The pretty much "official" DSPy framework for Typescript

Supercharged experience for multiple models such as ChatGPT, DALL-E and Stable Diffusion.

Deploy your private Gemini application for free with one click, supporting Gemini 1.5, Gemini 2.0 models.

Smoothly Manage Multiple LLMs (OpenAI, Anthropic, Azure) and Image Models (Dall-E, SDXL), Speed Up Responses, and Ensure Non-Stop Reliability.

ChatGPT Copilot Extension for Visual Studio Code

rUv's Claude-Flow, translated to the new Gemini CLI; transforming it into an autonomous AI development team.

A serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5

Basic UI to chat with Google Gemini AI

Using LLMs and AI browser automation to robustly extract web data

基于大语言模型（LLM）和可解释 AI（XAI）的下一代代码质量与安全分析工具。支持对整个代码仓库和单个代码片段进行自动化静态分析（SAST），旨在发现隐藏的 Bug、安全漏洞（如 SQL 注入、XSS）、性能问题、代码异味和技术债。为您的 Pull Request 和日常开发提供智能、可解释的审查反馈。A next-gen code quality and security analysis tool, powered by Large Language Models (LLM) and enhanced with Explainable AI (XAI).

An application to make learning as fun as gaming

A web app that dynamically generates playable 'Spot the Difference' games from a single text prompt using a multimodal pipeline with Google's Gemini and Imagen models.

GemAI - A Free RAG CLI ChatBot 🤖

Multi-Agent AI Travel Itinerary Generator in Next.js using Gemini Generative AI Model and Groq LLM

This open-source tool is designed for in-depth research using Google's Gemini models.

Google Gemini Voice/Vision Assistant with gemini-1.5-pro / gemini-1.5-flash modal ! #Gemini 1.5 Flash #Gemini 1.5 Pro

This project converts written material into speech by using Google AI (Gemini) for text creation or internet searches.

Gemini is an open-source application powered by the Google Gemini Vision API. It enables users to identify and learn about objects captured by their camera through a simple and interactive experience. Just say 'Hey Gemini' and show an object to the camera and say!

Experimental web console for real-time multimodal AI interactions (voice/video) using Gemini 2.0 Live API and NijiVoice. Next.js (TypeScript, Tailwind) frontend and FastAPI backend communicate over WebSocket for low-latency streaming.