Harnesses / Chat UIs / sillytavern
Chat UIsLocal + hybridWeb
SillyTavern
SillyTavern. API connections index checked 2026-10-12.
Character-oriented frontend. Connects to many local backends including llama.cpp and OpenAI-compatible Chat Completion.
What it’s for
Roleplay / character chat, not a coding agent.
Local endpoint
- llama-server base
http://127.0.0.1:8080/v1- Strata base
http://127.0.0.1:8083/v1- Model name
- Whatever the Chat Completion source lists after Connect
- API key
- If the server requires one
Optional function calling in Chat Completion sources — not documented as our daily-driver path.
Long context
Server -c. SillyTavern prompt plumbing can eat context; not measured here.
ROCm / Radeon gotchas
Frontend only. Keep llama-server on Vulkan.
Hybrid local + cloud
Cloud OpenAI-shaped sources plus local.
This is the same question as the calculator’sfully localversushybridtoggle. This page does not quote cloud prices.
Official links
Sources
Copy-paste
More on the connect page. Prove http://127.0.0.1:8080/v1/models first.
SillyTavern → llama-server :8080API: Chat Completion
Source: Custom / OpenAI Compatible
Server URL: http://127.0.0.1:8080/v1
API Key: local-not-a-secret
Exact llama-server flags for our daily driver stay TODO in stacks.yaml. This is the port only.
SillyTavern → Strata :8083API: Chat Completion
Source: Custom / OpenAI Compatible
Server URL: http://127.0.0.1:8083/v1
API Key: local-not-a-secret
Exact Strata flags for our rig stay TODO in stacks.yaml. This is the port only.
Next:compare · quiz · Hermes Agent