Self-hosted runtime

Jan

Jan is a desktop app from Menlo Research for running open models on your own machine.

Website (opens in a new tab)Source (opens in a new tab)

Checked 2026-10-31

Jan is a desktop app from Menlo Research for running open models on your own machine. Its docs describe Jan Desktop as a chat app with model management, MCP connectors and a local API server, and a separate Jan Agent for running coding agents against a local model. The README lists downloads for Windows, macOS and Linux. The built-in server is OpenAI compatible and defaults to http://127.0.0.1:1337/v1, with chat completions at /v1/chat/completions; host, port and prefix can be changed. We would suggest it to people who want a ready-made app with a chat window and a local endpoint for other tools, without touching a terminal. The source is on GitHub under an Apache 2.0 license; GitHub labels the file as Other because of an added attribution request. We found no price stated, and no pricing is needed to run local models. The limits are on the docs side: the server page lists only chat completions, and we could not find GPU support or a hardware list in the pages we read. We have not run it ourselves for this note.

Mentioned here

Questions

How much does Jan cost?

Free; Jan is open source and runs on your own computer. We found no price on its docs (checked 31 October 2026).

Is Jan OpenAI compatible?

Yes, it offers an OpenAI-compatible API, so most agents and SDKs can point at it by changing the base URL.

Can I self-host Jan?

Yes, it can run on your own servers.

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Similar

  • Text Generation Inference

    Text Generation Inference, or TGI, is Hugging Face's open server for running large language models on your own GPUs.

    • Self-hosted runtime
    • OpenAI compatible
    • Self-hostable

  • vLLM

    vLLM is a high-throughput, memory-efficient serving engine for large language models, run as a server you host yourself.

    • Self-hosted runtime
    • OpenAI compatible
    • Self-hostable

  • LocalAI

    LocalAI is an open-source runtime that runs AI models on your own hardware.

    • Self-hosted runtime
    • OpenAI compatible
    • Self-hostable

  • SGLang

    SGLang is a serving framework for large language and multimodal models, aimed at low latency and high throughput from a single GPU up to large clusters.

    • Self-hosted runtime
    • OpenAI compatible
    • Self-hostable