Utilizing Node.js and Express to create a server for enhanced security with hidden API keys, rate limiting, and efficient caching to optimize API performance.
-
Updated
Jan 12, 2026 - CSS
#
api-proxy
Here are 4 public repositories matching this topic...
聚合 AI 工作台 - 一个可连接 OpenAI 兼容 API 的纯前端聊天工作台，支持中转站API、多模态、本地存储 (OpenAI compatible API client, AI chat, local storage)
frontend api-client local-storage openai api-proxy chat-client multimodal openai-api ai-chat chatgpt multimodal-ai ai-workbench merge-ai
-
Updated
Aug 23, 2026 - CSS
AI Chatbot Platform — Local LLM Edition is a full-stack chatbot that connects a React (Vite) frontend with a FastAPI backend, which proxies requests to a locally running Ollama model (llama3). The entire system runs offline on your machine, enabling private and lightweight AI chat interactions without external APIs.
react javascript python full-stack api-proxy conversational-ai chatbot-ui vite fastapi wsl2 ai-chatbot prompt-engineering generative-ai local-llm ollama offline-ai llama3 llm-integration
-
Updated
Jun 12, 2026 - CSS
Lightweight YouTube search frontend with a Vercel serverless proxy that keeps the YouTube Data API key on the server.
-
Updated
Sep 9, 2026 - CSS
Add this topic to your repo
To associate your repository with the api-proxy topic, visit your repo's landing page and select "manage topics."