Local-first GenAI lab with a React frontend and Spring Boot backend, supporting Ollama, Amazon Bedrock, Hugging Face, RAG document retrieval, MCP-backed AWS tools, streaming chat, persistent sessions, and artifact/report workflows.

A modern, free AI chatbot application built with React, TypeScript, and Puter AI services with real-time streaming responses

macOS and iOS clients for self-hosted Hermes Agent API Server: streaming chat, Responses, Runs, tool progress, and Cron Jobs

自托管 HTTP 编程 Agent 工作台：支持流式对话、持久会话、文件交付、后台任务和 Docker Chrome 真实浏览器访问。

A lightweight, privacy-focused web interface for interacting with OpenAI-compatible APIs. This single-file application provides a feature-rich chat experience with complete client-side data management, ensuring your conversations and API credentials never leave your device.

A modern conversational AI interface built with Next.js and TypeScript. It integrates with LLM APIs to deliver real‑time, context‑aware chat responses with streaming output.

Next.js 16 boilerplate with a pluggable AI provider registry, streaming chat UI, and OpenAI integration out of the box.

Local-first AI console built with Next.js, TypeScript, and Ollama. Streaming chat, Quick/Daily/Heavy model routing, API layer, and RAG over local documents.

A fully local AI chat assistant with RAG, semantic memory, and web search. Built with FastAPI + React + Ollama + ChromaDB. Features streaming SSE chat, multi-model support (Ollama / OpenAI-compatible APIs), file upload Q&A, HyDE + BM25 re-ranking, and model warmup. No cloud API required.

A streaming chat web UI for an agentic RAG assistant — renders responses token-by-token over SSE, backed by the agentic-rag server.

Stateful AI study coach on Cloudflare Agents with persistent plan memory, Workers AI inference, tool calling, streaming chat, and scheduled workflow execution.

Official Android demo and integration guide for Umeng U-ADK, including chat, streaming, image generation and model discovery.

A modern full-stack AI chat app built with Next.js and Express, featuring streaming responses, markdown rendering, syntax-highlighted code blocks, and model/provider selection.

【Star-crossed coders unite!⭐️】🤖 Reusable template for AI-powered event Q&A assistants. Built with Next.js 16 & Google Gemini. Features full-screen chat, community-driven FAQ voting, Notion backend. Customize in minutes - just edit config files. One-click Vercel deployment.

Terminal-first TUI for Ollama local LLMs, browse models, pull new ones, chat with system prompts, compare and benchmark, all keyboard-driven.

Local Nook is a local-first Angular client for Ollama with streaming chat, model switching, system prompts, rich Markdown rendering, rebrandable configuration, and an AI-native Codex workflow. Built for private, maintainable local LLM use with official Ollama SDK integration.