How SillyTavern Works Under the Hood: Architecture Explained
SillyTavern's architecture bridges your local hardware to cloud or self-hosted LLMs. Here's how the routing, memory, and character card system actually function.
Explore all 26 articles about Self-Hosted AI Apps. Practical guides, reviews, and deep dives — tested and published regularly.
All 26 articles in this topic, newest first.
SillyTavern's architecture bridges your local hardware to cloud or self-hosted LLMs. Here's how the routing, memory, and character card system actually function.
Step-by-step guide to install Immich on your homelab with Docker Compose. Set up self-hosted photo backup…
Honest report running Whisper locally for speech recognition. What the demos hide, what broke, why I…
LibreTranslate stops working after startup? Walk through the actual errors I hit—memory limits, model downloads, GPU…
PhotoPrism runs AI tagging locally on your hardware. Here's how face detection, object classification, and indexing…
Tested Stable Diffusion WebUI against ComfyUI and InvokeAI on my homelab GPU. Here's where each one…
Setting up a local character chat interface. I've done this three times now. Here's what actually…
Wire ComfyUI into Home Assistant so your automations can generate images on demand. The setup that…
Wiring Immich into Home Assistant for quick access to recent photos and basic search. It's not…
Running out of memory during model initialization. Here's what I did wrong and how I fixed…