Back to directory

Jan

Jan is an open-source, offline-capable alternative to ChatGPT that downloads and runs LLMs locally, keeping full control over data and model choice.

Jan

Local models come from Hugging Face, including Llama, Gemma, Qwen and GPT-oss families, and Jan also connects to cloud providers such as OpenAI, Anthropic, Mistral, Groq and MiniMax when a cloud model is wanted instead. It supports custom assistants for specific tasks, exposes a local OpenAI-compatible API server so other applications can call the same running models, and integrates the Model Context Protocol for agentic tool use.

Building from source needs Node.js, Yarn, Make and Rust for the Tauri desktop shell, with selectable engine variants for CPU, Vulkan, Metal, CUDA and ROCm backends, and prebuilt installers exist for Windows, macOS and Linux.

Rust, license unspecified ("NOASSERTION") in repository metadata.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.