Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
RepeatFix finds repeat failures hidden in messy aircraft maintenance logs and helps technicians fix the next breakdown faster, using past fixes and cited FAA procedures. Running on AMD GPUs via AMD Token Factory.
AI maintenance copilot on AMD (Gemma-4-31B-IT): flags machine drift 39h before fixed alarms, explains the cause with cited manual sources and recommends safe actions.
Oscilla scores warehouse machine health from vibration, raises confirmed alerts, and turns them into work orders for technicians. A Gemma 4 assistant on AMD Token Factory explains each alert, and its answers are checked before they are shown
PitPulse Edge scores synthetic haul-truck telemetry at the site gateway with z-score and IsolationForest models, explains each alert in plain language, and lets a dispatcher approve a work order before a failure strands a truck.
Agentic Industrial Decision Twin on AMD ROCm GPUs & Evolus AI. Combines IoT signals and technical manuals via Shannon Information Gain (0.624 bits) to prevent €11,439 false teardowns and dispatch human-signed maintenance workflows.
InnerOS turns AMD-powered AI into governed real-world action. Gemma reasons, Evolus runs workflows, and Alexa/Inner Oz can query live operations and create governed GitHub tasks for AI agents, with approvals, evidence, and replay.
Spots damaged bearings from the motor current a drive already measures, tested honestly on bearings it never saw. Gemma on AMD Token Factory writes the technician's notes and shift plan, and every claim is checked in code first.
ShiftWhy is an AI-assisted industrial maintenance copilot that connects machine signals with maintenance history to produce an evidence-backed first assessment and safe next checks.
An open LLM (Qwen3-8B on vLLM, AMD Instinct MI300X) proposes plant maintenance and dispatch policies; a digital twin verifies them. On-time orders: 50.6% to 98.9%.
TrustForge is an autonomous software factory that builds, challenges, verifies, repairs and proves critical software behavior before it ships.
An AI-assisted engineering governance layer built on IBM Bob 2.0 that analyzes change intent, repository architecture, contracts, and dependencies to validate software changes before coding agents write code.
Tessera AI is an outcome-aware control plane for IBM Bob that routes tasks to the right workflow, independently verifies results, preserves failure evidence, and uses past outcomes to reduce rework and improve future routing.
UpgradePilot is an AI-powered CLI that scans your Node.js or Python project for breaking dependency changes, scores migration risk, generates a step-by-step upgrade plan, applies parallel codemods, and verifies tests pass — saving 80%+ of manual effort.
Ordo helps engineering teams maintain healthier software by automatically detecting technical debt, prioritizing risks, and generating roadmaps, test plans, and fix strategies.
For dev teams: Git catches line-level conflicts but misses ones that clash in meaning. We use IBM Bob to analyze each branch's intent and flag semantic conflicts before merge — stopping silent bugs before they reach production
An AI-powered tool that analyzes Python code changes using dependency graphs, test coverage, and Git history to produce evidence-backed impact reports before a change is merged.
A phone-friendly website that helps migrant workers keep their eShram record up to date, just by speaking, even with no internet, and only when they allow it.
A real-time voice agent that listens to a support caller, asks the right follow-up questions out loud, and turns a messy call into one clean, prioritized ticket, powered by AssemblyAI Universal Streaming.
InnerOS Physical Guardian turns existing cameras and building infrastructure into governed Physical AI, using SiMa.ai edge inference to detect real-world activity, evaluate security policies, propose bounded actions, and preserve verifiable evidence.
NIM Lab AI detects infrastructure problems, investigates root causes, recommends solutions, and helps engineering teams resolve incidents faster "so you can focus on shipping, not firefighting."
EdgeWatch monitors simulated IoT fleets, analyzes telemetry with AI, and predicts device failures before they happen through a lightweight edge-to-AI pipeline.
Deterministic Multi-Gate Telemetry Validation & Strict Prompt Grounding Toolkit Demonstration / Portfolio Project
Ghostchain Command Hub is an autonomous AI multi-agent platform bridging cloud backends with mobile terminals to execute real-time production workflows and automated crypto earning strategies.
Aura is a sovereign, neuro-symbolic AI operating system that turns natural-language intent into transparent, governed action through local parsing, agent collaboration, bounded experimentation, verifiable learning, and human-controlled decision gates.
Real-time quantum device digital twin with AMD MI300X GPU acceleration and intelligent triage agent that maintains state sync under extreme throughput conditions.
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.
AutOps is a self-healing AIOps agent that detects, reasons about, and resolves infrastructure incidents autonomously.
Factory Autopilot is an AI-powered predictive maintenance platform that monitors industrial machine sensor data in real time, predicts equipment failures, and generates intelligent alerts to reduce downtime and improve operational efficiency.
RAYS Studio is a decentralized OSINT AI agent network powered by FOGR and Spectrally Bounded Zero-Gated Adapters, enabling secure, privacy-preserving client-side fine-tuning and real-time orthogonal knowledge aggregation without server bottlenecks.
AIRA is an AI-powered autonomous manufacturing decision platform that combines multi-agent intelligence, Digital Twin simulation, and AMD Developer Cloud to deliver explainable, real-time operational decisions.