Skip to content

Assistant · Menlo Research

Jan

Open-source ChatGPT alternative that runs 100% offline on your computer.

FREEOpen sourceLocalmacOSWindowsLinuxAPI

An open-source desktop assistant that runs AI models 100% offline on your own machine, bundling a local model runner so you can download and chat with open models like Llama, Gemma, and Qwen. It also supports bring-your-own keys for cloud providers when you want them, and exposes a local OpenAI-compatible server. Fully open source under Apache 2.0 with no paid tier.

Model support

Multi-model

  • Llama
  • Gemma
  • Qwen
  • gpt-oss
  • Claude
  • Mistral

Runs open models locally; BYO API keys for cloud providers.

Where it runs

  • macOS
  • Windows
  • Linux
  • API

Tags

  • #offline
  • #local
  • #open-source
  • #privacy
  • #desktop
Open JanWebsiteDocs

Related in Assistant

  • View ChatGPT details
    AssistantFREEMIUM

    ChatGPT

    OpenAI

    The default AI assistant. Chat, voice, vision, and a tool ecosystem.

    OpenAI's consumer assistant — multimodal chat with voice, image input, web browsing, code, and custom GPTs. The product that put generative AI in everyone's hands.

    AI insight: The app that mainstreamed generative AI — its custom-GPT store turned a chatbot into a third-party app platform.

    • chat
    • assistant
    • multimodal
    • voice
    Open
  • View AnythingLLM details
    AssistantFREEMIUMOpen core

    AnythingLLM

    Mintplex Labs

    All-in-one private AI app for chatting with your documents, with agents.

    An all-in-one application for private, ChatGPT-style chat over your own documents, with built-in RAG, AI agents, and multi-user workspaces. Runs as a local desktop app (Mac/Windows/Linux) or self-hosted via Docker, and supports 40+ LLM providers plus local models with your own keys. Open source under MIT; Mintplex Labs also offers a paid hosted instance, making it freemium.

    AI insight: Runs either as a one-click desktop app or a Docker server — the same private RAG workspace whether you're solo or a team.

    • rag
    • documents
    • self-hosted
    • open-source
    • +1
    Open
  • View Big-AGI details
    AssistantBYO KEYOSS

    Big-AGI

    Enrico Ros

    Multi-model AI workspace with chat, voice, image gen, and tool use — BYO keys.

    A self-hostable AI workspace for chatting across hundreds of models from many providers, with voice calls, image generation, web search, and code execution. It runs self-hosted via Docker or Vercel and connects to local engines (Ollama, LM Studio, LocalAI) as well as cloud providers. MIT-licensed and free — you supply your own provider API keys.

    AI insight: Deploys to your own Vercel in a click, and its 'beam' feature runs one prompt across several models to compare side by side.

    • chat
    • multi-model
    • self-hosted
    • open-source
    • +1
    Open
  • View Cherry Studio details
    AssistantFREEMIUMOpen core

    Cherry Studio

    CherryHQ

    Desktop AI client unifying frontier LLMs, local models, and 300+ assistants.

    A cross-platform desktop AI productivity app for chatting across cloud and local models, with autonomous agents and 300+ prebuilt assistants. It runs on your own machine and supports local models via Ollama and LM Studio alongside cloud providers using your own keys. The community edition is AGPL-3.0; organizations over ten people require a paid commercial license.

    AI insight: Free for individuals and small teams, but its AGPL terms require a paid commercial license once an org passes ten people.

    • desktop
    • multi-model
    • local
    • open-source
    • +1
    Open
Open Jan