$ account tech-shrimp
This repository is a collection of tutorials, guides, and examples for integrating AI large language models with various services and platforms. It primarily serves as a resource base for the tech content creator '技术爬爬虾' (Tech Shrimp), containing video resource lists, step-by-step guides, and code snippets. The repository demonstrates practical patterns for AI integration including: RSS feed processing and summarization workflows (using n8n), AI-powered smart home assistants (integrating DingTalk with Home Assistant), and AI chatbots for messaging platforms (WeChat, DingTalk, Enterprise WeChat). While not a cohesive application itself, it contains reusable data pipeline patterns, particularly the n8n workflow for converting RSS feeds to AI-generated email newsletters, which exemplifies a practical ETL pattern using modern AI services.
This repository is a serverless web application that serves as a playground and API proxy for Google's Gemini Multimodal Live API. It provides a client-side interface for real-time text, audio, video, and screen-sharing interactions with the Gemini model. Crucially, it includes a backend proxy layer (deployable on Cloudflare Workers or Deno) that converts the native Gemini WebSocket/REST API into an OpenAI-compatible format, enabling integration with third-party clients like ChatBox or Cursor. The architecture is split between a static frontend (vanilla JS) and a lightweight serverless proxy that handles authentication, protocol translation, and streaming logic.