Skip to content

Ollama

A local Ollama server via its native /api/chat endpoint, selected with LLM_PROVIDER=ollama, used to extract facts from conversations.

Enable it

bash
LLM_PROVIDER=ollama
OLLAMA_BASE_URL=http://localhost:11434
# Default model is llama3.1; no API key (local server).

Configuration

VariableDefaultDescription
LLM_PROVIDERopenaiSet to ollama.
OLLAMA_BASE_URLhttp://localhost:11434Base URL of the Ollama server.

Notes

  • Uses Ollama's native /api/chat endpoint, not the OpenAI chat-completions protocol.
  • Default model is llama3.1; JSON requests are forced with Ollama's format: "json".
  • Local server with no authentication, so no API key is needed.

The memory layer for AI agents.