JarvisX-Cowork
Open Claude Cowork: A Personal AI Creative Assistant for Everyone
Turn a terminal-only AI into a visual, collaborative, and creative desktop companion.
English | 中文
🎬 Demo Video
👆 Click the image above to watch the demo video
JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization Yunlong Lin, Lingqing Wang, Zixu Lin and Kunjie Lin, etc.
[NeurIPS' 2025] JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent Yunlong Lin, Zixu Lin and Kunjie Lin, etc.
💡 What We're Building (And Why It's Different)
Many "cowork / office agents" focus on writing emails, filling spreadsheets, and running workflows.
JarvisX-Cowork goes further: building a "Personal AI Creative Assistant" for everyone — when you're out of ideas, it can search the web for references; when you need output, it can take you from copy to visuals all the way through.
Think of it as a creative workflow:
Blank canvas → WebSearch for references → generate images → refine (Lightroom integration) → create videos → build stunning demos / decks / docs
At the same time, it keeps the core strengths of "Open Claude Cowork":
- Anthropic API compatible: reuses
~/.claude/settings.json(no reinventing the wheel) - Desktop visualization: streaming output, message cards, session management
- Controllable & auditable: key tool operations require your confirmation (permission panel)
✨ What You Can Do With It
- Creative & content: write copy, proposals, scripts, generate posters/illustrations, create presentation/PPT structures, produce project documentation
- Visual creation: text-to-image, image-to-image editing, a refinement workflow from "decent" to "polished" (with professional editing tool integration)
- Video capabilities: generate short videos from text/images for product showcases, event teasers, social media content
- Real-time information: search web/news/images and provide citable summaries with sources
- Dev collaboration: write code, edit code, run commands, organize files (the workflow you know)
The goal isn't just an assistant that "does your office work", but one that "helps you bring ideas to life". From inspiration to output, the fewer tools you switch between, the better.
✅ Creative Tools Checklist
| Feature | Main Capabilities | 📖 Docs | |:---|:---|:---| | JarvisArt | Smart retouching, AI color grading, Lightroom integration | 🚀 Model Deployment · 💻 Client Usage | | WebSearch | Web/news/image search (Tavily API) | 📖 Guide | | Nanobanana | Text-to-Image generation | 📖 Guide | | Nanobanana-Edit | Image-to-image editing, mask editing | 📖 Guide | | Sora2 | Text-to-Video / Image-to-Video | 📖 Guide |
The table above focuses on "creative capabilities". Beyond this, the project also inherits common baseline capabilities from the Claude Code/Claude Agent ecosystem (files/commands/web/tasks, etc.).
Claude Code (Baseline Capabilities) Overview
| Category | What It Does (Examples) | |---|---| | File operations | Read/write/edit files, batch search and locate issues (e.g., Read/Write/Edit/Glob/Grep) | | Command execution | Run builds, install dependencies, script execution, automation pipelines (e.g., Bash) | | Web capabilities | Fetch web content for reference retrieval and context (e.g., WebFetch) | | Task planning | Break down complex goals into steps, continuously push forward and report progress (e.g., Task/Todo) | | Safety confirmation | Confirm and authorize potentially destructive operations (Human-in-the-loop) |
🚀 Quick Start
Option 1: Download Release
Option 2: Build from Source
Prerequisites
- Bun or Node.js 22+
- Python 3.11+ (required when using creative skills)
# Clone the repository
git clone https://github.com/DevAgentForge/JarvisX-Cowork.git
cd JarvisX-Cowork
# Install dependencies
bun install
# Development mode
bun run dev
# Build production version
bun run dist:mac-arm64 # macOS Apple Silicon
bun run dist:mac-x64 # macOS Intel
# Start the app
open "dist/mac-arm64/JarvisX-Cowork.app"
open "dist/mac/JarvisX-Cowork.app"
Troubleshooting Bun Install/Build Issues
If you encounter issues with bun install or bun run dist:* (such as hanging, timeout, or build failures), please refer to the detailed troubleshooting guide:
👉 Bun Install/Build Troubleshooting Guide
⚙️ Configuration
In-App Configuration
- Option 1: One-click JSON Import: Open App → Settings → Import Config, select
configs/jarvisx-config.example.json, then replace the placeholder Keys/URLs with your own. - Option 2: Manual Input: Fill in API Key / Base URL / Model directly on the same settings page, and enable skills and fill in corresponding keys as needed.
{
"$schema": "jarvisx-config-v1",
"version": "1.0",
"api": {
"baseURL": "https://api.anthropic.com",
"apiKey": "sk-your-anthropic-api-key-here",
"model": "claude-sonnet-4-5-20250929",
"apiType": "anthropic"
},
"skills": {
"websearch": { "enabled": true, "apiKey": "tvly-your-tavily-api-key-here" },
"nanobanana": { "enabled": true, "apiKey": "sk-your-nanobanana-api-key-here" }
}
}
Test API Mirrors (Optional)
To make the experimental environment easier to reproduce, you can use third-party API mirror sites during testing (unofficial, not required).
We make no advertisement or endorsement; please evaluate stability, compliance, and data security risks on your own.
- OpenAI/Anthropic compatible API (test):
https://www.sssaicode.com/ - Generative model API (Nanobanana / Sora, etc., test):
https://api.bltcy.ai/
Tip: For production use, prefer official or self-hosted services you trust, keep your keys secure, and avoid committing keys to the repository.
🛠️ Development Guide
# Start development server (hot reload)
bun run dev
# TypeScript compilation
bun run build
# Linting
bun run lint
More details (architecture/modules/skill extensions): docs/summary/PROJECT_ANALYSIS.md
🤝 Contributing
The project is continuously being improved. PRs from interested contributors are welcome!
🙏 Acknowledgements
JarvisX-Cowork is a secondary development based on the open-source project Claude-Cowork. Thanks to the original authors and community.
Project origin and inspiration: DevAgentForge/Claude-Cowork.
We also thank Anthropic for their excellent Claude Cowork product: Cowork: Claude Code for the rest of your work.
🌤️ Discussion Group
If you have any questions during the trial, running or deployment, feel free to join our WeChat group discussion!
📄 License
MIT License - See [LICEN