An Android keyboard that performs speech-to-text (STT/ASR) with OpenAI Whisper and input the recognized text; Supports English, Chinese, Japanese, etc. and even mixed languages.

A TypeScript library for building orchestrated framework-agnostic multi-agent AI systems

API Proxy | API 代理 | Прокси | وكيل | OpenAI | Nvidia-NIM | Claude

Advanced Coding AI Assistant that uses a Gradio interface to stream coding related responses. ChatRAG supports local and API inference and pulls context from GitHub Repos and local files.

AI-powered flood intelligence system featuring h2oGPTe Agent + NVIDIA NIM integration (A2A), NAT pipeline with Nemotron 49B, and real-time flood risk assessment. Part of NVIDIA–H2O.ai AI for Good Blueprint for disaster response and monitoring.

An open-source AI chatbot app template built with Next.js, the Vercel AI SDK and the newly released NVIDIA NIM API Inference.

RAG demo with Langchain , Gemini and NVidia NIM Models

A toolkit to explore and build with NVIDIA NIMs

AI office agent

Multimodal AI Chatbot

A simple Streamlit-based chatbot application that allows users to interact with their documents using a Retrieval-Augmented Generation (RAG) pipeline.

NimChat — A lightweight AI chat frontend built to work seamlessly with NVIDIA’s NIM API. Features live Markdown rendering, clean UI, and support for code blocks with syntax highlighting

This allows you to use NVIDIA NIM models (like moonshotai/kimi-k2-thinking, deepseek-r1, etc.) as a backend for Claude Code (the Anthropic CLI).

Feature-complete CLI client for Moonshot AI Kimi K2.5 (1T MoE). Dual backend: Moonshot API + NVIDIA NIM. Chat, Vision, Video, Files, Web Search, 11 Official Tools, Thinking Mode, JSON Mode.

using NvidiaNim to chat with pdf document

AI writing assistant designed by a dyslexic student for dyslexic thinkers. Learns patterns, voice-to-text, mind maps, non-intrusive corrections. Empowers authentic writing without the struggle!

🚀 Proxy messages to NVIDIA's models, converting Anthropic/Claude API calls into OpenAI Chat Completions with easy configuration and secure authentication.

An end-to-end RAG chatbot that retrieves information from your documents and generates accurate, context-aware answers using NVIDIA NIM and Gemma-3n-e4b-it. Features include multi-file upload, FAISS in-memory vector store, chat history, hallucination prevention rules, and support for PDF, DOCX, TXT, and CSV files — all wrapped in a fast Streamlit i

A benchmarking framework for LLM inference engines (vLLM, SGLang, NVIDIA NIM) that measures sustainable throughput under continuous full load in a closed Loop