Discover AI Applications

Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.

FlowCast

Cleanrooms and control cabinets run fans at worst case because predicting a lower setting takes a CFD study. Flowcast learns from 7,500 airflow simulations to find the lowest safe setting in seconds, on AMD GPUs, and confirms it by simulation.

FlowCast

AMD ROCmClaude CodeGemma

VitaLoop 360

VitaLoop 360: one AMD-hosted Gemma 4 core that joins a manufacturer's five departments (factory, back office, sales, customer experience, care) through the production lot, with code computing every number and a person approving every action.

H3CT1CD3V3L0P

AMD ROCmAMD Developer CloudGemma+8

Shelf-Sense

"Photograph a shelf, get per-product counts, a compliance verdict, an estimated margin at risk and a restocking list. Vision on AMD; decisions in code."

MaachaCode

AMD Developer CloudToken FactoryStreamlit+1

scanota

scanota turns paper receipts and online invoices into one clean sales database for small merchants, then tells them what to restock. Vision models via AMD Token Factory read handwritten notes, then the math validates totals and forecasts demand.

burayot garut

Claude Coderest apiStreamlit+1

Assembly

An autonomous ML engineer for factories. Give Assembly a goal in plain language and it finds the right plant data, builds the dataset, researches and tests models, and deploys the ones that meet your targets, without any code or ML expertise from you.

Assembly

AMD Developer CloudClaude CodeDeepSeek V3+5

Aegis-Tritangtu: Constitutional AI on AMD

Aegis-Tritangtu (ISEAC) is a hardware-enforced Constitutional AI Governance platform and Zero-Trust MCP Firewall built on AMD Instinct MI300X (ROCm/vLLM) and AMD EPYC SEV-SNP. It solves a critical enterprise problem: companies want AI agents to process documents and run workflows via APIs and Model Context Protocol (MCP), but face severe risks of unauthorized actions, capability escalation, log tampering, and cognitive manipulation. Our solution enforces a Two-Domain Architecture (Rules R1-R5) that separates the Human Sovereignty Domain (HSD) from the AI Experiential Domain (AED), ensuring growing AI capability never automatically grants authority. Inside AED, a 3-node Tritangtu MARL cluster operates: Node Rama: Ethical guard holding a lexicographic veto based on the Panca Waluya reward tree. Node Resi: Dialectical engine using the 9-knife Nawa Sastra analyzer to strip manipulative framing, detect exculpatory omissions, and build 6-part Toulmin arguments. Node Ratu: Zero-Trust executor preparing Evolus AI MCP tool calls. Before any action crosses into HSD, our Security Gateway enforces Execute(x) = C(x) AND P(x) AND S(x) across 4 dimensions of Validated Experience Transfer (VET). How AMD Powers Aegis-Tritangtu: AMD Instinct MI300X (192GB HBM3) & ROCm vLLM: Hosts the entire Tritangtu multi-agent cluster and vLLM Semantic Router in unified VRAM without PCIe bottlenecks. AMD Ryzen AI NPU: Runs INT4 SLMs (<50ms) for pre-execution prompt filtering. AMD EPYC SEV-SNP (VMPL-0): Anchors our SHA-256 audit ledger and VCEK hardware attestation, detecting log omission attacks in <500ms (TEST-11A), enabling an out-of-band IRA kill-switch (TEST-11D), and safely handing high-risk cases over to humans when it should.

Triwikrama

AMD Developer CloudAMD ROCmQwen3

TEP Copilot: reasoning, not reciting

Control-room copilot for refineries and chemical plants: Gemma 4 on AMD proposes the root cause of an alarm flood, a deterministic gate strikes unsupported evidence, a human approves. A disguised twin tests that it reasons, not recites.

TEP_copilot

Token FactoryGemmaDeepmind+3

Quorum

Validating a business idea usually takes weeks of surveys and interviews, and a chatbot asked "would you buy this?" gives one opinion that represents nobody. Founders need a fast first filter that answers like different kinds of people do.

Kepler b-157

AI/ML APILlama 4rest api+1

ATLAS

ATLAS: An autonomous AI orchestrator for complex cloud infrastructures. It delegates tasks to AI agents via secure tools and projects real-time activity into a 3D digital twin, running on AMD GPUs.

ATLAS

CursorDeepSeek R1Gemma+5

Procedure Drift Finder

Procedure Drift Finder reads plant shift notes against written SOPs, finds where practice drifts, and proves it with the exact quote. AI proposes, code verifies, people decide. Runs on AMD GPUs. Synthetic data. Not a safety control.

SOP

AI/ML APIToken Factory

Yield Guardian: AI Root-Cause Agents for Fabs

Yield Guardian turns a chip-fab alarm into an approved fix. It reads real sensor data and classifies wafer defects (0.90 macro-F1), then AI agents on AMD investigate, write a report where every number links to its evidence, and an engineer signs off.

JO-DEV

AMD Developer CloudToken FactoryAnthropic Claude+2

NEXUS — AI-Powered Cyber Simulation

NEXUS simulates cyber incidents to compare AI-assisted and scripted defense strategies using measurable security, service availability, and resource outcomes.

vikaza

Qwen3OpenAIAI/ML API+1

TradeForensics: Commerce Action Copilot

AI diagnostics copilot connecting transaction logs, carrier fulfillment latency, and customer reviews into deterministic root causes and actionable operational remediation plans — accelerated by AMD Instinct MI300X.

RyzenShine

AgentOpsAIMLAI/ML API+9

RIOSE

RIOSE is a livestock simulation platform built for modern cattle operations, enabling producers and agribusiness teams to compare management scenarios, evaluate modeled impacts, and test decisions reproducibly.

RIOSE

AMD ROCmOpenAIrest api+2

MachineSage AI: Evidence-Based Maintenance Copilot

MachineSage AI helps factory technicians investigate machine incidents using sensor threshold checks, technical manual evidence, AMD-powered AI explanations, and human-reviewed troubleshooting recommendations.

MachineSage AI

StreamlitAMD ROCmAMD Developer Cloud

Wafer Defect Copilot: AI Yield Optimization

An AI process-engineer assistant for semiconductor fabs. It instantly classifies wafer defects and uses an AMD ROCm-accelerated Qwen2.5 LLM to generate cited troubleshooting guides, saving millions in scrapped silicon and machine downtime.

can AMD run DOOM

AMD ROCmGemini 3 proClaude Code+4

NexusForge - Industrial Decision Twin

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.

ChignoliLabs

NVIDIAAMD Developer CloudAMD ROCm+10

DossierMind — Evidence before advice

Proposed Track 3 – Reinvent Commerce. DossierMind uses AMD-powered AI to transform fragmented business documents into searchable, evidence-linked knowledge and actionable insights, helping accountants deliver better services to business clients.

Axiark

AMD Developer Cloud

ForgeGuard AI – Maintenance Triage on AMD

ForgeGuard AI tells maintenance technicians which machine to inspect first, why, and what to check. It detects unusual sensor readings, links maintenance notes, ranks machines and explains each case with AI on AMD Token Factory - every claim verified.

HORIZONS

Token FactoryVercelAI Studio+7

Proof-Carrying RAG on ROCm (Qwen3-VL-8B)

A retrieval-augmented question answering container for AMD GPUs that treats every answer as a claim that must be proven from the corpus before it is written. A resident Qwen3-VL-8B-Instruct (bf16, greedy, transformers on the mandated ROCm base) serves a unix socket; each query is a thin stdlib client that always writes a valid JSON file within budget. Indexing walks the corpus defensively (unreadable, encrypted, binary and empty inputs never stop it) and turns PDFs, DOCX tables, multi-sheet XLSX, CSV, logs, Python literals and images into atomic records, with RapidOCR plus VLM transcription for images. Retrieval fuses BM25 with an exact rare-ID index and follows ID chains across files. Withdrawn and superseded revisions are resolved before the model reads anything. Cross-sheet joins link a part's lead time or cost to the product that uses it, and PDF family tables become one record per product. A deterministic verifier checks the value against a token-boundary span in an eligible record, the question's product, quantity and unit, code literals over stale comments, and false premises; a chain guard re-reads log-to-ticket chains when a topical decoy wins. Finally the model answers a YES/NO warrant question over the evidence, which refuses unanswerable questions instead of guessing. Citations come from record identity and chain necessity. Validated on the real model against the sample (200/200, A100 and Radeon Pro W7900D under ROCm), 13 generated adversarial suites with held-out seeds, and a 300-file corpus with 61 images: p95 5.4 s per question, 22.5 GiB peak VRAM.

qsociety

AMD ROCmQwen3-VLHuggingFace Hub

Student Insurance Navigator

AI health insurance advisor for US college students. Can help to estimate cost, choose insurance, and save money.

Interstellar

Anthropic ClaudeCodexAMD ROCm+3

TwinVerdict

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%.

focampo

AMD Developer CloudAMD ROCmCursor+2

Grounded RAG Container for Mixed Enterprise Docs

We built a Retrieval-Augmented Generation container for AMD AI League Match 3. It is pointed at a folder of mixed documents (PDF, DOCX, XLSX, CSV, TXT/LOG, Python source, PNG/JPG) and answers each question with a short value-only answer plus the exact files it came from. If the corpus does not contain the answer, it returns an empty answer and no citations instead of guessing. The pipeline parses every file type defensively: unreadable, encrypted, unknown and empty items are skipped without stopping the index. Superseded or withdrawn document revisions are tagged and ignored. Images are read with a vision-language model (Qwen2.5-VL), and text is retrieved with hybrid search: BM25, sentence embeddings and an exact-identifier index, fused by reciprocal rank fusion. Multi-hop questions follow identifiers across files (for example, a log naming a ticket, then a database giving the fix version). Answers must be grounded in the retrieved text, and citations are limited to the files the answer actually needs. A resident daemon holds the models and the index, and app.py is a thin client over a unix socket, so each question runs in about a second after warm-up. The container is built on the mandated ROCm PyTorch image, with weights fetched at build time and no network use at run time. Development and testing used a 4 GB NVIDIA GPU; the AMD ROCm build is prepared and awaits testing on AMD hardware.

DoubleG

Qwen3-VLAMD ROCm

Grounded Multimodal QA on ROCm

GroundTruth RAG answers questions over a messy folder of enterprise documents and returns only the value plus the exact files it came from, running entirely on an AMD GPU with ROCm. Indexing: every file is parsed in its own isolated process with a timeout, so an unreadable file, an encrypted PDF, an unknown binary or a corrupt document is recorded and skipped instead of breaking the walk. We handle PDF, DOCX, XLSX (all sheets), CSV, logs and source code natively. Images and scanned pages are transcribed by Qwen2.5-VL-7B on the GPU. Serving: because every question runs as a new process, indexing launches a resident model server that loads the model onto the GPU once and warms it up. Each query is a lightweight client over a unix socket, answering in a few seconds. Answering: retrieval combines BM25 with automatic handling of withdrawn and superseded documents, plus an identifier hop that follows ticket and part numbers across files for multi-step questions. The model proposes an answer, then deterministic code takes over: values that do not appear in the corpus are refused, a verification pass checks the answer matches exactly what was asked, and citations are chosen by necessity rather than relevance. When the corpus does not contain the answer, the system returns an empty answer instead of guessing. Everything ships inside the image with no network access at runtime: one 7B model, about 46 GiB total.

Kernel Panic Room

GPT-4 VisionGPT-4Qwen3+3

Saudi Sign Intelligence – Grounded RAG on AMD

Saudi Sign Intelligence is a citation-exact Retrieval-Augmented Generation container built for AMD Instinct GPUs with ROCm. It answers questions about a folder of mixed enterprise documents with the value only, and cites exactly the files the answer depends on - nothing more, nothing less - or returns an empty answer when the corpus does not hold it. How it works: (1) One resident Qwen3-VL-8B (bf16) server is started by the container CMD and loads once onto the GPU; app.py is a standard-library thin client over a unix socket, so every question process starts in milliseconds and never reloads the model. (2) Defensive parsers for PDF (including scanned pages read by the vision model), DOCX tables in reading order, multi-sheet XLSX, CSV, logs, Python constants and defaults, YAML/TXT and images (OCR by the same VLM). Empty folders, unknown types, unreadable and encrypted files are skipped without stopping the walk. (3) Superseded revisions are detected from what a document says about itself and from revision families, then hidden, so the model never sees the decoy number. (4) Long-context first: when the corpus fits, every current file goes into the prompt; long logs are compressed to their events and rare identifiers instead of being truncated. (5) Citations are verified in code: the value must appear in the cited file, image answers are re-checked by looking at the picture, and chain links (log to ticket to KB article) are kept only when they hand on an identifier the question does not contain. Results: 10/10 on the official sample, 20/20 on a harder self-built stress set, 3-6 s per question. Built in Riyadh by a Saudi Sign Language interpreter and AI developer for trustworthy document Q&A for the Deaf community.

Saudi Sign Intelligence

AMD ROCmHuggingFace HubQwen3-VL

Robust Multi-Hop RAG for Enterprise Documents

Our solution for AMD Mini-Challenge 3 is a high-speed, autonomous Retrieval-Augmented Generation (RAG) system engineered to extract exact values and citations from unconstrained, mixed-format enterprise documents. Key Architecture & Capabilities: 1. Defensive Multi-Format Ingestion: The system features robust, zero-crash parsers for PDF, DOCX, XLSX, CSV, Python source code, and production logs. It natively isolates corrupted files, handles empty directories, safely skips encrypted documents without failing, and bypasses permission-locked files. 2. Multimodal OCR: Integrated optical character recognition (OCR) accurately transcribes pinout schematics, diagrams, and asset label images, enabling discovery of visual-only information. 3. High-Precision Hybrid Retrieval: Uses BM25 lexical token matching preserving technical identifiers, model names, ticket IDs, and revisions (e.g., TQ-40, ORR-1847, REV-C2, THERM_ALERT#). 4. Multi-Hop Reasoning & Citation Filtering: Implements automated entity chaining across disparate files (e.g., correlating production throttle logs with bug tracker resolutions) while strictly adhering to the "necessity, not relevance" citation rule. 5. High Performance: The indexing pass completes in under 1 second, and queries execute in approximately 0.25 seconds—far below the 30-second budget—with zero external web services or network dependencies.

DemonaireSid

AMD ROCmAMD Developer CloudEasyOCR+3

MC3: Hardware-Optimized RAG Pipeline for AMD GPU

This project presents a highly optimized, fully containerized Retrieval-Augmented Generation (RAG) pipeline developed for Mini Challenge 3 of the AMD AI Academy Challenge. Built strictly upon the mandated rocm/pytorch base image, the solution processes proprietary domain knowledge—including multi-modal documents, spreadsheets, and source code—to deliver accurate answers paired with exact file citations. Designed to strictly adhere to the zero-hallucination policy, the architecture ensures that responses are grounded entirely in the provided corpus. The system is engineered for seamless deployment on AMD hardware, utilizing /dev/kfd and /dev/dri device mappings for native GPU acceleration. By restructuring the pipeline into a persistent long-running process, it completely eliminates the startup overhead per question, ensuring the system easily fits within the stringent 30-second query budget. Despite massive physical constraints, the final environment was successfully packaged into a unified image and pushed to Docker Hub. This solution demonstrates robust handling of complex dependencies, encrypted files, and unknown data types, ensuring high-throughput hardware-accelerated inference in AMD Instinct and Radeon environments.

ChallengeLab

AMD ROCm

InsightVoice — Ask the Business by Voice

InsightVoice turns spoken business questions into evidence-backed investigations. Powered by AssemblyAI, it transcribes voice queries, analyzes real e-commerce data, and returns structured Insight Briefs with metrics, evidence, and recommendations.

InsightVoice

GroqGemini 3 Flash

EasyLedger: Sales Made Clear

EasyLedger helps small shop owners record sales by voice, fix mistakes, and turn their records into clear charts. Powered by AssemblyAI, it lets owners ask about sales and build a dashboard in everyday language.

Token Maxxing

CodexGithub Copilot

Rosewood: AI Phone Orders for Small Bakeries

A voice agent that answers a small bakery's phone: takes custom cake orders against live stock, greets regulars by name, routes allergy questions to a human, and shows the owner what callers wanted and couldn't buy.

AI_TITANS

Assemblyai Guardrails APIClaude CodeAI/ML API+2

30apps loaded