Cartograph – AI-generated code documentation and architecture diagrams
Hey there HN! We're Vivek and Si-Yan from Cartograph (https://cartograph.app). We've built an AI-powered code documentation platform that automatically generates reference documentation and creates a visual interactive map of the codebase that serves as both high level architecture diagram and allows you to zoom in to specific implementations. How it works: We use static analysis to read a codebase and get its symbols and their dependencies, creating a complete map that includes function calls. We use LLMs (Gemini + Claude) to add metadata to this map, as well as augment it in…
What it does
In the maker’s words, at launch
Hey there HN! We're Vivek and Si-Yan from Cartograph (https://cartograph.app). We've built an AI-powered code documentation platform that automatically generates reference documentation and creates a visual interactive map of the codebase that serves as both high level architecture diagram and allows you to zoom in to specific implementations. How it works: We use static analysis to read a codebase and get its symbols and their dependencies, creating a complete map that includes function calls. We use LLMs (Gemini + Claude) to add metadata to this map, as well as augment it in cases where static analysis doesn't work (e.g. HTTP calls). This map is then used to create an interactive map that you can explore to understand the system of your codebase. This works on both monorepos and multi repo projects. We also make use of this map to generate reference documentation for various functions/classes/structs etc in the codebase. Some demo repos: NextJS e-commerce template: https://cartograph.app/share/demo/vercel-commerce-next-js-ec... FastAPI + React template: https://cartograph.app/share/demo/full-stack-react-fastapi-t... Rust tokenizers library: https://cartograph.app/share/demo/huggingface-tokenizers-rus... FastAPI/NextJS RAG chatbot: https://cartograph.app/share/demo/weaviate-verba-rag-chatbot... If you'd like us to process more public repos, please comment below and we will process it on our end. We plan to improve things significantly over the coming months, but we want to hear your feedback on our product and/or any use cases you think this could be useful for.
Does the same job
all alternatives →- IIIlograph – interactive architecture diagrams as code2020 · app.ilograph.com · ▲92
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 · 17d 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
