NVIDIA

Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

NVIDIA

NVIDIA Corporation is a global leader in accelerated computing, specializing in the design of graphics processing units (GPUs) for the gaming, professional visualization, data center, and automotive markets. As a pioneer in parallel computing, NVIDIA has been instrumental in the advancement of artificial intelligence, providing the foundational hardware and software platforms that drive modern AI research and deployment.

General
Author	NVIDIA Corporation
Release Date	1993
Website	https://www.nvidia.com/
Documentation	https://docs.nvidia.com/
Technology Type	Hardware / AI

Key Products and Technologies

GPUs (Graphics Processing Units): High-performance processors essential for parallel computing tasks in AI, machine learning, and deep learning.
CUDA Platform: A parallel computing platform and programming model that enables significant performance gains by harnessing the power of GPUs.
NVIDIA AI Software Suites: Comprehensive collections of tools and frameworks, such as NVIDIA NeMo for large language model development and deployment, and NVIDIA TensorRT for high-performance deep learning inference.
NVIDIA Jetson: Edge AI platform for autonomous machines, robotics, and embedded systems.
NVIDIA Omniverse: A platform for 3D design collaboration and simulation, facilitating the development of virtual worlds and digital twins.

Start Building with NVIDIA

NVIDIA's ecosystem of hardware and software is critical for accelerating AI development and deploying high-performance computing solutions. From data centers to edge devices, NVIDIA technology powers a vast array of AI applications, including agent lifecycle management with tools like NeMo. Developers are encouraged to explore the extensive documentation and resources available to leverage NVIDIA's capabilities for their projects.

👉 NVIDIA Developer Program 👉 NVIDIA AI Platform Overview

Edit on GitHub

NVIDIA AI Technologies Hackathon projects

Discover innovative solutions crafted with NVIDIA AI Technologies, developed by our community members during our engaging hackathons.

SWARM

SATO's SWARM ports CUDA kernels to AMD ROCm/HIP autonomously — hipify, compile, execute, and validate, with the target GPU architecture auto-detected at runtime. Every performance number is a real measurement (HIP-event timing, real amd-smi telemetry) or explicitly labeled "Not captured" — never guessed. A Repair Loop autonomously catches real compile failures, matches them against a memory of cited, verified CUDA→ROCm gaps, applies a mechanical fix, and recompiles — proven live on real hardware against a confirmed gap in HIP's own header. Full stack: FastAPI backend, Next.js frontend, CLI, all sharing one proven pipeline core.

AMD Port Studio

AMD Port Studio is an AI-powered developer platform that accelerates the migration of machine learning applications from the NVIDIA CUDA ecosystem to AMD ROCm. As AI projects become increasingly dependent on CUDA-specific libraries, GPU APIs, and container configurations, migrating to AMD hardware is often a complex, time-consuming, and error-prone process. AMD Port Studio transforms this challenge into a structured, explainable workflow. Developers simply provide a GitHub repository or upload a ZIP archive, and the platform automatically scans the codebase to detect CUDA usage, identify NVIDIA-specific dependencies, evaluate ROCm compatibility, estimate migration effort, and generate actionable migration guidance. Rather than relying solely on AI, AMD Port Studio combines deterministic rule-based analysis with AI-assisted recommendations, ensuring results remain transparent, reproducible, and trustworthy. The platform features an interactive Command Center and Migration Workspace, providing compatibility scores, migration readiness, dependency visualization, confidence indicators, blockers, recommendations, patch suggestions, deployment guidance, Dockerfile generation, and exportable HTML, PDF, and JSON reports. It also includes a repository-aware AI assistant powered by Gemini or Fireworks AI with retrieval-augmented ROCm knowledge for contextual migration guidance. AMD Port Studio is fully containerized using Docker Compose, making it easy to deploy and evaluate. Rather than replacing developers, it serves as an intelligent migration copilot that helps engineering teams reduce migration risk, understand compatibility challenges earlier, and accelerate AMD adoption with confidence. By combining deterministic code analysis, AI-assisted planning, and a developer-focused experience, AMD Port Studio transforms what is traditionally a manual migration process into a faster, more explainable, and efficient workflow for adopting AMD's AI ecosystem.

AutOps - Autonomous Operations

AutOps is an autonomous, AI-driven virtual system administrator designed for real-time monitoring, intelligent diagnosis, and automated remediation of server environments. Instead of relying on traditional ping monitors, AutOps acts as a 24/7 intelligent agent that watches over your containerized infrastructure. When a service goes down, it instantly fetches the relevant error logs, uses an embedded Large Language Model (LLM) to diagnose the exact root cause of the crash, and formulates a precise fix. Key Features: Discord Command Center: It transforms Discord into a secure, mobile-friendly command-and-control terminal using a custom Python bridge, allowing administrators to manage servers directly from their phones. Human-in-the-Loop (HITL) Safety: To prevent the AI from making destructive changes autonomously, AutOps enforces a strict safety mechanism. The AI generates a remediation proposal and sends an alert to the admin via Discord. The fix is only executed if the admin explicitly replies with an !approve command. Microservices Architecture: The system operates securely within Docker and is powered by n8n, a visual orchestration engine that routes complex background health checks, webhook events, and SSH command executions. Ultimately, AutOps reduces the tedious, multi-step troubleshooting process (connecting to a VPN, authenticating SSH, manually hunting for logs) into a simple mobile notification and a 5-second approval response—drastically lowering both the Mean Time to Detect (MTTD) and Mean Time to Resolve (MTTR) for server incidents.

Codyssey Captionate: Cognitive Video Telemetry

Codyssey Captionate is a luxury-grade cognitive subtitling and interactive audio telemetry workspace designed to revolutionize how video content is consumed, analyzed, and generated. By fusing high-performance speech-to-text workflows with real-time sentiment analysis, the application transforms raw audio tracks into deeply expressive, human-centric visual telemetry. At the heart of Codyssey Captionate is a highly synchronized visual media player paired with a dynamic Recharts graphing engine. As videos play or live microphones stream, every spoken word is mapped with microsecond precision against emotional sentiment indexes—positive, negative, or neutral. Users can manually tune advanced subtitle variables such as generation temperature, temporal accuracy constraints, noise filtering thresholds, and verbatim matching to perfectly align with the cinematic tone. The infrastructure is architected for extreme high-uptime and blisteringly fast containerized throughput. Hosted on advanced, highly scalable AMD Cloud GPU architectures, the app utilizes AMD Instinct ROCm-accelerated containers to handle heavy multi-thread processing with near-zero latency. For ultra-fast token generation and transcription routing, the system coordinates with Fireworks AI endpoints, backed by our proprietary Gemini Multi-Model Fallback Controller. If primary cloud quotas are ever depleted, the backend automatically fails over to local lexical caches, preventing any runtime disruption. All user history, processed queues, and sentiment analytics are synchronized securely across sessions using a robust Firebase Firestore database. Ready for modern developer workflows, Codyssey Captionate includes single-click SRT and TXT subtitle exports, live microphone ingest logs, and a beautiful dark-slate glassmorphic dashboard styled with cinematic film-grain textures, defining the next era of accessible, intelligent video streaming.

ayaka-hand: the grip forms before you touch

Roughly 23% of upper-limb myoelectric prostheses are abandoned in real-world use. It's rarely the hardware that fails. The real cost is cognitive load: consciously picking a grip and metering force for every object, all day long. ayaka-hand moves that decision off the user and onto a wrist camera. The camera looks at what you're reaching for and pre-shapes the hand into the right grip before contact. Your own muscle signal, just one EMG channel, gets reduced to a single binary GO. You decide when to close. The vision system already decided how. Underneath, it's a teacher and a reflex. The teacher is a cloud vision-language model, Qwen3-VL. It labels training data offline, and in this live demo it also shows up as a slower second opinion a couple of seconds later; it's never in the real-time control loop. The reflex is what actually decides: a 2.23-million-parameter model running on-device, in the browser, on pixels alone, committing within 125 milliseconds. It never gets told an object's class name, only what it looks like. On force estimation specifically, that matters: it beats a baseline that's simply handed the object's exact label for free, and still wins by 16 points of accuracy, because force depends on an object's state, not its label. This is a research prototype, not a certified medical device, and what's real today is the live demo. There's no physical hand built yet. Hazard flags from the cloud model are advisory only; they're never wired to an actuator. The teacher's serving path targets AMD ROCm, and I validated it end-to-end on RDNA3 hardware, with MI300X as the scale target; the student was trained on local hardware. I'm building it because I want to see it actually help someone use their hand again, not because I wanted to win a hackathon. Try the live demo yourself in any browser: https://lfl1337.github.io/ayaka-hand