Custom API provider falling back to Anthropic
Hey, I’m trying to run Moltbot using a custom OpenAI-compatible API provider.
The gateway starts correctly and shows the custom provider + model being used, but Moltbot still keeps falling back to Anthropic internally and fails because I haven’t configured an Anthropic API key.
From the logs it looks like some internal processes (e.g. session memory / slug generation) are still trying to call
Questions:
1. Is there a default internal model Moltbot uses for background hooks?
2. How can we fully disable Anthropic as a fallback?
3. Is there a way to force all internal LLM calls to use the configured provider only?
The gateway starts correctly and shows the custom provider + model being used, but Moltbot still keeps falling back to Anthropic internally and fails because I haven’t configured an Anthropic API key.
From the logs it looks like some internal processes (e.g. session memory / slug generation) are still trying to call
anthropic/claude-opus-*Questions:
1. Is there a default internal model Moltbot uses for background hooks?
2. How can we fully disable Anthropic as a fallback?
3. Is there a way to force all internal LLM calls to use the configured provider only?
The AI that actually does things. Emails, calendar, home automation - all from your favorite chat app. New shell, ready to help. The lobster way.
134,827Members
Resources
Recent Announcements
Similar Threads
Was this page helpful?
