"Porcupine AI team on AMD Developer Hackathon: ACT III Hackathon"
Team Idea
Building an AMD-powered version of Porcupine, an existing open-source autonomous AI agent focused on safe autonomy. Porcupine can take high-level goals, use tools and computers, recover from failures, and operate with explicit permission boundaries. For ACT III, we want to build and benchmark an AMD-accelerated agent runtime using AMD GPU inference, local/open models, tool use, model routing, and measurable autonomous workflows. The core Porcupine project already exists, so we are not starting from zero. Looking primarily for teammates with experience in AMD GPUs, ROCm, local model inference, optimization, back-end systems, or polished demo/UI work. I care more about people who build and test seriously than titles.
Team Members
.png&w=256&q=75)
.png&w=256&q=75)
Submission
Submission draft in progress