Sandbox
@Utopai-Research/pai-pro

Local filmmaking workspace for Claude Code and Codex

PAI-Pro gives your coding agent a local filmmaking studio with project files, reusable skills, and a visual workspace. You can use it to organize scenes, manage assets, arrange shots, and generate media through one shared API service.

340 stars36 forksJavaScriptUpdated 28d ago
Who it's for

Builders who want Claude Code or Codex to help run filmmaking work in a local project workspace.

What it delivers

You can keep film planning, asset management, and media generation in one agent-driven workflow instead of juggling separate tools.

What it does

Filmmaking skills

Includes skills for scripts, images, videos, voice, groups, and story-to-video workflows.

Canvas and timeline

Provides a visual canvas and timeline for arranging scenes, shots, and assets.

Agent setup files

Uses `CLAUDE.md`, `AGENTS.md`, `.claude/settings.json`, and hooks to shape agent behavior in the project.

Media API service

Offers one service for image, image pro, video, voice, and 4K upscaling generation.

Docker and local startup

Supports Docker-based startup and local setup scripts for Claude Code and Codex.

README

PAI-Pro

The local AI filmmaking studio, driven from your coding agent.

简体中文 · English

Try the hosted web service

Utopai Studios Discord Follow @UtopaiStudios
Claude Code supported Codex supported

PAI-Pro canvas view

What's PAI-Pro?

PAI-Pro is a local-first AI filmmaking workspace built around four things:

  • Your own Claude Code or Codex, capable agents connected to local project files, persistent context, and customized filmmaking skills. (Setup and agents)
  • End-to-end filmmaking skills for scripts, images, videos, and voice. (More skill details)
  • A visual canvas and timeline for designing scenes, managing assets, arranging shots, and keeping larger productions organized.
  • One API service for story media across image, video, voice, and 4K upscaling, so productions do not need separate providers for each step. (API service details)

Quick start

Use Claude Code or Codex to install PAI-Pro for you. Paste this into your agent:

Clone https://github.com/Utopai-Research/pai-pro, read the setup docs in README.md and docs/setup.md, then install PAI-Pro for my current agent. Ask me for my PAI_KEY, use Docker unless I ask for local development, and start the app when setup is complete.

ChooseCommands
Anthropic Claude CodeDocker: ./scripts/docker-start.sh
Local: if ports are busy, run ./scripts/stop.sh first; then ./scripts/setup --agent claude and ./scripts/start.sh
OpenAI CodexDocker: PAI_DEFAULT_AGENT_ID=codex ./scripts/docker-start.sh
Local: if ports are busy, run ./scripts/stop.sh first; then ./scripts/setup --agent codex and PAI_DEFAULT_AGENT_ID=codex ./scripts/start.sh

Open Docker at http://localhost:7588 or local at http://localhost:7443.

API Service

PAI_KEY gives each production one service for image, image pro, video, voice, and 4K upscaling, without separate provider keys for each step. Use the PAI Pro Developer Platform to manage keys, tasks, balance, and credits. It also supports less restrictive video moderation via asset preupload and helps support this project. Paid generations are staged first; for BYOK and exact payloads, see API Service.

CapabilityQualityTime# of referencesEstimated price
generate_imageGreat~10-30s16 imgs$0.07 / $0.10 / $0.15 for 1K / 2K / 4K
generate_image_proBest~3-6 min32 imgs$0.26 / $0.45 / $0.77 for 1K / 2K / 4K
generate_videoBest~3-6 min9 imgs / 3 vids / 3 auds$0.08/s / $0.20/s / $0.44/s for 480p / 720p / 1080p
upscalerBest1-min example: ~4-8 min landed1 video1-min example: $1.35 for 1080p->4K, $2.35 for 720p->4K
generate_voiceGood~5-15sN/A$0.01 per 500 input characters, rounded up

Resources

  • 💬 Discord — questions, ideas, support, and show & tell
  • ⚙️ API Service — developer platform notes, BYOK counterparts, and exact media JSON payloads
  • 🎬 Skills reference — how filmmaking skills route agent requests
  • 🚀 Setup and agents — choose Docker or host mode, configure Claude/Codex, and understand ports, auth, and permissions
  • 🏗 Architecture — viewer, CLI, canvas, and project-file layout
  • FAQ — common setup and generation issues
  • 🐛 Issues — bug reports only
  • 🤝 Contributing — contribution guide, proprietary-skills carve-out, and CLA flow

License

PAI-Pro is released under the PAI PRO Sustainable Use License, which permits personal use, non-commercial research, and internal business use. Commercial use of PAI-Pro Skills or enterprise-designated source code/Skills requires an explicit agreement; enterprise licenses are available.

Files in the repo

Repository payload27 top-level entries
  • .claude
  • .claude-plugin
  • .github
  • agent-templates
  • docker
  • docs
  • scripts
  • server
  • skills
  • web
  • .dockerignore
  • .env.example
  • .gitattributes
  • .gitignore
  • .nvmrc
  • AGENTS.md
  • CLAUDE.md
  • CODE_OF_CONDUCT.md
  • CONTRIBUTING.md
  • CONTRIBUTOR_LICENSE_AGREEMENT.md
  • docker-compose.yml
  • Dockerfile
  • LICENSE.md
  • README.md
  • README.zh-CN.md
  • SECURITY.md
  • VERSION

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More harnesses

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

42k
chaitanyagiri/
munder-difflin

A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents

6.8k
holaboss-ai/
holaOS

Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.

11k
QwenAudio/
qwen-audio-agent

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

2.4k
AMAP-ML/
LongHorizon-Harness

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

1.5k
code-yeongyu/
lazycodex

The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

3.4k