local LLM desktop app
Jan is an open-source, offline-first desktop app (Tauri) for downloading, running, and chatting with local LLMs, with optional cloud integrations and an OpenAI-compatible API.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
self-hosted web workspace with built-in RAG and document management; requires external model runtime like Ollama.
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
self-hosted web interface for LLMs; choose over Jan if you prefer a browser-based multi-user setup.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
lightweight cross-platform AI chat UI; choose for lower resource use and multi-platform support.
✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
archived desktop LLM client with MCP support; usable but no longer maintained.
a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP
archived local GPT chat app with document features; older and less active than Jan.
Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/
These projects were analysed and named jan among their alternatives. The relationship is not symmetric — how jan rates them is a separate judgement, made when jan is analysed in its own right.
calls jan “Choose when you want a privacy-first offline desktop client with built-in local model management.”
Powerful AI Client
calls jan “Choose Jan for a fully offline local-model desktop assistant with built-in model management; it lacks AnythingLLM's server-side RAG and multi-user agent workflow.”
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
calls jan “Choose it when you need fully offline/private AI chat with local models rather than a remote ChatGPT wrapper.”
❄️ ChatGPT Desktop Application (Mac, Windows and Linux)
calls jan “choose it for a local-first offline chat client that can run open-weights LLMs”
An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)
calls jan “Choose for a polished offline ChatGPT-style chat client when you have no need to train or run diffusion models.”
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
calls jan “Choose it if you prefer a polished desktop app over a web server; it runs fully offline and supports many local models, but isn't something you embed in your own server.”
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!