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.

Jarvis

It is a very powerful ai chatbot which can run using your hand movements and run on various environments to perform your various tasks visually using 3D visualisation and remind you of anything anytime just using commands and many more to come.JARVIS is not just an AI assistant; it is an ambitious step toward building a futuristic digital intelligence inspired by the possibilities of Tony Stark’s legendary technology. Designed as an expanding ecosystem of intelligent environments, JARVIS combines conversational AI, futuristic interfaces, visual intelligence, scientific simulations, and centralized command capabilities into one powerful web-based platform. Its six environments—Main JARVIS, Velve, Terranexus, Command Centre, Vision Intelligence, and Ultron—represent different dimensions of an interconnected digital universe. From exploring scientific experiments and mechanical simulations to visual intelligence and advanced system interaction, every environment expands what a personal AI ecosystem can become. JARVIS aims to transform the way humans interact with technology, bringing multiple intelligent capabilities together through a unified interface. Its long-term vision reaches beyond answering questions toward helping users interact with digital tools, navigate complex information, and manage technological workflows. Built with the ambition to evolve continuously, JARVIS represents a bold vision of a world where AI is not merely something you talk to—it becomes the intelligent interface connecting you to your digital universe. JARVIS: One Intelligence. Multiple Environments. An Entire Digital Universe at Your Command.

DENCO

AI/ML APIAssistants APIrest api

AEGIS

AEGIS – Short Version AEGIS is a low-cost autonomous ground rover for border and field patrolling, target navigation, surveillance, and operation in GNSS-denied environments. Built on ROS 2 and Nav2, it supports GPS-based target navigation and multi-waypoint autonomous patrol missions. When GPS becomes unreliable, AEGIS switches to local navigation using odometry, inertial sensors, visual odometry, and pre-built maps, enabling continued patrol without satellite positioning. Its camera-based perception system uses YOLOv8 to detect drone-like aerial targets, people, and predefined human activities, generating operator alerts for suspicious events. It does not identify individuals or infer intent. The rover uses a rechargeable battery with solar-tracking support for longer field endurance. A modular, regulated RF counter-UAS research module is included for authorized defence/testing environments, focusing on GNSS-degradation detection rather than operational jamming. AEGIS is intended as a safe, modular technology demonstrator for perimeter security, disaster response, infrastructure monitoring, and search-and-rescue missions, reducing human exposure in hazardous areas..

TEAM AEGIS

AI/ML APIAntigravityAMD Developer Cloud+5

Maintenance Copilot: Catch Failures Early

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.

Synthetix

AMD Developer CloudGemmaStreamlit

RootTrace 8D: Complaint to 8D Report on AMD

RootTrace 8D turns a customer quality complaint into an evidence-backed 8D report in minutes. Deterministic SPC finds the process shift and the suspect lots, AI on AMD drafts D1-D8 citing every fact, and the engineer approves.

RootTrace 8D

Token FactoryAMD Developer CloudAMD ROCm+1

RoboProof: Motion-Learning Lab

RoboProof trains and evaluates a VEX robot’s motion policy in the original Simulator/iraLIB, combining GVF path following with TD3 residual learning on AMD GPUs.

RoboProof

AMD Developer CloudAMD ROCmAnthropic Claude+11

InterCycle

From public CCTV to a factory twin: learned production cycles and people and forklift flows that allows currently deployed inspection robots to operate in highly dynamic industrial plants.

InterCycle

GemmaToken FactoryAWS+3

MediGuide AI Multilingual Healthcare Intelligence

An AI-powered healthcare assistant that extracts, summarizes, and explains medical reports in multiple Indian languages, helping patients understand clinical information and prepare for doctor consultations.

Team Tech

AgentOpsAI/ML APIAMD ROCm+7

Shift Handover Briefing

Turns machine logs, maintenance notes, operator voice memos, and equipment manuals into a prioritized shift handover with evidence-linked findings and suggested checks for human review.

Limey Salt

AI/ML APIAMD Developer CloudAnthropic Claude+4

SimToReal Agent

AI on AMD Token Factory writes eight robot programs for a factory task; MuJoCo tests each one, unsafe plans are rejected with a reason, and an operator approves the best before export.

Visionary Creators

AMD Developer CloudDeepSeek V3

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

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

Whisperer a failing bearing in motor current

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.

Bearing Whisperer

Token FactoryGemmaQwen3+1

IGNIS: Traceable maintenance intel & audit reports

IGNIS turns maintenance work orders into reviewed records, transparent priorities, evidence-backed explanations and traceable reports, using AMD-powered AI with human approval at every critical decision.

Develarper

Token FactoryAMD Developer CloudAMD ROCm+4

ClaimThat

ClaimThat helps freight teams decide whether a shipment issue should become a claim. It combines shipment documents and photo evidence to recommend Claim, No Claim, or Human Review, while showing the evidence and recoverable value behind the decision.

AngieX

AMD Developer CloudVercel

Tablekeeper: AI-Built Restaurant Reservations

A restaurant reservation service where a table is never double-booked, built by three AI agents (Planner, Implementer, Reviewer) on BAND. No human wrote app code. Stages 1 and 2 pass the official harness; the website supports combinable tables.

CResTE

AgentOpsAMD Developer CloudAntigravity+5

TrustForge — Evidence-Gated AI Software Factory

TrustForge is an autonomous software factory that builds, challenges, verifies, repairs and proves critical software behavior before it ships.

FlashTsk17

OpenAISolo TechBand Intergrations+15

Symbio

Ai self fine tunes it self based of mistakes it made either from a human or what the environment tells them which helps them sharpen their skill in that area. Thus, it becomes better over time which helps clear out the context window as it does not need a bloated prompt to explain and gives space for conversation. The model will have been shaped from what a human wants in AI which is what AI should be not just for the general public but more secluded to what you want artificial intelligence to achieve under your use. This fine tuning will make the AI agent personalize. Plus the AI dictates its learning so it can chose to ask the user to fine tune or change its own training data to make sure it doesn't cause problems. the harness also has a golden file to ensure the core functionalities in the model remains through all iterations. as well as giving the AI to track how far the weights have moved and investigate if it caused any errors and to either fix it or divert away from the weight.

areyouokay

Claude CodeAnthropic ClaudeGemma+7

Amazing Troop – AI Dark Factory Tablekeeper

A three-agent AI software factory built in BAND that autonomously develops, tests, and verifies Tablekeeper, a restaurant reservation application completed across four progressive stages.

Amazing Troop

Band Agentic MeshBand IntergrationsCodex+2

Pocketful: Three-Agent Payment Settlement

Three AI agents plan, execute, and audit payment transfers in a BAND room. A C ledger and FastAPI service enforce atomic transfers, idempotency, and exact integer-cent accounting, supported by 76 passing automated tests.

settlement-agents

Claude CodeBand Agentic MeshCodex

PhantomPay: Autonomous Ledger & Settlement Factory

PhantomPay is an autonomous ledger and multi-agent settlement factory built with ASIL-D safety state machines, dual-entry accounting, and rigorous multi-stage code verification.

Phantom Foundry

AI/ML APIVercelLangChain+1

TableKeeper – AI Dark Factory

An OpenTable-style restaurant reservation platform built through a multi-agent AI Dark Factory, with restaurant discovery, real-time table availability, reservations, cancellations, amendments, authentication, and reliable booking workflows.

Coders_1

rest apiOpenAICodex+4

PlateParse: ROCm Vision OCR for Plates and Signage

PlateParse is a vision-language OCR system for vehicle registration plates and road signage, built to run entirely on AMD Instinct GPUs via ROCm. It uses Qwen2.5-VL-7B-Instruct as the recognition backbone, served from a container whose final stage is the mandated rocm/pytorch ROCm 10.0 base, with model weights staged in a separate build stage so they never bloat the base image. The scoring pipeline separates recognition from transcription rules. The vision model does the reading; normalize.py then applies category-aware cleanup: Chinese license plates keep their province prefix, single-token alphanumeric strings are treated as plate numbers so state banners and mottos are stripped, and multi-token output is treated as road signage where all text is preserved. Units appended to advisory speed plaques are removed without damaging genuine sign text. Both sides of grading are normalized identically, so emitting the correct character set is what matters, not formatting. The system was debugged directly on an AMD Instinct MI300X under ROCm, which surfaced a hardware-specific failure worth noting: the Qwen2.5-VL vision tower segfaults under bfloat16 on this ROCm generation. Pinning float32 weights with eager attention resolved it. Verified end to end on the MI300X, reading a synthetic California plate as 7ABC123 at 0.9988 confidence, with the banner correctly stripped. The container is defensive by design: it always writes schema-valid JSON and exits zero, so a single malformed image costs its own points rather than ending the run and zeroing every remaining image.

HaloHubX

AMD ROCmHuggingFace HubAMD Developer Cloud

Optical Character Recognition using VL

This project is an AMD ROCm based optical character recognition pipeline for the LabLab AMD AI Academy Mini Challenge 2. It uses Qwen2.5-VL-3B-Instruct with PyTorch and Hugging Face Transformers to read text from license plates and traffic signs. The pipeline handles US plates with state names and slogans, Chinese plates, stop signs, speed limit signs, advisory speed plaques, and multi-line warning or work-zone signs. Its instructions and post-processing are designed to keep only registration characters on US plates, preserve relevant characters on Chinese plates, and transcribe visible sign text in reading order without adding explanations or inferred characters. The solution accepts PNG, JPEG, and TIFF images through the required command-line interface and writes one JSON response per image. A resident worker loads the model once on the AMD GPU, then processes each image, avoiding a full model reload on every call. The project is packaged in Docker using the challenge-mandated ROCm PyTorch base image. It was validated on an AMD Instinct GPU for the required image formats, startup and inference limits, VRAM use, and a 298-image evaluation set. The larger evaluation achieved exact matches on all 82 samples with available ground-truth labels.

nomeechum

AMD Developer CloudAMD ROCmHuggingFace Hub

Voice Screen-AI

Screen-AI is a voice-controlled autonomous computer agent that enables users to interact with their computer naturally through speech. It combines real-time voice intelligence, screen perception, OCR, UI automation, and contextual computer-state awareness to understand applications, windows, files, browser tabs, contacts, and on-screen elements. Its Universal Target Resolution identifies the exact target behind natural commands, while the autonomous execution engine plans and performs tasks across the desktop. Every important action is observed and verified, with built-in recovery and self-healing mechanisms to handle failures and continue toward the user’s intended goal.

DONT

Assemblyai Guardrails APIAssemblyai GuardrailsAntigravity+2

MIRROR — Workflow Intelligence & Verification

MIRROR watches repetitive computer workflows, discovers the underlying pattern, proposes semantic automation, requires human approval, executes the workflow, and verifies the actual result.

dev-God

Anthropic ClaudeChatGPTChroma+4

Karya

KARYA is a voice-first AI agent that turns natural speech into real actions across tasks, notes, calendar, research, weather, GitHub, memory, and more.

GGCart

Assemblyai GuardrailsAssemblyai Guardrails APIAssembyai Guardrails API+5

PlateSign OCR on AMD ROCm

PlateSign OCR reads licence plates and road signs from uncooperative images on AMD GPUs. It runs Qwen3-VL-8B-Instruct in BF16 with Hugging Face Transformers on ROCm 10.0, packaged on the mandated rocm/pytorch base image. A resident server loads the model once at container start and warms up the GPU before it reports ready, so each grader call to app.py is a thin standard-library client that sends the image path over a Unix socket and writes the JSON answer. The prompt encodes the transcription rules: keep only the registration number on US plates (drop state names and slogans), keep the province character and letter on Chinese plates, keep every printed word on signs, and join multi-line text top to bottom. Tested in a grader-style run on an AMD Instinct MI300X: 10 of 10 sample images correct across PNG, JPEG and TIFF, 20 s startup, 0.16 to 0.35 s per image, 18.4 GB peak VRAM, 45.7 GiB uncompressed image.

Sovereign AI Labs

AMD ROCmAMD Developer CloudQwen3-VL+1

Architectural Pre-Flight

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.

WhyNOT!!!

AI StudioAWSChatGPT+11

Bifrost Sentinel

Autonomous zero-downtime database migration rehearsal, query blast-radius analysis, and compatibility view healing engine built with IBM Bob 2.0.

Bifrost Sentinel

IBMGemini 3 proGemini 3 Flash

30apps loaded