Search code, repositories, users, issues, pull requests...
Stina is a lightweight AI chat client specifically designed for environments with strict restrictions. In many government, healthcare, and large corporate settings, stringent IT policies prohibit the use of web servers, installations of new software, or access to online AI chat bots.
Stina is a client-side solution that requires no server, no installations, and no build tools. Chat with with LLMs with your own API keys or a local Ollama instance after downloading the repo and opening the chat.html file from the file system.
Stina can be hosted on a SharePoint server, run directly from the filesystem, or accessed through a local web server. It supports multiple language models, custom instructions, and dynamic system prompts.
Obtain API keys from your language model provider (e.g., Azure AI Foundry, OpenAI). If using Ollama, ensure it's running locally.
models.js: Define custom models or override existing ones. Stina currently only supports setting model configurations through the models file. If you need models with differnt temperature, max tokens, or context length, you can add them here.
