{"id":11478,"date":"2025-08-14T01:02:00","date_gmt":"2025-08-14T05:02:00","guid":{"rendered":"https:\/\/www.both.org\/?p=11478"},"modified":"2025-08-05T10:33:15","modified_gmt":"2025-08-05T14:33:15","slug":"introducing-jan-a-privacy-centric-open-source-gpt-for-ai-enthusiasts","status":"publish","type":"post","link":"http:\/\/www.both.org\/?p=11478","title":{"rendered":"Introducing Jan: A Privacy-Centric, Open-Source GPT for AI Enthusiasts"},"content":{"rendered":"
\r\n
\r\n \r\n <\/i>\r\n <\/a>\r\n <\/span>\r\n<\/div><\/div>\n

Are you looking for a locally hosted open source GPT that protects your privacy while allowing you to leverage the latest AI models? Then you need to download\u00a0Jan<\/a>. Jan is easy to install on\u00a0Linux<\/a>,\u00a0macOS<\/a>,\u00a0and\u00a0Windows<\/a>\u00a0and has excellent documentation to guide that process.<\/p>\n\n\n\n

Jan is a ChatGPT alternative that runs 100% offline on your desktop. The goal is to make it easy for anyone, with or without coding skills, to download and use AI models with complete control and privacy. Jan operates on a truly open-source model with an Apache 2.0\u00a0license<\/a>. It stores all data locally, so internet usage is optional since it can function entirely offline. Users have the flexibility to choose AI models, both local and cloud-based, without the worry of data being sold. Jan is powered by Llama.cpp, a local AI engine that offers an OpenAI-compatible API This enables you to utilize AI capabilities in various applications on your laptop or PC.<\/p>\n\n\n\n

I downloaded and installed Jan on Linux Mint 22.1 using the\u00a0deb<\/a><\/strong>\u00a0file. If you are using a non-Debian-based Linux like Fedora, you can install the\u00a0app image<\/a>\u00a0file.<\/span> I also\u00a0downloaded\u00a0and installed Jan on my M3 MacBook Air. The project has excellent\u00a0documentation,\u00a0which makes it easy to get started using Jan. Be sure to consult it.<\/p>\n\n\n\n

As suggested in the documentation, I downloaded and installed the\u00a0Jan-nano-128K<\/a>\u00a0model. The project provides excellent\u00a0resources<\/a>\u00a0that helped me learn how to use the LLM.<\/span> I decided to see if it could give me the code for a simple web app that converted Fahrenheit to Celsius using Python and Flask. The model took about fifteen seconds and then gave me the code, which I copied and pasted into VSCodium and saved it as a Python file. The model suggested I install Flask and gave me the code\u00a0pip3 install Flask.\u00a0I saved the file as directed and then presented me with the dialogue below. The result was two files, which I saved in the Python virtual environment on my computer.<\/p>\n\n\n\n

The Python file:<\/p>\n\n\n\n

from flask import Flask, request, render_template\n\napp = Flask(__name__)\n\n@app.route('\/', methods=['GET', 'POST'])\ndef convert_temp():\n    result = None\n    if request.method == 'POST':\n        fahrenheit = float(request.form['fahrenheit'])\n        celsius = (fahrenheit - 32) * 5\/9\n        result = celsius\n    return render_template('convert.html', result=result)\n\nif __name__ == '__main__':\n    app.run(debug=True)<\/code><\/pre>\n\n\n\n
The second file was an HTML file, which was stipulated in the code Jan produced.<\/p>\n\n\n\n
<!DOCTYPE html>\n<html>\n<head>\n    <title>Fahrenheit to Celsius Converter<\/title>\n<\/head>\n<body>\n    <h1>Fahrenheit to Celsius Converter<\/h1>\n    <form method=\"post\">\n        <label for=\"fahrenheit\">Enter Fahrenheit:<\/label>\n        <input type=\"text\" id=\"fahrenheit\" name=\"fahrenheit\" required>\n        <button type=\"submit\">Convert<\/button>\n    <\/form>\n    {% if result is not none %}\n    <h2>Result: {{ result }}\u00b0C<\/h2>\n    {% endif %}\n<\/body>\n<\/html><\/code><\/pre>\n\n\n\n
I copied both the code snippets into\u00a0VSCodium\u00a0and saved them to the Python virtual environment, which I created using the following command:<\/p>\n\n\n\n
python3 -m venv temperature<\/code><\/pre>\n\n\n\n
I opened a terminal and gave the following command\u00a0python3 temperature.py<\/code>. Then I opened my browser and pointed it to\u00a0https:\/\/127.0.0.1:5000<\/code>\u00a0as directed and was presented with the following simple web app that I had requested the model to create.<\/p>\n\n\n\n
\"image<\/figure>\n\n\n\n
Reading the project\u2019s extensive\u00a0documentation<\/a>\u00a0is crucial and I also found that the community maintains a number of useful resources including\u00a0Github<\/a>,\u00a0Discord<\/a>,\u00a0X\u00a0<\/a>and\u00a0LinkedIn<\/a>. The project has a\u00a0blog<\/a>\u00a0with a number of useful resources too.<\/p>\n","protected":false},"excerpt":{"rendered":"
Are you looking for a locally hosted open source GPT that protects your privacy while allowing you to leverage the latest AI models? Then you need to download\u00a0Jan. Jan is easy to install on\u00a0Linux,\u00a0macOS,\u00a0and\u00a0Windows\u00a0and has excellent documentation to guide that process.<\/p>\n","protected":false},"author":32,"featured_media":4837,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_lmt_disableupdate":"","_lmt_disable":"","footnotes":""},"categories":[307,5,158],"tags":[123,806],"class_list":["post-11478","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","category-linux","category-open-source","tag-ai","tag-gpt"],"modified_by":"David Both","_links":{"self":[{"href":"http:\/\/www.both.org\/index.php?rest_route=\/wp\/v2\/posts\/11478","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.both.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.both.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.both.org\/index.php?rest_route=\/wp\/v2\/users\/32"}],"replies":[{"embeddable":true,"href":"http:\/\/www.both.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=11478"}],"version-history":[{"count":3,"href":"http:\/\/www.both.org\/index.php?rest_route=\/wp\/v2\/posts\/11478\/revisions"}],"predecessor-version":[{"id":13202,"href":"http:\/\/www.both.org\/index.php?rest_route=\/wp\/v2\/posts\/11478\/revisions\/13202"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/www.both.org\/index.php?rest_route=\/wp\/v2\/media\/4837"}],"wp:attachment":[{"href":"http:\/\/www.both.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=11478"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.both.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=11478"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.both.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=11478"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}