← Admin Console

Hindsight LLM Provider

Configure which LLM Hindsight uses for entity extraction and memory processing.

Checking Hindsight status...
Quick presets
The model used for entity extraction during memory retention.
Required for Ollama. For OpenAI/Anthropic, leave blank to use default endpoints.
Current key: not set
Note: After saving, run deploy.sh to restart the Hindsight container with the new LLM settings. Changes don't take effect until the container restarts.