Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
Amber captures the same product from inside two countries via Bright Data residential exits, strips VAT, and seals the net price gap into a signed, geo-attributed evidence packet anyone can verify offline. Catch gray-market diversion, and prove it.
The end-to-end AI content engine for real estate agents. 4RealEstate Flow runs four AI agents that plan viral content, produce listing videos, and optimize paid ads autonomously. Every agent, their own marketing team.
Transform cold outreach with nuncio: an agentic pipeline turning social profiles into personalized video pitches. Using TinyFish, Claude, and HeyGen, it delivers 1:1 tailored videos at scale to drive higher engagement for enterprise sales teams.
The MVP converts human, robot teleop, and simulation videos into searchable robotics episodes using Gemini, pgvector, GCS, Cloud Run, and a React console. It must support governed video search, summarization, clip retrieval, and LeRobot-style export.
DemoPilot turns any web app URL into a polished, narrated demo video in ~60 seconds. Gemini analyzes the UI, writes the script, Playwright records the browser, edge-tts narrates, and ffmpeg renders the final MP4, fully autonomous, zero human editing.
An autonomous agent that turns any social profile into a personalised video — from enrichment to rendered output, zero human steps.
Meridian turns any video into a queryable knowledge base. Upload a video, ask a question in plain English, and get a precise timestamped answer drawn from speech, on screen text, and what was visually happening at that exact moment.
CogniBot Simulator is an AI-powered warehouse robotics simulator that uses Google Gemini to understand scenes, generate task plans, monitor execution, and create training videos for safer and smarter automation workflows.
At Dexter AI, we built AURA: a real-time AI HUD. Fusing low-latency Edge AI with Cloud reasoning, AURA scans micro-expressions and speech at 60 FPS. We give you 'super-perception' in high-stakes meetings to turn missed signals into closed deals.
BilimForAll is a gamified "Duolingo for professions" powered by a multi-agent Gemini 3.1 system. It features automated onboarding, content generation, voice roleplays with AI mentors, and Context Caching, slashing enterprise API costs by up to 85%.
OpenLook gives coding agents visual unit tests: they record browser sessions, send the video to Gemini, get pass/fail UX verdicts, fix the UI, and rerun until it works.
An AI-powered documentation lifecycle engine built for the IBM Bob Hackathon. Automatically parses Python repositories and compiles ready-to-read markdown assets via a clean Streamlit interface.
Synvex is an AI-powered interview prep platform that helps candidates master real-world debugging, mock interviews, ATS-friendly resumes, and repo-based technical rounds through personalized AI-driven practice sessions.
AI-driven gamified ecosystem that converts YouTube playlists and long-form "one-shot" lectures into structured, interactive curricula with adaptive scheduling and automated progress tracking. Live : questxp.in
AI-Powered Recyclable Material Detection Agent: An intelligent agent that helps robots automatically detect recyclable materials in industrial settings — extensible to classify any category of materials via prompt-driven adaptation
Enter a topic, and a style, and then lyrics and a video is generated automatically
An AI-powered music visualizer that uses an AMD MI300X and Qwen 2.5 to let users dynamically control visual aesthetics in real-time through natural language.
Lumnia Ultra is an AI-powered digital smile design and shade analysis platform that combines computer vision, facial analysis, and dental aesthetics to deliver highly accurate, clinically guided smile simulations and restorative planning.
Faultline is a multi-agentic platform to simulate how real users fail, abandon, misunderstand, and exploit software before release.
One prompt becomes a 30-second cinematic reel - planning, video, music, voice-over - end-to-end on a single AMD Instinct MI300X. Apache 2.0 / MIT all the way down. Qwen3.5-35B + FLUX.2 klein + Wan2.2-I2V + ACE-Step + Kokoro.
A multimodal AI system that analyzes UEFA Champions League match footage using YOLO + Qwen3-VL 32B on AMD MI300X to detect tactical signals that sports prediction markets misprice.
An agentic Search And Rescue system with full vision and sensing capability, embodied in a physically-accurate simulation environment.
Sentinel Vision Navigator - Android APP, is an assistive AI system designed to act as a practical pair of eyes for blind and partially sighted users.
SafeSite AI exists to act as a real-time safety officer for every CCTV in construction sites; it catches violations instantly, calls the worker out by name, logs the violations and stops the next accident before it ever happens.
A fully-local multimodal video analysis pipeline that transforms raw video into structured entities, events, and timelines using YOLO26, Whisper.cpp, Depth Anything V2, and Qwen3.5-VL — all running on consumer AMD hardware. No cloud, no API keys.
Drop a 3-hour video. Get a timestamped intelligence dossier with speaker claims, topic maps, and highlight clips. Powered by Qwen3-VL-32B-Thinking + VibeVoice ASR on AMD MI300X at 0.15× real-time.
AI-powered multimodal video orchestration engine that automatically analyzes, sequences, synchronizes, and renders short-form videos from raw clips, images, prompts, and music using AMD ROCm accelerated infrastructure.
AI-driven Image and Video generation, train LoRAs on AMD GPU and produce polished social media content. Designed to be fully API-driven for AI agents.