Aron Shrestha@AronTalcha

Doc AURA is a living-documentation platform that turns any GitHub repository into self-maintaining technical documentation. It solves a problem every fast-moving engineering team has: documentation rots the moment a PR lands. Onboarding slows, knowledge becomes tribal, and developers stop trusting their own docs. Most tools generate docs once — Doc AURA maintains them continuously, treating documentation as a byproduct of development rather than a separate task. The system works in two phases. On initial setup, a Repo Analyzer parses the codebase with Tree-sitter to build a structured code graph of modules, APIs, and dependencies, while a Doc Generator produces high-signal artifacts — Project Overview, Architecture Overview, API Reference, Key Workflows, and Usage Examples. On every subsequent PR, a Change Detector maps the diff to affected components, a Doc Sync Engine updates only the impacted sections (no full regeneration), and a Reviewer Agent posts PR comments flagging undocumented changes or behavioral mismatches. The headline feature is the documentation diff — side-by-side added/modified/removed docs reviewed alongside code — paired with an interactive code graph built on React Flow that highlights blast radius across the system. The stack is FastAPI + Python on the backend, LLMs orchestrated via LangGraph for agent workflows, Tree-sitter for AST-level parsing, React + React Flow on the frontend, and JSON (with optional SQLite) for structured doc storage. Authentication runs through GitHub OAuth plus a GitHub App for repo access and PR webhooks. The differentiator is positioning: not a doc generator, but a continuous doc system, the value lives in keeping documentation correct over time, surfaced through doc diffs and impact-aware graph highlights at every PR.

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.

🌟 Explore new AI capabilities 🤝 Collaborate and build something extraordinary. 👥 Take part alone or form a team with other participants. 🎓 Receive guidance from expert mentors. 🏆 Compete for $20,000 in Prizes. 🧑🏻‍💻 Sign up before the Kick-Off Stream to secure your spot!

🗓️ This will be a 7-day virtual hackathon on 21 - 28 April 💻 Access AI21 Labs' state-of-the-art language models to build innovative applications 💡 Meet and learn from AI21 Labs and Lablab experts 👥 Join the community and find your team ✔️ All levels are welcome, AI tutorials and mentors are there to help you 🏆 Prizes and awards of up to $9000 API credits + $3500 cash ⭐ Receive a certificate of completion and Wordtune premium for submission 🐱‍💻 Sign up now! It's free!