Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
Real-time quantum device digital twin with AMD MI300X GPU acceleration and intelligent triage agent that maintains state sync under extreme throughput conditions.
A hybrid, token-efficient AI agent for 8 task categories. Zero-token heuristic routing sends easy tasks to a bundled local model (free) and hard ones to the best Fireworks model, clearing the accuracy gate while minimising billed tokens.
FlowForge turns plain English into ready to import n8n automation workflows. We fine-tuned Gemma 3 4B on an AMD Radeon PRO W7900 using LoRA and real n8n templates taking the model from generating workflows to twenty percent fully valid schema JSON.
ForgeMind AI is an AI-powered software architecture assistant that transforms project ideas into complete technical blueprints, including system architecture, security recommendations, development roadmaps, and implementation guidance and etc.
On-prem, air-gapped AI coding agent + LLM cost-router for enterprises barred from cloud AI - 100% AMD, open-weight, Ed25519 tamper-evident audit. $0/token on-prem; cuts existing token bills 40–70%. AMD ACT I 1st-place winner.
A high-performance solar fleet intelligence and dispatch automation platform that calculates real-time soiling losses and automates technical field routing via WhatsApp, accelerated by an AMD ROCm pipeline and live Firebase architecture.
Agentic carbon, energy, and water footprint analyzer for AI workloads. Built for AMD Developer Hackathon Act II — Track 3 (Unicorn / Open Innovation).
TeleGenesis OS is an autonomous multi-agent network operations platform accelerated by AMD Instinct™ MI300X & ROCm to automate telecom diagnostics, offering vendor-agnostic connectors and digital twin simulation for sub-20 second incident MTTR.
An intelligent routing layer built in Python that uses a fast, lightweight classifier to dynamically route queries between a free local model and the Fireworks AI API, minimizing token costs without sacrificing output accuracy.
Project Raze is an enterprise AI security platform executing surgical machine unlearning on LLMs. It ablates targeted weights to guarantee GDPR Article 17 compliance and erase copyrighted data without destroying model utility, powered by AMD & Fireworks.
Takes a video as an input, extracts frames which are sent to a vlm, a description is generated and fed to an llm to generate captions
NetGuard automates the first stage of security incident triage by analyzing network logs with an AI model. It transforms raw security events into structured incident reports, helping SOC analysts quickly understand threats and respond effectively.
Loopkeeper uses a band of AI agents to track accountability in B2B workflows - detecting who holds the ball, reading the inbox for escalations, scoring case health, and triggering playbook rules so nothing falls through the cracks
High-performance microservice for parallel web data collection, structuring, and cross-analysis.
Leak Radar: a scalable pipeline that ingests sources, scans repositories and feeds, classifies leak candidates with ML, enforces policies, and sends alerts for exposed secrets and sensitive data.
Bob-SRE transforms the IBM Bob CLI from a simple coding assistant into a fully autonomous Site Reliability Engineer. By wrapping the AI in a robust orchestration platform, it automatically generates multi-stage Docker/Docker Swarm/Cloud infrastructure.
Spec-to-Ship converts plain-English software feature requests into structured engineering tasks and automated GitHub pull requests using IBM Bob IDE, watsonx Orchestrate agents, 7 GitHub API automation. Demo: https://spec-to-ship-pied.vercel.app/
AIRA autonomously triages, diagnoses, and fixes software incidents using Groq's Llama 3.3 70B and LangGraph. It analyzes errors, generates patches with confidence scoring, and auto-creates PRs or requests human approval—resolving incidents in <30 seconds.
FactoryFlow is an autonomous predictive maintenance and parts procurement agent for small-to-medium manufacturers
GhostTrace AI is an autonomous cyberattack investigation platform powered by AMD Instinct MI300X GPUs that uses AI agents to detect threats, reconstruct attack timelines, analyze multimodal evidence, and generate forensic intelligence in real time.
Solo builder shipping AI agent governance on AMD ROCm. Vaara is an open-source Python runtime that intercepts AI agent tool calls, scores risk with split conformal prediction, and writes a W3C PROV-JSON audit trail for EU AI Act Article 14 compliance.
Sigui: Vision-AI Security for agents. Powered by AMD MI300X/ROCm, it uses fine-tuned Qwen2-VL-7B to detect attack topologies in <50ms. It identifies threat "Topological DNA" that text engines miss. Real-time. Autonomous. Immutable. EIP-8259.
Blitz SOC is an explainable hybrid SOC workflow combining deterministic governance with AI-assisted incident reasoning using CrewAI, Qwen, and AMD ROCm/vLLM inference.
An autonomous AI agent that monitors real AMD GPU/CPU telemetry, learns which Windows optimizations work best for your hardware using a Deep Learning Neural Network, and applies them with human approval. 18 tools, real frametimes, zero cloud.
ArcSplit routes every workflow payment directly to the creators behind the pieces—LoRAs, tools, assets, and extensions—using USDC nanopayments so community builders earn every time their work is used.
NanoPay Platform is a payment gated AI app where users pay small USDC amounts per request, unlock higher throughput, and get transparent settlement, revenue splitting, and transaction logs across AI, wallet, and blockchain layers.
We are moving robotics from 'Human-Assisted' to 'Truly Autonomous.' Right now, Kiwibot is limited by how many humans they can hire to swap batteries. We are building the Autonomous Battery Exchange that removes the human cost entirely.