GitHub Repository

Your codebase was probably AI-generated. Get a better handle on it. Noodles creates interactive diagrams that visualize how your code actually works, so you can understand what the AI built without reading every line.

1,275 starsPython

Noodles – Turn any codebase into a diagram with Claude and Tree-sitter

Name: Noodles – Turn any codebase into a diagram with Claude and Tree-sitter
Availability: InStock
Author: unslop

by unslop·Feb 24, 2026·6 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemShip It

Tree-sitter + agentic flow ~50x faster than raw LLM calls, but codebase visualization is crowded category.

Strengths

•Tree-sitter AST parsing before LLM call is smart—reduces hallucination and token waste compared to naive code-to-diagram LLMs.
•Practical dual-mode (repo + PR analysis) with GitHub integration solves real onboarding friction without server overhead.

Weaknesses

•Language support limited to Python/JS/TS; other languages require grammar+detection work, fragmenting utility.
•Codebase visualization tools exist (code2flow, Sourcetrail, IDE plugins); unclear differentiation beyond 'AI-enhanced' branding.

Post Description

I built a CLI tool that turns codebases and PRs into diagrams so you can quickly understand how things fit together. Originally made it because I couldn't follow my own AI-generated repos.

Just shipped a big update:

- Switched from D2 to Mermaid for rendering - Tree-sitter AST parsing + agentic flow instead of raw LLM calls. ~50x faster. - Works on any GitHub repo or PR, not just local - Dropped the web frontend, it's just a CLI now - Published as a pip package

Still a ton to improve and I'm building fast. Feedback, issues, PRs all welcome.