Roosa Yöruusu@ZtotheZ

Fully local AI voice assistant built with Faster-Whisper, Ollama, Piper TTS, and FastAPI. Supports real-time speech recognition, local LLM inference, browser microphone integration, and custom LoRA fine-tuned models without relying on cloud APIs.

Multi-agent infrastructure analysis platform that reviews Terraform configurations and operational metrics to identify configuration drift, resource waste, optimization opportunities, and infrastructure improvements through AI-assisted automated reporting

AegisOps AI is not a chatbot. It is a purple-team detection workflow engine: known attacker behavior becomes validated defensive readiness. Security teams cannot operationalize threat intelligence fast enough. Translating ATT&CK techniques into precise detections, SOC response guidance, and coverage validation is still mostly manual, creating generic rules, noisy alerts, and a bottleneck around scarce detection engineering expertise. AegisOps AI closes that gap with a 4-agent LangGraph pipeline: Threat Agent: generates high-fidelity ATT&CK simulation, Office-lineage process execution, encoded command patterns, script block telemetry, network callout patterns, and file artifacts. Detection Agent: converts those observables into a layered Sigma rule with primary, corroborating, and fallback signal layers, field mappings, Event IDs, and realtime SIEM/EDR detection plans. Response Agent: produces triage, containment, hunt, escalation, and reporting guidance tied to specific observables. Validation Agent: scores coverage across six dimensions, identifies production gaps, outputs structured JSON. Routed to a Qwen verifier sidecar. Live inference on AMD Instinct MI300X via vLLM on ROCm. Four simulation modes: Single Technique, APT Group, Kill Chain, and Hunting Topology Lab. Exports include Sigma YAML, Splunk SPL, SOC Playbook, VECTR JSON, and PDF report bundle.

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.