Multi-agent parallelism applies to all LLMs, not just local

LLM-ROUTING.md

@@ -65,14 +65,17 @@ curl http://127.0.0.1:8080/v1/chat/completions \
 - No rate limits
 - No cost accumulation
 
-### 🚀 Parallel Work → **MULTI-AGENT LOCAL**
+### 🚀 Parallel Work → **MULTI-AGENT**
 When speed matters, spawn multiple workers:
 ```bash
-# Flynn can spawn sub-agents hitting local LLMs
+# Flynn can spawn sub-agents targeting any LLM
 # Each agent works independently, results merge
 ```
 - Use for: bulk analysis, multi-file processing, research tasks
-- Coordinate via sessions_spawn with local model routing
+- Coordinate via `sessions_spawn` with model param
+- **Local:** best for privacy + no rate limits
+- **Cloud:** best for complex tasks needing quality
+- Mix and match based on task requirements
 
 ### ⚡ Quick One-Shot → **COPILOT or LOCAL**
 ```bash

MEMORY.md

@@ -55,7 +55,12 @@
 **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
+
+**Multi-agent parallelism** — Spawn multiple agents for speed:
+- Works with local AND cloud LLMs
+- Local: best for privacy, no rate limits
+- Cloud: best for complex tasks needing quality
+- Mix based on task requirements
 
 **Always check availability** — Local LLMs may not be running:
 ```bash