小爱音箱mini定制固件 Let the Xiao Ai Speaker Mini free

Start a chat room between all, or some, of your models running on Ollama. All in a single Bash shell script.

Chat locally using leading open models built by the community, optimized and accelerated by NVIDIA's enterprise-ready inference runtime

Mem0Chat is an application showcasing an LLM-powered chat with a model-agnostic persistent memory layer powered by mem0. It enables context-aware conversations, using mem0's memory management to retain and utilize key memories across sessions/chats for a personalized, efficient user experience.

Scalable implementation of Semantic search and LLM powered chat bot for online store

Single HTML Page offering split screen LLM Chat and Web App Prototyping

Testing assistant-ui Chat with Pirate!

Chat App with Ollama

llm-is-fun-for-js introduces front-end developers to Large Language Models (LLMs) with simple projects like a chatbot, a text summarizer, and a To-Do List app. It encourages developers to explore new technologies, enhance their resumes, and build innovative applications using LLMs.

implement llm streaming with page reload support using vercel ai sdk

A modern real-time streaming chat application with FastAPI backend and React TypeScript frontend

JavaScript templating engine based on Jinja2 (forked to experiment with LLM Chat templates in Jinja2 syntax)

An ai-powered journal that determines your mood.

Asses-2 is a modern, responsive frontend prototype for an AI chat application, built with React, TypeScript, and Vite. It features a clean interface for managing conversations, a collapsible sidebar with chat history, debounced search, and a rich input area supporting file attachments with drag-and-drop. The backend is currently simulated.

Chat LLM local: Interfaz CLI para modelos GGUF y Transformers con compatibilidad CUDA. Permite ejecutar Llama, Mistral, Gemma, Phi y Qwen localmente con detección automática de modelos, adaptación de mensajes del sistema, soporte RAG y más.

A branching LLM chat application that allows users to revisit past turns and create new conversation branches. Supports multiple LLM providers (OpenAI, Gemini, Claude, Ollama) with a React/Next.js frontend and a Python/FastAPI backend.