Skip to content

Latest commit

 

History

History
13 lines (9 loc) · 727 Bytes

File metadata and controls

13 lines (9 loc) · 727 Bytes

ADR 006 — No local LLM as the primary brain interface

Status: accepted · Date: 2026-07

Context

Ollama + Llama 3.2 3B was installed and benchmarked as a potential local reasoning layer.

Decision

Rejected as primary: measured ~93 seconds for trivial inference on the Pi 4 CPU. Cloud AI (Claude Code) handles vault reasoning and organization; local processing is reserved for cases where data sensitivity outweighs everything else.

Consequences

  • The sensitive-content boundary must be enforced by workflow (which files get read into cloud context), not by tooling defaults. Documented in the vault's usage conventions.
  • Revisit if the node is ever replaced with hardware that changes the latency math.