Brian Lai@brian9004

DynoDocs is an AI-powered architecture intelligence platform that turns a code repository into an interactive system architecture diagram. For this first phase, the project focuses on the Component Services View, which shows clients, API gateways, backend services, workers, databases, caches, queues, object storage, and external integrations. The system uses a hybrid approach: a deterministic analyzer scans the repository to extract verified architecture facts from code, config files, Docker files, APIs, service calls, database usage, and messaging patterns, while an LLM enriches the diagram with clearer labels, grouping, descriptions, and layout hints without inventing unverified nodes or edges. DynoDocs also includes a static bottleneck detection layer that highlights potential architectural risks such as long synchronous call chains, chatty services, missing pagination, possible N+1 database queries, external API dependencies, missing timeouts, and unbounded queues. Each diagram element includes evidence, allowing users to understand why a service, dependency, or risk appears in the diagram. The goal is to help developers quickly understand unfamiliar codebases, visualize data flow, identify structural performance risks, and maintain living architecture documentation as repositories evolve.

Grab your ideas, spin up compute, and start building what’s next! Start with $100 in AMD Developer Cloud credits and begin building right away. Get access to hands-on tutorials, workshops, and curated learning resources to help you build faster and go further. To unlock credits and join the hackathon, sign up for the AMD AI Developer Program. 🤝 Go solo or team up — ship something real. 💰 $21,500+ total prize pool & 1 × AMD Radeon™ AI PRO R9700 GPU up for grabs. 📍 On-site Venue (May 9-10): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📍On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.