Quiz / chat-hybrid-web-yes

Open WebUI

Chat UIsLocal + hybridWeb

Browser chat against any OpenAI-compatible server. Open WebUI is the usual self-hosted pick. The llama.cpp built-in web UI is the zero-extra-process option on :8080.

Hybrid (the same toggle as /calculator?usage=hybrid): keep private or always-on turns on the Radeon; send token-heavy reasoning to a cloud model the harness already supports. This page does not quote cloud prices.

Open Open WebUI Connect to :8080 / :8083 Change answers

Also consider

LibreChat — One UI for local /v1 and cloud providers.
AnythingLLM — Docs + chat with a local /v1. RAG-shaped, not a coding agent.
SillyTavern — Roleplay / character chat, not a coding agent.
llama.cpp built-in web UI — Fastest chat on the daily-driver server. No extra process.