Hey there HN! We're Vivek and Si-Yan from Cartograph (<a href="https://cartograph.app" rel="nofollow">https://cartograph.app</a>). 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.<p>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.<p>Some demo repos:<p>NextJS e-commerce template: <a href="https://cartograph.app/share/demo/vercel-commerce-next-js-ecommerce-template-0f355afa-f09f-412c-bc89-808735aef26e" rel="nofollow">https://cartograph.app/share/demo/vercel-commerce-next-js-ec...</a><p>FastAPI + React template: <a href="https://cartograph.app/share/demo/full-stack-react-fastapi-template-522e71ab-074d-4e05-b5b0-f786d4b0b1aa" rel="nofollow">https://cartograph.app/share/demo/full-stack-react-fastapi-t...</a><p>Rust tokenizers library: <a href="https://cartograph.app/share/demo/huggingface-tokenizers-rust-2ab46bae-1912-4368-ae8c-6a0b3c301d83" rel="nofollow">https://cartograph.app/share/demo/huggingface-tokenizers-rus...</a><p>FastAPI/NextJS RAG chatbot: <a href="https://cartograph.app/share/demo/weaviate-verba-rag-chatbot-f674a15d-1f43-4864-8c68-6a5c786762de" rel="nofollow">https://cartograph.app/share/demo/weaviate-verba-rag-chatbot...</a><p>If you'd like us to process more public repos, please comment below and we will process it on our end.<p>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.