and configuration instead of maintaining a second execution engine.
• OpenCreator uses the active $CODEX_HOME by default, so confirm the impact before changing global Skills or MCP configuration.

Schedules and Dedicated Task Threads

• Every schedule owns a persistent, dedicated OpenCreator conversation.
• Automatic triggers, manual runs, and user follow-ups reuse that conversation and run serially with the queue or skip policy.
• Deleting a schedule archives its dedicated conversation while preserving existing Runs, results, and underlying Codex history.
• Rotating or recovering an underlying Codex thread does not change the OpenCreator task entry or page route.

OpenCreator System Architecture

OpenCreator treats the visual workspace and the Agent conversation as two interfaces to the same creative task, rather than two separate workflows. Each creator workflow is modeled as a state machine: source input, configuration, generation, review, revision, and export become explicit states and events. Workspace actions and conversational commands enter the same state machine, while the current step, configuration, progress, versions, and results are projected back into both interfaces. This keeps the workspace and conversation synchronized without introducing a second source of truth.

Creative work is iterative, so revisions do not overwrite the current result. Each correction or regeneration creates a new version from the existing workflow state, retaining the settings and outputs of earlier versions for review, comparison, and continued refinement.

+-----------------------------+     +------------------------------------+
| Browser Access              |     | Desktop Host                       |
|                             |     | Shared Web build + Electron        |
+--------------+--------------+     +------------------+-----------------+
               |                                       |
               +-------------------+-------------------+
                                   v
+----------------------------------------------------------------------------+
| Creator Experience / apps/web                                              |
| Dashboard / Creator Tools / Agent Conversation / Settings / Files          |
+-------------------------------------+--------------------------------------+
                                      |
+-------------------------------------v--------------------------------------+
| Collaboration Core                                                         |
| Shared workflow state / Steps / Progress / Results / Versions              |
+-------------------------------------+--------------------------------------+
                                      | Runtime API + SSE
+-------------------------------------v--------------------------------------+
| Local Runtime / apps/daemon                                                 |
| Projects / Runs / Approvals / Schedules / Memory / Notifications           |
| Component status / Update checks / Verified updates / Safe fallback        |
+-------------+------------------------+------------------------+-------------+
              |                        |                        |
              v                        v                        v
+---------------------+  +---------------------+  +-------------------------+
| Local Data          |  | Codex Engine        |  | Media Toolchain         |
| SQLite / Files      |  | CLI / app-server    |  | FFmpeg / yt-dlp         |
| System credentials  |  | Skills / MCP        |  | Whisper / AI services   |
+---------------------+  +---------------------+  +-------------------------+

OpenCreator Component	Responsibility	Implementation
Creator Experience	Dashboard, creator tools, Agent conversation, settings, and files	apps/web · React 18 · Vite · TypeScript
Collaboration Core	Keeps workspace steps, conversation context, progress, results, and revisions synchronized	Shared workflow state · CreatorCollaborationPanel · version history
Local Runtime	Manages projects, Runs, approvals, schedules, memory, and notifications	apps/daemon · Fastify · Runtime API · SSE
Runtime Components	Tracks bundled, active, and latest versions; checks periodically and installs only user-requested updates	yt-dlp nightly · update verification · working-version fallback
Codex Engine	Provides the Agent loop, sessions, reasoning, tools, Skills, and MCP	Codex CLI · app-server
Media Toolchain	Downloads, transcribes, transforms, generates, and exports creative media	yt-dlp · Whisper · FFmpeg · configured AI services
Local Data	Stores project data, Runs, attachments, outputs, and credentials locally	SQLite · filesystem · system credential storage
Desktop Host	Loads the shared Web build and adds operating-system capabilities	apps/desktop · Electron · Preload Bridge

Core principles:

• The workspace and Agent conversation are synchronized projections of one workflow state; both dispatch events to the same state machine instead of maintaining parallel task state.
• Revisions create new versions instead of replacing existing results, preserving the context and output of every creative iteration.
• The frontend does not launch Codex directly and does not depend on raw Codex JSONL event formats.
• The daemon owns process lifecycle, event normalization, persistence, approvals, schedules, and the notification outbox.
• Codex remains the execution source of truth for the Agent loop, Skills, and MCP.
• Browser Bridge and Desktop Bridge do not implement separate copies of general product logic.

Repository Layout

OpenCreator/
├── apps/
│   ├── web/          # The single React frontend implementation
│   ├── daemon/       # Local Fastify Runtime and Codex adapter
│   ├── desktop/      # Electron Main, Preload, native capabilities, and packaging
│   └── harness/      # Runtime command-line verification tool
├── packages/
│   ├── protocol/     # Runtime contracts shared by Web, Daemon, and Desktop
│   └── skill-market/ # Skill marketplace models and shared logic
├── docs/             # Design docs, API references, runbooks, and test reports
├── scripts/          # Repository-level checks
└── .runtime/         # Local Runtime data, created on first launch

Configuration

AI Service API Keys

Open Settings → AI Services to configure the model, transcription, voice, and image providers used by the current workspaces. Additional service categories may appear in preparation for upcoming creator tools. Each category exposes only the fields required by its selected provider, including the Base URL, API Key, model, proxy, or provider-specific credentials.

Credentials are saved through the local Runtime's system credential storage and should never be committed to the repository. Some local or system-backed providers, such as Edge TTS, do not require an API Key.

Account and Subscriptions

The personal center displays your account, confirmed subscription and available credits. Sign-in opens https://www.open-creator.ai/device in your browser. Sign in on the website and approve the device; the local Daemon obtains its own session. The browser and client share an account but keep independent sessions.

Subscription plans are selected inside OpenCreator. Purchasing opens Stripe Checkout, and managing a subscription opens Stripe Billing Portal. Client billing returns use the website's /billing/return page without requiring a website session. OpenCreator refreshes benefits from Gateway after verified Stripe notifications. The website's /pricing and /account pages provide another purchase entry to the same subscription backend.

Third-party Runtime Components

Open Settings → Third-party Components to inspect the yt-dlp nightly version currently in use, the version bundled with OpenCreator, its source, and the latest available release. OpenCreator checks for updates every seven days but never installs them automatically. Updates require an explicit user action, and the current working version remains available if downloading, verification, or installation fails.

Runtime Environment Variables

Most users do not need environment variables. Use these when you need isolated data, a specific Codex executable, or a custom managed-project directory:

Environment variable	Default	Purpose
OPENCREATOR_DATA_DIR	.runtime	OpenCreator database, Runs, attachments, and managed workspaces
OPENCREATOR_GATEWAY_ORIGIN	https://www.open-creator.ai	Gateway for account sign-in, subscriptions, credits, and official model services; override for a local Gateway
OPENCREATOR_CODEX_BIN	codex	Path to the Codex CLI executable
CODEX_HOME	~/.codex	Source of truth for Codex sessions, configuration, Skills, MCP, and Profiles
OPENCREATOR_DEFAULT_CWD	Current working directory	Default daemon working directory
OPENCREATOR_DEFAULT_PROJECT_ROOT	Runtime default policy	Managed-project root; when set, OpenCreator uses its OpenCreator/ child directory
OPENCREATOR_CODEX_THREAD_ROTATION_RUN_THRESHOLD	50	Terminal Run threshold for rotating the Codex thread behind a long-running schedule; use 0 to disable proactive rotation

For example, isolate both Runtime data and the Codex environment:

OPENCREATOR_DATA_DIR=/path/to/opencreator-data \
CODEX_HOME=/path/to/codex-home \
pnpm web:dev

Data and Security

Runtime data is stored under .runtime/ in the repository root by default:

Path	Contents
.runtime/app.sqlite	Projects, threads, Runs, events, schedules, notifications, attachment metadata, approvals, memory, and summaries
.runtime/runs/	Redacted logs, diagnostics, and metadata for individual Runs
.runtime/attachments/	Controlled attachment files
.runtime/workspaces/	Runtime-managed project workspaces

Codex sessions and configuration remain in $CODEX_HOME and must be backed up separately from .runtime/.

Security boundaries include:

• The daemon listens only on 127.0.0.1; every API except the health check requires a Bearer token.
• HTML preview disables scripts, navigation, and popups by default and allows only controlled same-workspace relative resources.
• Sensitive memory requires a second confirmation. OpenCreator never permanently stores unconfirmed suggestions automatically.
• Diagnostics and Run logs are redacted before they are returned or exported.
• Desktop packages enable ASAR integrity and cookie encryption while disabling RunAsNode, NODE_OPTIONS, and the Node CLI Inspector.

See the user guide and troubleshooting reference for complete backup, restore, cleanup, and reset procedures.

Development

Common Commands

Command	Purpose
pnpm web:dev	Start Web and launch the local daemon on demand
pnpm daemon:dev	Start the daemon only
pnpm desktop:dev	Build dependencies and start Electron in development mode
pnpm test	Run workspace unit and integration tests
pnpm typecheck	Run TypeScript checks across the repository
pnpm build	Build every workspace
pnpm e2e	Run Web Playwright E2E tests
pnpm smoke:ci	Run the fake-Codex Runtime smoke test
pnpm perf:check	Check the recorded performance baseline

Before submitting a change, choose verification that matches its impact, as described in the contributing guide. Docs, copy, and style changes need only relevant checks; shared behavior and Runtime changes need targeted module tests and typechecks. Run full workspace tests or builds when the affected scope requires them, and report what you ran in the PR.

Changes to Desktop, Host Bridge, the Runtime proxy, or shared frontend workflows also require Web/Desktop consistency tests, packaged application E2E, and Web build hash verification. Passing Web unit tests alone does not establish Desktop release readiness.

The real Codex smoke test is disabled by default. Enable it explicitly with:

OPENCREATOR_RUN_REAL_CODEX_SMOKE=1 \
pnpm --filter @opencreator/daemon test -- test/smoke/real-codex-smoke.test.ts

Documentation

• Use OpenCreator: Quick Start · User guide and troubleshooting
• Develop and extend: Contributing guide · Code of Conduct · Contributing a Skill · Contributing a creation template · Runtime API v1 · Visual component guidelines
• Maintain and release: Codex-native Runtime design · Desktop release runbook · Windows Desktop release guide

Translation Convention

The root README.md is the canonical English document. Maintained translations live at docs/<locale>/README.md. Add a language to the switcher only after its full document has been translated and synchronized with the English structure.

Community

The Crew

Each crew member is responsible for their area, including its standards, contribution reviews and merges, and community support.

Contributors

Thanks to everyone who has taken part through code, documentation, feedback, issue reports, Skills, illustraions, and ideas. This README list is maintained separately from GitHub's automatically generated Contributors graph.

Contributing

Contributions are welcome in these areas:

Type	What to contribute	Where it lives	Ship size
Code	Bug fixes, creator workflows, shared features	apps/web/, apps/daemon/	One focused PR with tests
Skills	Reusable Agent workflows	skills/	One folder with SKILL.md and optional references → guide
Creation templates	Reusable image, video, or cover presets	template/	One folder with template.json plus assets → guide
Illustration and design	Original illustrations, icons, or UI designs	An agreed asset location	One PR with previews, source files, and license
Third-party service integrations	AI or media provider support	Relevant Web or Daemon modules	One PR with error handling, credential safety, and tests
Documentation and translations	Docs improvements or new locales	README.md, docs/, docs/<locale>/	One PR

The full guide — including local setup, review criteria, and common rejection patterns — lives in CONTRIBUTING.md (available in 10 languages).

Star History

OpenCreator was formerly named KrillinAI. This chart covers the repository's full history across the rename.

Related Projects

Project	Role
OpenAI Codex	The Agent execution engine behind model access, reasoning, tool calls, sessions, Skills, and MCP integration.
yt-dlp	Inspects supported public media links, lists available formats, and downloads video or audio for creator workflows.
FFmpeg	FFmpeg and ffprobe handle media conversion, composition, frame extraction, and output validation.
Whisper, whisper.cpp, faster-whisper, and WhisperKit	Cloud and platform-specific local speech-transcription options selected according to available Runtime capabilities.
React	The shared user interface foundation for the Web and Desktop experiences.
Fastify	The HTTP and API foundation of the local Runtime.
Electron	The Desktop host for native system capabilities, application lifecycle, and packaging.
SQLite	Local persistence for projects, conversations, Runs, schedules, memory, and other workspace data.
Model Context Protocol	The open protocol used to connect external tools and services to the Agent workspace.

---

OpenCreator · Create locally, work continuously.