Show HN: Chitchat, an easy-to-use, cross-platform, chat-based LLM interface
clarkmccauley.comJust finished the first draft of my weekend project. Sadly my industry is far away from all the exciting machine learning developments happening right now, so I wrote this project as my first exploration into the world of LLMs. It's not perfect, but I'm excited to see where the project goes from here!
https://github.com/clarkmcc/chitchat
My main motivations were:
- Easy-of-use: Many models are supported out-of-the-box so users don't have to figure out how to download, where to save, etc.
- Intuitive: A clean interface
- Cross platform: The project is written in Rust and cross-compiled to other platforms. You don't have to have Python or the C++ toolchain installed to use.
- Chat-based experience: Model sessions are persisted so the model is contextually aware of your conversation. No add documents or memory context? That's a good idea to tackle next. The project is only a few days old so I haven't added this yet. Will look into it! It does have memory context in the sense that as you chat, it will remember your messages, but there's no support for pre-populating the context from a document (though you could drop a bunch of content into the warmup prompt right now). No release build for linux? Not yet, I haven't had a chance to test on Linux but it should compile fine. Tauri doesn't have great support for cross-compilation, you need to actually be on the target platform.