AI-native IDE with agentic workflows, iPhone emulation on Windows/Linux, PyTorch ML Studio, and ROCm-optimized local AI. Built for security researchers and cross-platform developers.

Dashboard for InferenceX™, Open Source Continuous Inference

Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.

A lightweight AMD GPU monitor for Linux. Real-time temperature, clock, load, VRAM + one-click power-mode switching in a tray-resident mini app. Tauri v2 + React.

A management dashboard for Lemonade Server. This extension provides a visual interface to manage your Lemonade models, backends, and system settings directly within VS Code.

Install PyTorch: Target CUDA, ROCm, or CPU on Linux, Windows, or MacOS (arm64/x86_64) with Supported Python Versions

An AI-powered pipeline translating Japanese ASMR to Chinese. Features automated ASR transcription, DLSite metadata scraping, surgical audio repair, and context-aware LLM translation.

GPU-accelerated stem separation deck for DJs - Tauri + Demucs/BS-Roformer on AMD ROCm for Windows. Drop a track, pull acapellas, drums, bass & synths as DAW-ready WAVs.

Post-quantum secure enterprise AI gateway featuring client-side PQC encryption, dynamic hybrid workload routing, and isolated open-source LLM inference accelerated by AMD ROCm. Built for the AMD Developer Cloud Hackathon (Track 3).

Manage Lemonade Server models, backends, and settings within VS Code using a visual dashboard with real-time updates and chat interaction.

FarmiPal — An AI-powered agricultural assistant for smallholder farmers in East Africa. Features agentic crop disease diagnosis, RAG-powered farming chat, real-time market intelligence, and surplus risk detection to prevent post-harvest losses. Built with Next.js, Django, and AMD ROCm.

An interactive AI-driven sports analytics simulation platform. It functions as a hybrid between an instant search interface and a sports management game.

ENZIU audits your actual insurance policy PDF and returns a scored ENZIU Index based on Clarity, Coverage, and Claim Efficiency, with red flags, page citations, and a Deep Dive Q&A. No accounts. No stored data.

Enterprise DevSecOps pipeline automating NVIDIA CUDA to AMD MI300X migration using deterministic translation and a Mixture-of-Agents (MoA) architecture.

One sentence in, trained computer vision model out, zero human labels. An autonomous agent swarm (FLUX.2 - SAM 3 - Gemma 4) running entirely on one AMD Instinct MI300X (AMD Compute used). AMD Developer Hackathon ACT II.

The Operating System for Autonomous Intelligence on AMD AI Fabric — AMD Developer Hackathon ACT II

On-device AI wellness co-pilot — task breakdown, energy, hydration & expense scanning, all running entirely on your phone. No cloud, no accounts. Trained on AMD MI300X, powered by ExecuTorch.

A lightweight setup for serving LLMs using vLLM with AMD ROCm GPUs