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.

WaltTrace — Offline Multimodal RAG

WaltTrace answers short factual questions from mixed engineering documents while returning the exact files needed to support each answer. It parses PDF, Word, Excel, CSV, logs and source files, and uses a local vision-language model to read diagrams, scanned pages and equipment labels. Retrieval follows identifiers between incident reports and lookup tables, allowing answers that require more than one document. Generated quotations are checked against indexed source text; unsupported answers are refused with an empty answer and citation list. Qwen2.5-VL-7B runs on a real AMD GPU through ROCm PyTorch. All weights are embedded in the mandated container base, and the application runs without outbound network access. Indexing starts a resident model behind a private Unix socket so each fresh question process avoids reloading the weights. Malformed, unreadable, encrypted and unsupported files are skipped independently. The development report documents actual GPU timings, memory readings, individual answers and citation checks. Public-sample results are development evidence, not a claim about hidden evaluation scores or League points already awarded.

WaltTeam

AMD ROCmHuggingFace Hub

DocuPilot AI: Smart Docs & AI Asst.

DocuPilot AI transforms PDFs, scanned documents, and invoices into searchable knowledge, evidence-backed answers, financial insights, and explainable classifications through a secure, human-in-the-loop document intelligence platform.

Tech_Innovators

AntigravityChromaRedis+2

Referto: medical report, explained in plain words

Referto explains medical reports to patients in plain words, right next to the report. Only what the doctor wrote, a source for every answer (AIFA, medical glossary, open data), no diagnoses. Open model on AMD Token Factory.

Lunarcat

Token FactoryAMD Developer CloudDeepSeek V3+4

PlainProof

PlainProof rewrites complex documents for the reader: teen, senior or everyday, in multiple languages. A separate AI verifier checks every fact, number and date survived, and you get a proof receipt. Built on AMD Instinct MI300X.

BitBandits

AMD ROCm

Supplier Document Desk

AI agent that reads supplier invoices, checks them against purchase orders with exact code, explains mistakes in plain words, writes replies in the supplier's language, hides personal data, and sends risky cases to a human.

Code Voyagers

AMD Developer CloudAMD ROCmClaude Code

CROMO: why every factory step exists

CROMO reads a factory's own archive with Google's Gemma 4 on AMD and finds out why every process step exists: it flags costly fossil steps, protects fences that prevent accidents, and warns when a change breaks either.

Scorpion

AMD ROCmClaude CodeGemma+2

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

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

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

NotALawyer

NotALawyer reads your contract before you sign it. It flags the clauses that work against you, explains them in plain language, and links each one to the exact section of Canadian law, using Gemma on AMD Token Factory.

Tigran Arturovich

Token FactoryGemmarest api

TwoHands

Two Hands catches typing errors in handwritten forms: Gemma on AMD reads every number, the form's own sums decide, a person checks only what fails. 1,270 real Mexican tally sheets: 49 errors confirmed; 91.6% field match vs 62.84% for a state's Google AI.

py_tr - SoloPlayer

GemmaAMD Developer CloudQwen3

DocuSwarm: Parallel Due-Diligence on AMD GPUs

DocuSwarm is a parallel document due-diligence agent swarm running on AMD Instinct GPUs in the cloud. Reviewing contracts, NDAs, and reports for risky clauses is slow, manual work done one document at a time. DocuSwarm turns it into a single upload: drop in up to 20 documents and a swarm of async agents analyzes them concurrently against the same LLM endpoint, surfacing risk level, red flags, key dates, and parties per document, with a consolidated Excel/JSON report. This isn't a chatbot demo — it's built to make AMD GPU throughput visible. Every document gets its own async task bounded by a semaphore; all of them hit the same vLLM server, which is exactly the continuous-batching workload AMD Instinct GPUs + ROCm + vLLM are built for. A live dashboard streams completed/total, tokens/sec, elapsed time, and active concurrency in real time. Tested end-to-end on an AMD Instinct MI300X (AMD Developer Cloud) serving Qwen3-8B via vLLM: 6 documents processed concurrently in 1.5 seconds at 1,653.9 tokens/sec — real GPU throughput, not a simulation. Each result reflects genuine LLM judgment (e.g., a contract flagged MEDIUM risk with specific red flags like termination penalties and liquidated damages), not keyword matching. The backend is provider-agnostic by design: it talks to any OpenAI-compatible endpoint, so moving from a laptop to an AMD GPU instance is a one-line config change. Tech stack: FastAPI + asyncio backend, React/Vite dashboard streaming over Server-Sent Events, vLLM serving on AMD Instinct GPUs (ROCm), openpyxl for Excel export. Repo: https://github.com/yanerox69/docuswarm

Yanero Rockstar

AMD Developer CloudAMD ROCmQwen3+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

ShelfReady: Trust Layer for Product Data

Gemma 4 31B on AMD checks supplier spec sheets against their own photos, care labels and drawings, asks a person only what the evidence can't settle, and publishes EU-ready listings in 8 languages from verified facts only.

Zenin

AMD Developer CloudAMD ROCmToken Factory+4

Workplace Safety Incident Assistant

Turns a free-text or PDF injury report into OSHA codes with measured confidence, similar real cases and a sourced corrective-action plan from our Evolus agent on AMD Token Factory. Where it is unsure, the safety officer decides.

DarkSea28

Token FactoryGemmaVercel+1

Hepozy real time internet searcher

Hepozy is an AI chat assistant with a built-in search engine (All, Images, News). It answers from a verified knowledge base and Wikipedia, and reads every result page before showing it. Built with FastAPI, Supabase, Groq and Gemini.

hepozy

AI/ML APIGroq

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

KGB: Grounded OCR and RAG on AMD

KGB provides two GPU inference containers for the AMD AI League: optical character recognition and document-grounded question answering. Both preserve the required AMD ROCm PyTorch base layers and include a pinned Qwen3-VL-8B-Instruct model, so inference does not need a network connection or a hosted API. The OCR service reads license plates and road signs from PNG, JPEG and TIFF inputs. It keeps the model resident while each evaluator invocation writes its own JSON result. The RAG service indexes a mixed corpus once, reads PDF, Word, spreadsheet, CSV, source-code and image content, and returns a short answer with corpus-relative citations. It validates quoted evidence and returns an empty answer when support is missing. The public repository includes behavioral tests for parsing, independent client processes, output contracts and evidence verification. Both images build successfully and resolve anonymously from the registry. Native Radeon evaluation passed 10 OCR illustrations, 32 synthetic degraded OCR cases and all 10 RAG sample questions with exact citation sets. The required Instinct/container environment and private evaluation set have not been tested. Public examples and synthetic cases are development checks, not a claim about hidden-set scores.

KGB

AMD ROCmQwen3-VLHuggingFace Hub

OPTEsc

OPTEsc turns a floor plan into an interactive 3D building, simulates fires and earthquakes with realistic occupants, and gives short, source-backed escape instructions as the scene changes. A software prototype, not a live emergency system.

Valhallahans

AI/ML APICloudflare Workers AIClaude Code+1

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

Factory Evidence: verified CBAM savings on AMD

Reads steel suppliers' CBAM emissions documents in any language with Gemma on AMD, checks every value against the official EU tables with deterministic rules, and turns verified evidence into euros saved: €636 → €63 per tonne of Indonesian slab.

Factory Evidence

GemmaAMD ROCm

CertGate: mill certificates, a person decides

CertGate reads a steel mill certificate (EN 10204 3.1) on AMD Token Factory, checks it against the purchase specification with deterministic rules and proposes release, block or review; a person decides. False conforming 0 of 18 in both Qwen3.8-27B runs.

four-seats

VercelRedisAnthropic Claude+5

MURPHY - fuzz the procedure, not the plant

Turns a written operating procedure into an executable model and fuzzes it with thousands of error-prone crews against a physics twin of the plant.

Team Murphy

Vercel

AMD Multi-Modal AI Solutions

royek ini menghadirkan rangkaian solusi kecerdasan buatan multi-modal berkinerja tinggi yang dioptimalkan untuk ekosistem komputasi AMD ROCm dan PyTorch. Seluruh modul solusi dikemas ke dalam arsitektur container Docker terstandarisasi untuk menjamin portabilitas, efisiensi konsumsi memori GPU, dan kecepatan inferensi pada lingkungan produksi maupun pengujian otomatis. Solusi ini mengintegrasikan fondasi model multi-modal mutakhir untuk menangani pemrosesan data visual dan bahasa secara terpadu, dimulai dari pengenalan teks visual (OCR) berlatensi rendah dengan keluaran terstruktur format JSON, hingga kesiapan pipeline inferensi untuk integrasi beban kerja AI lanjutan sesuai parameter evaluasi teknis kompetisi.

SmartClass Solo

AMD Developer CloudAMD ROCmHuggingFace Spaces+5

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

InnerOS: Governed AI & Voice Ops on AMD

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.

InnerChispa Labs

NVIDIAOpenAIQwen3+11

Cite or Refuse: RAG on ROCm

Match 3 entry: a document question-answering container that only answers what it can prove. It runs on the mandated ROCm PyTorch base image with Qwen3-VL-8B shipped inside the image, so nothing is downloaded at evaluation. Index pass: every file is parsed on its own (PDF, DOCX, XLSX, CSV, TXT), and one unreadable, encrypted or unknown file never stops the walk; empty folders are fine. Text is indexed with BM25 in two passes, the second one keyed on product and part identifiers so two-hop questions can bridge between files. Revised documents supersede the withdrawn revision. Query pass: the model stays resident behind a unix socket, so each of the ten questions is a thin client call well inside the 30 second budget. The model may only answer with a value that appears in the passage it cites, and a number taken from the question must appear in that same passage; otherwise the container refuses with an empty answer and no citations. Citations are the minimal set of files the answer needs, not the retrieval list. On the sample corpus the pipeline scores 200/200 in a CPU smoke run with the 2B model; 45 unit tests cover parsers, trap files, two-hop bridging and refusals.

KHLab

AMD ROCm

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

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

30apps loaded