# Use a specific config file
llm-mem-mcp --config /etc/llm-mem/prod.toml
# Run with raw HTTP (skip rig-core) against a self-hosted llama.cpp
llm-mem-mcp --request-format raw
# Force re-download the model (skip cache)
llm-mem-mcp --no-cache-model
# Pre-populate the cache, then run normally
llm-mem-mcp --cache-dir /mnt/fast/models
# Use a different banks directory
llm-mem-mcp --banks-dir /mnt/data/banks
# Print the config template
llm-mem-mcp --generate-config > config.toml