Hamza4100/ai-workflow-agent
0
AI Workflow Agent - M1 (Milestone 1)
๐ค Core AI Decision Making System - Analyzes automation needs and generates intelligent workflows.
Features
- ๐ง AI Analysis: Uses Gemini 2.5 Flash to understand your automation requirements
- โ๏ธ Workflow Generation: Creates n8n and ComfyUI workflows from natural language
- ๐ Smart Search: GitHub repository search and web search (DuckDuckGo)
- ๐ฌ AI Chat: Conversational assistant for workflow planning
- โก Dual Mode: Fast keyword matching or intelligent LLM analysis
- ๐ Bilingual: Full English + Spanish support
How to Use
- Enable AI Mode: Toggle "๐ง Intelligent AI Mode" in sidebar for Gemini analysis
- Choose Language: Select English or Spanish
- Navigate Tabs:
- ๐ Home: Overview and getting started
- ๐ง AI Analysis: Analyze automation needs
- โ๏ธ Build Workflow: Generate n8n/ComfyUI JSON
- ๐ GitHub Search: Find open source projects
- ๐ Web Search: Search with DuckDuckGo
- ๐ฌ Chat: Conversational AI assistant
- Try Examples: Each tab has pre-filled examples
Technology Stack
- LLM: Google Gemini 2.5 Flash (REST API)
- Workflow Tools: n8n (automation) + ComfyUI (AI image generation)
- Search: DuckDuckGo (no API key) + GitHub API
- Framework: Streamlit 1.31.0
- Python: 3.11
Configuration
Required for AI Mode:
GEMINI_API_KEY: Get free key from Google AI Studio
Optional:
GITHUB_TOKEN: For higher GitHub API rate limits
Setting Secrets in HuggingFace Spaces:
- Go to Space Settings โ Variables and secrets
- Add secret:
GEMINI_API_KEY= yourkeyhere - Restart the Space
Fast vs Intelligent Mode
- โก Fast Mode (AI disabled): <100ms, uses keyword pattern matching, perfect for testing
- ๐ง Intelligent Mode (AI enabled): 2-3s, uses Gemini for deep analysis and complex workflow generation
Example Workflows
Customer Support Automation: Generate workflows that receive tickets, classify urgency, check knowledge base, create Jira tickets, and send notifications.
Image Generation: Create ComfyUI workflows for txt2img, img2img, upscaling, inpainting, and ControlNet.
Notes
- No Docker Required: Runs entirely on HuggingFace infrastructure
- No Training: Uses pre-trained Gemini model (no GPU needed)
- Minimal Dependencies: Only 8 packages for fast startup
- Free Tier: Works with free Gemini API (15 requests/minute)
Built for Milestone 1 of the AI Workflow Agent project.
