Models and Keys

Start with local memory mode unless you know you need automated language-heavy maintenance. It gives you storage, embeddings, dedupe, hybrid search, MCP recall, and local artifacts.

Add an on-device model or Anthropic key when you want richer daemon-side extraction, page synthesis, recaps, and knowledge graph work.

Local memory mode is the no-model default. It is enough for the core work loop: brief, capture, recall, handoff, distill from the agent side, and inspect local artifacts.

This mode is also the right starting point when you want the smallest install path or when a machine cannot run local model inference comfortably.

An on-device model lets the daemon perform more language work locally. It can help with classification, extraction, title generation, recaps, and other maintenance tasks without sending those daemon-side prompts to an external API.

Local model capability is still bounded by hardware and context limits. For large distillation jobs, an API provider can be stronger when you choose to configure one.

A configured Anthropic key is bring-your-own-key for daemon-side language tasks. It is optional and should be treated as an explicit tradeoff: stronger language work in exchange for sending the relevant task prompt to the API provider.

The CLI can read ANTHROPIC_API_KEY through the key setup path. Your connected AI client may already call its own provider during normal chat; this page only describes Wenlan's daemon-side model and key paths.

Claude Code skills can classify captures, write handoffs, and synthesize pages from inside the active agent session. That is why Wenlan remains useful before you configure a daemon model.

The daemon stays the store and retrieval layer. The agent can supply language judgment when it is already in the work context.