SillyTavern
A local LLM frontend that connects to local backends and cloud APIs, with lorebooks, image generation and voice. Open source under AGPL-3.0.
SillyTavern is a locally installed LLM frontend for AI hobbyists who want detailed control over character chats and prompts. It builds on TavernAI as an independently developed fork and brings text models, image generation and voice into one interface. It's open source under AGPL-3.0.
The interface runs on your own hardware, with support for Windows, macOS, Linux, Android through Termux, and Docker. It connects to local backends such as KoboldAI/CPP, Ooba and Tabby, or cloud services including OpenAI, OpenRouter, Claude, Mistral and NovelAI. The interface runs locally; choosing a cloud API sends generation requests to that provider. The project offers no hosted service and doesn't programmatically track user data.
Character chat features include WorldInfo lorebooks for supplying background information, extensive prompt controls and a Visual Novel Mode. You can customize the interface, translate conversations automatically and add capabilities through third-party extensions. Its mobile-friendly layout also suits smaller screens.
Automatic1111 and ComfyUI integrations bring image generation into the chat interface, while TTS support adds spoken output. The frontend itself has modest hardware needs and runs on machines that support Node.js. Running models locally has separate requirements that depend on the model and backend; the project's recommendation is an NVIDIA 3000-series GPU with at least 6GB of VRAM.
