Yun-Zhi Lin@yun193671

ThreatHunter is an AI-powered cybersecurity threat intelligence platform built for Track 1: AI Agents & Agentic Workflows. It helps security teams move beyond raw vulnerability lists by turning package, source-code, and configuration findings into prioritized, evidence-backed remediation decisions. Unlike a RAG chatbot, ThreatHunter does not rely on document retrieval as its core architecture. It uses a tool-driven, auditable multi-agent workflow that coordinates an Orchestrator, Security Guard, Scout, Intel Fusion, Analyst, Critic, and Advisor. These agents gather and validate evidence from OSV, NVD, GHSA, OTX, EPSS, CISA KEV, exploit intelligence, and ATT&CK-style signals. ThreatHunter analyzes exploitability, chained risk, repeated findings, and remediation priority, then produces structured JSON reports with actionable recommendations. Memory, JSONL checkpoints, and a FastAPI + SSE dashboard make the workflow replayable, observable, and suitable for live demonstration. For AMD alignment, ThreatHunter is designed to use an AMD Developer Cloud vLLM/OpenAI-compatible endpoint as the primary inference path, with fallback providers used only for demo resilience.

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.