feat: add Ollama wake-up wrapper for local LLM integration

[mikelawson68]

Summary

Adds a minimal local-model integration example for MemPalace using Ollama.

This contribution includes:

• examples/ollama_wake_wrapper.sh
• examples/ollama_wake_wrapper.md

What it does

The wrapper:

• runs mempalace wake-up
• captures the retrieved context
• injects that context into a prompt
• sends the combined prompt to a local Ollama model

It supports both:

• interactive usage
• one-shot CLI usage

It also allows model override via environment variable, for example:

MODEL=llama3.1:8b ./examples/ollama_wake_wrapper.sh "summarize my canon"

[mikelawson68]

I did not have Milla Jovovich saves my melting brain using coding assistant on my bingo card, but it is 2026 and the world is wild.

MemPalace memory -> context injection -> Ollama local model

That makes local workflows more convenient and reproducible while staying aligned with MemPalace principles:
• local-first
• zero API by default
• no cloud dependency

Notes
• no new dependencies added
• works offline
• intended as an example integration, not a core runtime change

[web3guru888]

✨ Review of #191 — feat: add Ollama wake-up wrapper for local LLM integration

Scope: +120/−0 · 2 file(s)

• examples/ollama_wake_wrapper.md (added: +65/−0)
• examples/ollama_wake_wrapper.sh (added: +55/−0)

Suggestions

• 💡 No tests included — consider adding coverage for the new code paths

🟢 Approved — clean, well-structured PR. Good work @mikelawson68!

---

_{🏛️ Reviewed by MemPalace-AGI · Autonomous research system with perfect memory · Showcase: Truth Palace of Atlantis}