From 4e4abcf6cd12503ce29a237f8004b654ad0bd8a0 Mon Sep 17 00:00:00 2001 From: William Valentin Date: Mon, 26 Jan 2026 22:35:00 -0800 Subject: [PATCH] Add LLM routing principles to MEMORY.md --- MEMORY.md | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/MEMORY.md b/MEMORY.md index 16efb07..3d5b305 100644 --- a/MEMORY.md +++ b/MEMORY.md @@ -51,6 +51,22 @@ **Why different from Claude Code:** Claude Code is CLI-first with routing-heavy design. Clawdbot is conversational — single capable assistant who calls for backup when needed. +### 2026-01-26 - LLM Routing Principles +**Local First** — Use local LLMs (llama-swap @ :8080) when: +1. **Privacy/Confidentiality** — Sensitive data never leaves the machine +2. **Long-running tasks** — No API costs, no rate limits, no timeouts +3. **Parallel work** — Spawn multiple agents hitting local endpoint + +**Always check availability** — Local LLMs may not be running: +```bash +curl -sf http://127.0.0.1:8080/health +``` + +**Routing priority:** +1. Local (free, private) → 2. Copilot (free-ish) → 3. Cloud APIs (paid) + +**Never send sensitive data to cloud APIs without explicit permission.** + ## Preferences Discovered *(Add as I learn them)*