michaelzixizhou/codag
Visualize AI/LLM workflows in your codebase.
Building AI applications often involves complex chains of Large Language Model (LLM) calls spread across many files. This tool helps AI engineers visualize how their AI code actually works by analyzing the codebase, identifying all LLM API calls and AI framework usage, and generating an interactive workflow graph. You input your AI project's code, and it outputs a real-time, visual map of your AI agent's logic, complete with clickable nodes that link back to the source code.
499 stars.
Use this if you are an AI engineer or agent builder struggling to understand, debug, or onboard new team members to complex LLM-driven applications and need a clear, visual representation of the AI's workflow.
Not ideal if your project does not involve AI agents or LLM interactions, or if you prefer to trace code dependencies manually without visual aids.
Stars
499
Forks
41
Language
TypeScript
License
MIT
Category
Last pushed
Feb 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/michaelzixizhou/codag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
usalu/semio
🧩 Design-Information-Modeling for Kit-of-Parts 🏘️
dtyq/magic
Super Magic. The first open-source all-in-one AI productivity platform (Generalist AI Agent +...
nilooy/flowgpt
Generate diagram with AI
swark-io/swark
Create architecture diagrams from code automatically using large language models (LLMs).
gridaco/assistant
🤖 Bring your Figma design & development pipeline to the next level - with design to code,...