Codag

See how your AI code actually works.

Codag analyzes your code for LLM API calls and AI frameworks, then generates interactive workflow graphs — directly inside VSCode.

Gallery

vercel/ai-chatbot

langchain-ai/langchain

trycua/cua

Why Codag?

AI codebases are hard to reason about. LLM calls are scattered across files, chained through functions, and wrapped in framework abstractions.

Codag does this automatically:

• Extracts the workflow — finds every LLM call, decision branch, and processing step across your codebase
• Visualizes it as a graph — interactive DAG with clickable nodes that link back to source code
• Updates in real-time — edit a file and watch the graph change instantly, no re-analysis needed

Features

• Automatic Workflow Detection — point at your files, get a full AI pipeline graph
• Live Graph Updates — edit code, watch the graph change with green highlights on changed functions
• Click-to-Source — every node links to the exact function and line number
• Export to PNG — export workflow graphs as high-resolution images

Supported Providers

LLM Providers: OpenAI, Anthropic, Google Gemini, Azure OpenAI, Vertex AI, AWS Bedrock, Mistral, xAI (Grok), Cohere, Ollama, Together AI, Replicate, Fireworks AI, AI21, DeepSeek, OpenRouter, Groq, Hugging Face

Frameworks: LangChain, LangGraph, Mastra, CrewAI, LlamaIndex, AutoGen, Haystack, Semantic Kernel, Pydantic AI, Instructor

AI Services: ElevenLabs, RunwayML, Stability AI, D-ID, HeyGen, and more

IDE APIs: VS Code Language Model API

Languages: Python, TypeScript, JavaScript (JSX/TSX), Go, Rust, Java, C, C++, Swift, Lua

Getting Started

1. Start the Backend

Codag uses a self-hosted backend powered by Gemini 2.5 Flash. You'll need a Gemini API key (free tier available).

git clone https://github.com/michaelzixizhou/codag.git
cd codag
cp backend/.env.example backend/.env
# Edit backend/.env and add your Gemini API key
docker compose up -d

Verify it's running: curl http://localhost:52104/health

See the full setup guide for manual installation.

2. Use It

1. Cmd+Shift+P / Ctrl+Shift+P → "Codag: Open"
2. Select files containing LLM/AI code
3. Explore the graph — click nodes, zoom, pan

Settings

License

MIT