An open-source AI agent platform offering no-code workflow building with dynamic graph-based solutions powered by the Actor Model, supporting multiple LLM integrations and real-time monitoring.
One-Minute Overview#
CraftGen is an AI platform designed for both technical and non-technical users, featuring visual canvas-based AI workflow building with support for hundreds of proprietary and open-source LLMs, agent capabilities, model management, and real-time monitoring. It bridges the gap between advanced AI technology and practical usability, suitable for rapid prototyping to production deployment.
Core Value: Seamlessly integrate AI into every workflow with a no-code platform that creates powerful solutions without requiring programming knowledge.
Getting Started#
Installation Difficulty: Medium - This is a monorepo project using pnpm-workspace, requiring Node.js and TypeScript knowledge
# Clone repository
git clone https://github.com/craftgen/craftgen.git
# Install dependencies
cd craftgen
pnpm install
Is this right for me?
- ✅ Data Analysis Automation: Connect LLMs and data sources through visual workflows
- ✅ Content Management Systems: Use agents to automate content creation and distribution
- ✅ Custom AI Assistants: Create agents with tools based on Function Calling or ReAct
- ❌ Simple Text Processing: May be overly complex for tasks that don't require complex workflows or agents
- ❌ Existing AI Service Integration: Unnecessary if you only need direct OpenAI API integration
Core Capabilities#
1. Visual Workflows#
Build and test powerful AI workflows on an intuitive canvas, combining all platform features for complex automation. Real Value: Create sophisticated AI solutions without writing code, significantly reducing technical barriers.
2. Comprehensive Model Support#
Seamless integration with hundreds of proprietary/open-source LLMs from dozens of inference providers and self-hosted solutions, including GPT, Mistral, Llama3, Ollama, and any OpenAI API-compatible models. Real Value: Flexibly choose the most suitable models without being limited to a single vendor, optimizing cost and performance based on specific needs.
3. Agent Capabilities#
Define agents based on LLM Function Calling or ReAct, add pre-built or custom tools, or create tools on demand. Real Value: Create intelligent agents with specific capabilities that automate tasks and improve productivity.
4. Real-time Monitoring#
Provide complete workflow visualization and monitoring features. Real Value: Real-time understanding of AI workflow execution status, facilitating debugging and optimization.
Tech Stack & Integration#
Development Languages: TypeScript, JavaScript, Rust, MDX, CSS Major Dependencies: Bun, Deno, pnpm, Turbo Integration Method: API / App-oriented Platform
Maintenance Status#
- Development Activity: Very active with multiple commits per week
- Recent Updates: Recently updated (v0.0.17 released July 11, 2024)
- Community Response: Actively responding to issues and contributions
Documentation & Learning Resources#
- Documentation Quality: Comprehensive
- Official Documentation: https://craftgen.ai
- Example Code: Available