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.

ChronosGraph: Temporal Web Verification Engine

ChronosGraph is a temporal web information retrieval and verification engine for AMD AI League Match 4. It answers a natural-language question by navigating seed pages and their links, within a 6-page and 2-hop budget, extracting claims from specification tables, JSON-LD and body text, and scoring them by relevance, freshness and version. When a stale 2023 page conflicts with a 2026 specification, the newer authoritative row wins, and the answer is always a verbatim quote with a citation and a SHA-256 evidence receipt. If no source contains verifiable evidence, it refuses instead of hallucinating. The public demo shows this clearly: Mode 1 resolves 128 GB versus 192 GB HBM3 and 5.3 TB/s, Mode 2 resolves $4.50 versus $2.85 per hour, and Mode 3 refuses a fictional Quantum Flux Toaster 9000. A short exact answer, such as $2.85, is shown separately from the full quote, with a citations list that is empty on refusal. Understand uses synonym groups, so throughput, fee, RAM and cost are matched to bandwidth, rate, memory and price. The engine was verified in an AMD notebook on ROCm, with 16 tests passed and a 6/6 benchmark, and the public demo runs on CPU with zero paid API keys.

ChronosGraph ROCm

StreamlitAMD ROCm

FormForge

FormForge turns exercise analysis into something people can understand. It shows a user’s original movement beside the same recording with its form corrected, deterministic pose geometry, multilingual AI coaching, and frame-timed voice guidance.

Van Gogh

AMD Developer CloudGemmaDeepSeek V3+2

Community Connect

CommunityConnect helps people in Genova and Liguria find practical, sometimes paid, local support, like tutoring or help with online forms. Seekers describe a need, review AI-suggested details, and see eligible providers ranked with an explainable score.

Community Connect

AIMLAMD Developer CloudAnthropic Claude+8

Wrench: compressor maintenance with cited answers

Wrench warns a technician before an air compressor fails, answers "what should I do" from the service manual with every quote checked word for word, and drafts a work order a person approves. Alerts come from an autoencoder, not a language model.

Wrench

Token FactoryGemma

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

BlackBox — Persistent Visual Memory

BlackBox gives cameras persistent memory, tracking objects across time and reasoning under uncertainty to answer questions about what likely happened when an object was no longer visible.

BlackBox

AMD Developer CloudAMD ROCmHuggingFace Hub+1

Factory Pilot 3D

AI maintenance copilot for production lines. A live 3D digital twin traces a fault to its root cause, explains it citing the manual, prices the downtime, and acts safely or escalates to a human. Runs on AMD Token Factory. Modular and scalable to any line.

Fugassa

Token FactoryVercelrest api+4

VisionForge OCR + Grounded RAG on AMD ROCm

Two offline AMD ROCm systems share this entry: VisionForge AI for multilingual visual OCR (Match 2) and Grounded RAG for document question answering (Match 3). Each has a separate public Docker image in the matching private image field. Both include pinned model weights and need no runtime model downloads or external inference APIs. Match 2 reads US and Chinese registration plates and road signs from PNG, JPEG and TIFF. A resident Qwen3-VL-2B-Instruct worker loads once; a thin Python CLI sends image requests over a local Unix socket and writes the required JSON text output. US jurisdiction banners are excluded; Chinese province symbols remain part of the registration. Direct ROCm code passed 17/17 own synthetic cases on an AMD Radeon Pro W7900D (16.01 s startup, 3.57 s for ten CLI calls, 4.790 GiB observed peak). GPU inference inside the final Docker image was not tested. Match 3 answers questions over PDF, Word tables, spreadsheets, CSV, logs, Python source, diagrams and photographed labels with exact file citations. When evidence is missing it returns an empty answer and no citations. Resident Qwen3-VL-8B and Qwen3-Embedding-0.6B models combine lexical and semantic retrieval, identifier links and a second evidence check. Direct GPU code passed 287/287 development questions with answers and exact citation sets, plus 47 Linux tests. Peak PyTorch reserved memory was 19.87 GiB. Full Docker plus AMD GPU launch remains unverified because the free notebook has no container runtime. Both images preserve the required ROCm base. The tests use development or self-generated cases and do not establish an official hidden-set score.

Lord

AMD ROCmAMD Developer CloudQwen3-VL+1

Crash Guard: AI Traffic Accident Detection System

Crash Guard uses a fine-tuned YOLOv8 AI model to detect traffic accidents from camera feeds, record video evidence, and send real-time alerts with GPS locations to emergency responders through a connected Flutter mobile and web application.

LidArc

YOLOv8rest apiReinforcement Learning+3

ROCm RAG: Cite-or-Refuse Document QA

This project implements a retrieval-augmented generation (RAG) system for the AMD AI League Match 3 challenge, running entirely on AMD ROCm hardware. The system ingests a mixed corpus of PDF, DOCX, XLSX, CSV, TXT, and image files, applies structure-aware chunking, and builds a dense vector index using Qwen3 embedding models. At query time, it retrieves the most relevant chunks and generates answers with an instruction-tuned language model, returning exact file citations for every answer. A core design principle is cite-or-refuse: when retrieved evidence does not support an answer, the system refuses rather than hallucinating, which is critical for citation-accuracy scoring. The full pipeline is packaged as a single ROCm container image that completes startup and indexing within the required time limits. Both the container image and source code are public.

solodog

AMD ROCmHuggingFace Hub

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

WebRetriever — Deterministic Web Retrieval Agent

WebRetriever is an autonomous web information retrieval agent built for AMD AI League Match 4: Intelligent Web Information Retrieval. Ask in plain English and get back the specific information you asked for, with the exact source URLs behind it — or an honest refusal when no verifiable answer exists. How it works — five-stage pipeline with a deterministic core: Understand — parses the request into intent (price, contact, hours, spec, definition, how-to, date, fact), entities, and 2–4 search query variants. No ML model required. Search — provider chain with automatic fallback: TinyFish Search for the best quality (JS-aware), and DuckDuckGo HTML as the keyless fallback with no signup needed. Fetch + navigate — fetches top hits, then follows promising in-page links within a fixed budget (8 pages, 2 hops) when the answer looks like it is one click deeper. Extract — structure-aware parsing: JSON-LD (Product, Organization, FAQPage), HTML tables such as spec sheets, intent-specific patterns for prices, phone numbers, emails, hours and dates, plus ranked text spans. Verify — every candidate is checked against its own source text; independent multi-source agreement boosts confidence. If nothing is supported by evidence, the agent refuses instead of guessing. The core pipeline uses no LLM, so results are reproducible and cheap. Citations are mandatory, and the agent runs on the free tier with no paid APIs. MIT licensed and Docker-ready, with 12 unit tests.

ArcOmega

rest api

Compressor Maintenance Copilot

Catches compressor faults hours to days before they stop the line, explains them in plain language with cited manual pages and past repairs, and drafts the work order. An Evolus agent on an open model running on AMD GPUs.

gheware

AMD Developer CloudStreamlit

Silent Key RAG: cited answers on AMD ROCm

Silent Key RAG is a single container built on the mandated ROCm PyTorch base image, with its layers kept byte for byte so the base check passes. One resident process loads Qwen3-VL-8B once and keeps the index in memory, so each question pays only for retrieval and one model call. Every file goes through a defensive parser. Empty folders, unreadable and encrypted files, and unknown formats are skipped and logged instead of crashing the run. Images are read by the vision model, so answers that only exist inside a picture are still found. Retrieval is exact BM25 over chunks. The model proposes an answer and its sources; deterministic code then checks that the answer really occurs in a readable file, keeps exactly one answer file (current over superseded) plus a second only when it is a genuine bridge, and runs a short yes or no check that turns near misses into refusals, because citations are graded as an exact set. When nothing in the corpus supports an answer, the container refuses rather than guessing. The image ships its own weights, needs no network at evaluation, and is sized for the 1 to 48 GiB VRAM window. Match 4 (Intelligent Web Information Retrieval): the form has no Mini Challenge 4 Image field yet, so the image is listed here. Mini Challenge 4 Image: ghcr.io/silentkeytech/mc4-web:v1 (public). It answers each question with one exact value and its source page, runs on the same ROCm base image, and scored 10 of 10 on our own tasks on an AMD Radeon Pro W7900D.

Silent Key Technologies

AMD ROCmQwen3-VLHuggingFace Hub

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

AMD AI League: RAG & OCR on ROCm

What we've built so far in the AMD AI League — everything on AMD GPUs with ROCm: MC1: onboarding, AI Academy courses and the ROCm certification. Done. MC2: OCR from images — license plates, stop signs, speed limits, work-zone signs; also blurry, dark or glaring shots. Output normalized to the challenge rules. MC3: questions over a messy document corpus (PDFs, Office files, spreadsheets, logs, code and images, some unreadable by design). Answers are copied from the documents, never guessed; unanswerable questions get an empty answer on purpose. A vision model reads labels and pinouts. MC4+: to come as the league continues. Write-ups on our blog (derkosi.github.io); code on GitHub. AI note: built with AI assistance (AutoClaw + GLM 5.3-Flash). At runtime everything runs locally on the AMD GPU with open models.

Kosi IT

openclawAMD ROCmAMD Developer Cloud+1

simply: plate OCR and cited document RAG

Two containers from one codebase, both running Qwen3-VL-8B on the AMD GPU, built on the mandated ROCm base image. In each, start.sh launches a server that loads the model once and keeps it on the GPU. app.py is a thin client over a unix socket, so no image or question pays for loading the model. Match 2 (OCR) reads the plate number or sign text from one PNG, JPEG or TIFF image. One prompt spells out the transcription rules: the plate number without the state name or slogans, the province character kept on Chinese plates, every word of a sign from top to bottom, and a bare number with no unit. A small clean-up step removes labels, quotes and line breaks. Match 3 (RAG) answers questions about a folder of mixed company files and cites only the files the answer came from. The index pass reads PDF, Word (including tables), Excel (every sheet), CSV, logs, Python and images, and the same model reads text printed in images and scanned pages. Locked, encrypted and unknown files are skipped one at a time. A small corpus goes to the model whole. A larger one goes through BM25 plus ID linking, so a ticket number found in a log pulls in the row it points to. The model returns an answer and a quote from each file it used. Plain code then checks every quote against its file, refuses if the answer is not in a cited file, and keeps a file only if it hands an identifier to the next step. Questions the files cannot answer get an empty answer and no citations. Torch is pinned to the ROCm build and checked during the build, and the weights ship inside the images, so nothing is downloaded at run time.

simply

AMD Developer CloudAMD ROCmQwen3

RAG-MATCH3-AMD

RAG-Match3-AMD is an intelligent document question-answering system designed to help users find reliable information inside PDF, DOCX, spreadsheet, and text documents. The project uses Chroma Cloud as its vector database and retrieval engine. Documents are parsed, divided into manageable chunks, and transformed into dense embeddings with Chroma Cloud Qwen and sparse embeddings with Chroma Cloud SPLADE. Hybrid search and Reciprocal Rank Fusion combine semantic and keyword results to retrieve the most relevant evidence. OpenAI GPT-4.1 Mini then analyzes the retrieved context and generates a concise answer supported by citations to the original document. The system can also process images and scanned content through a vision-capable model. Document metadata, chunk indexes, and source identifiers are preserved to improve traceability and prevent duplicate results. The project provides a practical RAG workflow that separates document retrieval from answer generation. Chroma Cloud handles embedding and search, while OpenAI handles language understanding and response generation. This architecture makes the application suitable for learning materials, technical documentation, reports, and other knowledge-intensive document collections

cavenguy

AI/ML APIChromaCodex+6

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

ChipQC Guardian: Citation-Exact RAG on ROCm

ChipQC Guardian is a containerised retrieval-augmented question-answering system for Match 3, built on the mandated rocm/pytorch base with all weights shipped inside the image, so nothing is downloaded at evaluation. Pointed at a folder of mixed enterprise documents (PDF datasheets including withdrawn revisions, DOCX roadmaps with tables, XLSX part lists, CSV ticket databases, production logs, release notes, Python source, diagrams and photos) it indexes everything once, then answers each question with the bare value and the exact set of files the value came from. On AMD Instinct GPUs a resident server holds Qwen3-VL-8B-Instruct (bf16) and Qwen3-Embedding-0.6B behind a unix socket, so each per-question invocation is a thin client that returns in seconds and never loads a model. Ingestion is defensive: an empty directory, an unreadable file, an encrypted PDF and an unknown binary are skipped per file without stopping the walk. Spreadsheets and CSVs are indexed row by row with their headers so a ticket id lands on the row carrying its value; Python files contribute their constants and parameter defaults; images and image-only PDF pages are transcribed by the vision model at index time and re-read from the image at answer time. Retrieval fuses identifier-aware BM25 with dense embeddings, and a second hop follows identifiers the model asks for, which is what makes log, ticket and fixed-in-version chains answerable. Citations are filtered for necessity rather than relevance: withdrawn or superseded documents are dropped, chain links are kept only with directional evidence (a shared ticket, part or error identifier plus the question pointing at that document), redundant sources are reduced to one primary source, and a verification pass rejects values that belong to a different item. When the value is not in any excerpt the system returns an empty answer and no citations. It never guesses.

ChipQC Guardian

AMD ROCmAMD Developer CloudQwen3-VL+1

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

AMD Medical RAG & Prescription Scanner

The AMD Medical RAG & Prescription Scanner is a containerized Retrieval-Augmented Generation system designed and optimized for high-performance clinical data analysis in AMD ROCm environments. Clinical workflows deal with high volumes of unstructured and semi-structured documentation, including complex laboratory diagnostics, patient histories, and handwritten or printed prescription records. Extracting reliable dosages, administration frequencies, and patient metrics requires both domain accuracy and verifiable source grounding. This project addresses those challenges by implementing a decoupled, low-latency client-server architecture. The backend daemon manages document ingestion, structured entity extraction, and vector index generation. Inter-process communication between the lightweight command-line interface and the inference engine is mediated directly via high-speed UNIX domain sockets (/tmp/rag_service.sock), ensuring minimal runtime overhead.

varahi

AMD Developer CloudAntigravityrest api+1

AI Educational Tablekeeping system

TableKeeper is a smart restaurant table management platform that simplifies reservations, table allocation, and customer management. It provides restaurants with an organized way to track table availability

hackers

AI StudioBright Data Scraping BrowserChroma+1

EmergencyTwin Voice - 3D digital twin that talks

A live 3D digital twin that talks — an AssemblyAI Voice Agent lets security staff and occupants manage real building emergencies: block exits, calculate safe routes, and report hazards, all by voice, with the 3D view updating instantly.

Cooking AI

AI StudioAI/ML APIAI21 Labs+3

Muninn: Living Memory System for Technical Work

An opt-in living memory companion that captures technical discussions, extracts structured claims with ground-truth turn timestamps, weaves a recursive knowledge graph, and proactively resurfaces unfinished tasks and conflicting engineering decisions.

High Entropy

Assemblyai Guardrails APIAssemblyai GuardrailsCloudflare Workers AI+8

PitchPI-AI_B2B_Sales_Agent

An intelligent, real-time AI voice agent designed for B2B sales. It automates lead qualification and handles dialogue using RAG, Speech-to-Text, and Text-to-Speech, seamlessly syncing data to a Spring Boot microservice backend.

Guard

AI/ML APIAI StudioAssemblyai Guardrails+11

Inko: Voice-First Research Companion

INKO is a voice-first academic research companion that investigates topics with students, compares evidence, finds contradictions, organizes findings, and challenges conclusions through natural conversation.

Meowstars

Assemblyai GuardrailsGemini AIkiro+1

30apps loaded