Noodles – Explore AI-generated codebases through interactive diagrams
I built Noodles to help me keep up with the codebases my AI tools generate. Open sourced last week, hit 400 stars in 8 days. The problem: AI assistants scaffold entire features quickly, but leave you maintaining code you didn't write. When bugs appear, you're reverse-engineering your own project. Noodles generates interactive D2 diagrams showing execution flow: - Scans the repository and identifies entry points (CLI commands, routes, UI components) - Maps how execution flows from entry to outcome - Renders interactive overlays with clickable nodes and tooltips - Updates incrementally when…
In plain words
Noodles is an open-source tool that generates interactive diagrams showing how code executes, helping developers understand AI-generated codebases. It scans repositories to identify entry points like CLI commands and routes, then maps execution flow and renders clickable, interactive overlays. The tool updates as code changes. It's designed for developers maintaining code they didn't write, particularly from AI assistants, though performance degrades with very large codebases and diagram quality depends on code structure.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I built Noodles to help me keep up with the codebases my AI tools generate. Open sourced last week, hit 400 stars in 8 days. The problem: AI assistants scaffold entire features quickly, but leave you maintaining code you didn't write. When bugs appear, you're reverse-engineering your own project. Noodles generates interactive D2 diagrams showing execution flow: - Scans the repository and identifies entry points (CLI commands, routes, UI components) - Maps how execution flows from entry to outcome - Renders interactive overlays with clickable nodes and tooltips - Updates incrementally when code changes Technical limitations: - Performance degrades beyond ~100 files - Diagram quality varies by codebase structure - UI is minimal GitHub: https://github.com/unslop-xyz/noodles Feedback welcome!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
