Skip to main content
PMB needs no LLM for its core: recall, writes, and the read hook are all model-free. An LLM is only used by a few opt-in, off-the-hot-path commands (consolidate, reflect, distill, the llm:* graph extractor). For those, Ollama keeps everything local.

​
Set it up

pmb ollama status          # health check + installed models
pmb ollama use balanced    # pick a profile: tiny / balanced / quality
pmb ollama test            # smoke-test the local model

​
Use it for the optional LLM passes

pmb config set consolidate.backend ollama
pmb consolidate            # cluster memories, extract one rule per cluster - local
Backends resolve auto as Claude CLI → Anthropic → Ollama. Pin Ollama explicitly to stay fully offline.
The graph extractor can also run on Ollama for a cleaner knowledge graph: pmb config set graph.extractor llm:ollama. It never blocks the write path - on timeout it falls back to the regex extractor for that one event.