amd-rocm

面向 DeepSeek Harness 的本地图像生成插件（优化版）：经本机 ComfyUI 调用 Qwen-Image 2.1 生成图像，全部流量限于 127.0.0.1。本版增强推理性能、NVIDIA/Intel/AMD 显卡适配与 Windows/Linux 兼容。原作者 @奇迹与你，优化版 @yanfei0725。

A machine learning compiler for GPUs, CPUs, and ML accelerators

3D, LLM-driven adventure engine: a walkable three.js frontend plus a local-AI backend (AMD Strix Halo GGUF via llama.cpp, optional ComfyUI) where an AI narrator generates explorable 3D worlds and sentient NPCs you talk to. Strictly isolated contract-per-layer architecture. 3D sibling of gamentic.

RyFlow is an offline-first AI collaboration workspace. Run local LLMs, collaborate in real time over LAN, create tasks with plain English, index local folders and github repos and build a semantic knowledge graph that lasts. Zero cloud, zero cost, zero compromise.

ACRE (Adaptive Cognitive RAG Engine) is a RAG engine that reasons like a researcher: it decomposes questions, retrieves and critiques evidence, resolves contradictions across sources, and renders its reasoning as a live concept flowchart — not just a wall of text.

Built for AMD Developer Hackathon ACT II. A token-efficient routing agent cascading tasks through local code solvers and Gemma models on AMD ROCm before escalating to Fireworks AI.

AI Guardian for Malawi Kabaza & Taxi - Breakdown rescue, police & mechanic finder via WhatsApp. Built on AMD + Llama 4

🧠A Metacognitive Engineering Intelligence OS. NeuroSyn-Dev plans, compiles, and verifies code inside self-healing isolated Docker sandboxes and multi-agent debate boards. Powered by a hybrid local AMD ROCm GPU and Fireworks AI cloud.🚀