Hollama

Hollama is an open-source LLM chat app whose interface runs entirely in your browser. It's for people who want to chat with local AI through Ollama or connect to OpenAI servers, with support for multiple server connections. The interface stores data locally in the browser; the connected server handles model requests, so where inference runs depends on the server you choose.

It supports text, vision and reasoning models. Large prompt fields give you room for longer inputs, while editable messages and retries let you revise a conversation without starting over. Custom system prompts and advanced Ollama parameters let you adjust model behavior. You can also download Ollama models through the interface.

For conversations that include code or technical material, Hollama renders Markdown with syntax highlighting and KaTeX math notation. It includes code editor features, and you can copy a code snippet, a single message or an entire session. Import and export cover stored data, including session history, attachments, custom model settings and the knowledge base. Server connections, model filters and labels are part of its data management settings too.

The live demo requires no sign-up. Hollama also offers downloads for macOS, Windows and Linux, plus Docker self-hosting. Its responsive layout supports different screen sizes, and the interface has multiple languages and light and dark themes. The project uses the MIT license.