jan
AI assistant framework
An offline AI assistant framework supporting multiple LLMs and GPU acceleration.
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)
24k stars
137 watching
1k forks
Language: TypeScript
last commit: about 1 month ago
Linked from 1 awesome list
electrongptllama2llamacpplocalaiself-hosted
pluja/awesome-privacyRelated projects:
| Repository | Description | Stars |
|---|---|---|
 lencx/chatgpt | A desktop application built with Rust and Tauri, providing a chat interface using the GPT-3 AI model | 53,237 |
 bin-huang/chatbox | A desktop application for interacting with AI models and language learning platforms | 23,791 |
 antimatter15/alpaca.cpp | A locally run Instruction-Tuned Chat-Style LLM project that combines foundation models and fine-tuning to create a chat interface. | 10,249 |
 vincelwt/chatgpt-mac | A toolkit to embed ChatGPT in a macOS menubar application | 6,373 |
 ai-shifu/chatall | A platform that enables concurrent interaction with multiple AI chatbots to find the best answers. | 15,332 |
 jackmort/chatgpt.nvim | A plugin for Neovim that integrates with the ChatGPT API to generate natural language responses and assist with coding tasks. | 3,825 |
 ztjhz/betterchatgpt | A tool providing an enhanced chatbot experience using OpenAI's ChatGPT API | 8,212 |
 jina-ai/serve | A framework for building and deploying AI services that can be scaled from local development to production | 21,180 |
 sugarforever/chat-ollama | An open-source chatbot platform using large language models and vector databases | 2,707 |
 lyogavin/airllm | Optimizes large language model inference on limited GPU resources | 5,446 |
 mintplex-labs/anything-llm | An all-in-one Desktop & Docker AI application with built-in RAG and support for multiple LLMs and vector databases. | 28,746 |
 prefecthq/marvin | An AI toolkit for building natural language interfaces and generating multimedia content | 5,362 |
 skypilot-org/skypilot | A framework for running AI and batch workloads on any infrastructure, offering unified execution, cost savings, and high GPU availability. | 6,905 |
 exo-explore/exo | An experimental software framework to run AI models on diverse devices without requiring expensive GPUs. | 17,369 |
 swift-ai/swift-ai | A high-performance deep learning library written in Swift for Apple platforms. | 6,032 |