Install with GitHub Copilot in VS Code

  1. Open VS Code → Copilot Chat → Agent mode.

    Don't have VS Code? Download VS Code. Set up Copilot.

  2. Copy this prompt, paste it into Copilot Chat, and send it.

Install the RAPP Brainstem on this computer and get it running. Follow https://kody-w.github.io/grail-layers/skills/rar-easy-mode/SKILL.md exactly. Ask me before anything that needs my password or a sign-in code, show me the GitHub code when it appears, and finish by sending one test message to the Brainstem and showing me the reply. Then open http://localhost:<port>/ (using the actual port) in VS Code's integrated browser for a short guided tour, typing and sending a chat message with browser tools so I can watch. If those tools are unavailable, use Browser: Open Integrated Browser and guide me manually, stating that limitation.

Advanced: install from a terminal

RAPP Brainstem

A local-first AI agent server for the RAPP Agent Registry.
Cloud AI or fully on-device with Ollama. Your choice.

Start simple. Layer up when you're ready.
macOS/Linux
# Works everywhere. Installs everything.
$ curl -fsSL https://raw.githubusercontent.com/kody-w/RAR/main/scripts/install.sh | bash copy
O

Ollama — Local-First AI

True on-device inference — no cloud, no keys, no data leaves your machine
Local-First >

Cloud AI is a phone call. Local AI is thinking with your own brain. Ollama runs Gemma 4 directly on your hardware — the Brainstem reasons locally. Zero network calls for inference. Air-gapped capable.

1. Install Ollama

One command. Works on macOS, Linux, and Windows.

curl -fsSL https://ollama.com/install.sh | sh

Or download from ollama.com/download for macOS / Windows.

2. Pull a model

Pick based on your hardware. E2B for phones, E4B for laptops, 26B/31B for workstations.

ollama pull gemma4

3. Launch the Brainstem with local AI

One command — starts Ollama, loads the model, launches the Brainstem runtime. No API key needed.

ollama launch brainstem --model gemma4

4. Connect the Agent Store

Open the RAPP Agent Store, go to Stream > Ollama, and connect to localhost:11434. Flick agents to the Brainstem — they reason locally.

ModelSizeContextBest for gemma4:e2b7.2 GB128KPhone / tablet gemma4:e4b9.6 GB128KLaptop gemma4:26b18 GB256KWorkstation (MoE) gemma4:31b20 GB256KFrontier local (Dense)

Gemma 4 by Google DeepMind. Multimodal (text + image + audio on edge models). Native function calling. 256K context on workstation models. Reasoning, coding, agentic workflows — all on-device.

B

The Brainstem

Local agent server — the survival basics
Start here >

The biological brainstem keeps you alive — breathing, heartbeat, reflexes. Your AI brainstem does the same: it runs the core agent loop, calls tools, and responds. Everything else builds on top of this.

1. Authenticate with GitHub

The GitHub Copilot CLI provides the AI engine. No OpenAI keys needed.

gh auth login

2. Start the brainstem

The server starts on port 7071 with a chat UI, health endpoint, and agent auto-discovery.

brainstem

3. Talk to it

Open localhost:7071 in your browser, or hit the API directly.

curl -s localhost:7071/health | python3 -m json.tool

4. Make it yours

Write a soul.md to define its personality. Drop *_agent.py files into the agents folder to give it skills. Point SOUL_PATH and AGENTS_PATH in .env to your private files.

H

The Hippocampus

Persistent memory — runs local, deploys to Azure
Next step >

The hippocampus is where memories form. One command sets up everything — Python, Azure Functions Core Tools, venv, dependencies, start script. No Azure account or API keys needed. Auth happens through the chat UI.

Run the one-liner

This is the only step. It clones CommunityRAPP, installs everything, and tells you what to do next.

curl -fsSL https://raw.githubusercontent.com/kody-w/RAR/main/scripts/install_hippocampus.sh | bash

Windows: irm https://raw.githubusercontent.com/kody-w/RAR/main/scripts/install_hippocampus.ps1 | iex

Full onboarding guide

> Advanced: manual steps

Start it & authenticate

Open index.html in your browser and send a message. The chat UI walks you through GitHub device-code auth — no env vars to set.

cd ~/rapp-projects/my-project && ./start.sh

Deploy to Azure (when ready)

Edit local.settings.json with your Azure OpenAI credentials, then publish.

func azure functionapp publish YOUR_APP_NAME --build remote
N

The Nervous System

Connect to Copilot Studio — reach into M365
Advanced >

Your nervous system extends your brain's reach to every part of your body — eyes, ears, hands. Copilot Studio does the same: it connects your agent to Teams, M365 Copilot, and the entire Microsoft ecosystem. Your brainstem becomes an enterprise AI.

1. Download the solution

Grab the Power Platform solution package. This .zip contains the declarative agent, connectors, and flows preconfigured for your Azure Function.

curl -fsSL -o MSFTAIBASMultiAgentCopilot.zip https://raw.githubusercontent.com/kody-w/RAR/main/scripts/MSFTAIBASMultiAgentCopilot.zip

2. Import into Power Platform

Go to make.powerapps.com > Solutions > Import > upload the .zip. This creates the Copilot Studio agent and Power Automate flows in your environment.

3. Wire the connector

Open the imported Power Automate flow and update the HTTP action URL to point to your deployed Azure Function endpoint from Step 2. Add your Function Key if using key-based auth.

4. Publish to Teams & M365 Copilot

In Copilot Studio, publish the agent. Your users can now talk to it in Teams, M365 Copilot, and any channel Copilot Studio supports. Same agent logic you tested locally — now enterprise-wide.

What you learn: Copilot Studio, declarative agents, Power Platform solutions, Teams integration, enterprise AI deployment.

Checking brainstem...
Agent Store RAPP Repo CommunityRAPP Ollama