An open-weight 11B model series for long-form and real-time video understanding
Real-time stream editing pipeline powered by the FLUX.2-klein-4B model, optimized for consumer GPUs
ECS World Model Architecture: Real-Time Data AI Framework 2026
Real-time Face & emotion recognition system using a lightweight CNN, with OpenCV webcam inference, GroqCloud for chatbot & FastAPI + frontend web deployment.
An open source risk-management tool built for stock and security risk analysis
Can you train a GPT-Live with $50?
Real-time behavioral intelligence for call centers. Transcribes support calls, redacts PII, extracts emotional tone, classifies issues, and delivers insight-rich dashboards — powered by GPT-3.5 (cheap tokens), Whisper, DuckDB, and a polished React+TypeScript frontend. No Azure. No Power BI. No vendor lock-in. Just full-stack AI that runs local.
AI-powered desktop app that provides real-time interview assistance. Get instant, professional answers to interview questions with screen-share safe technology.
artificial-intelligence computer-vision deep-learning emotion-detection facial-expression-recognition tensorflow opencv cnn machine-learning python real-time-ai
A production-ready voice agent template that feels like a real phone call
GameAI.Net is a high-performance embedded realtime AI compute library for games and simulations on .NET.
Production Android AI with ExecuTorch 1.0 - Deploy PyTorch models to mobile with NPU acceleration and 50KB footprint
The WYRD Protocol Architecture. The goal is to move the "World Model" out of the LLM's fleeting memory and into a structured Entity-Component-System (ECS). World-class foundation for deterministic AI world-modeling. Light-weight agnostic world-modeling system designed for the next generation of AGI, AI gaming, AI RPGs, and AI charactor systems.
A unified benchmarking framework for evaluating Voice AI agents across conversational quality, audio realism, latency metrics, and safety guardrails with scalable multi-language stress testing.
Simulation first governed neuroadaptive runtime for BCI inspired intent to action systems: uncertainty aware abstention, signal quality and drift detection, locally qualified decoders, shared autonomy, symbolic world modeling, Simplex fallback, evidence gated adaptation, signed replayable assurance, and deterministic fault injection.
Real-time student detection using YOLOv8 with Python and OpenCV.
Real time AI hand pose detection and styling it with the infinity stone gauntlet style build by using ReactJS and react webcam
SOTA real-time interactive AI avatar platform for multimodal conversational digital humans.Next-generation realtime multimodal conversational AI avatar system with streaming digital human interaction.
A Cloud LLM plays unpaused 35 Hz ViZDoom through streamed one-token actions and staggered requests—with no local aim assist.
LiveVision AI: Real-Time Visual Conversations with Gemini
To associate your repository with the real-time-ai topic, visit your repo's landing page and select "manage topics."