Summary: A complete walkthrough from zero to a running AI agent. We'll install OpenClaw on a Raspberry Pi, connect it to Ollama for LLM inference, create a Telegram bot, and have your agent respond to messages — all in under an hour.

What You'll Need

Raspberry Pi 4B (2GB+ RAM) or a Linux/Mac laptop
Stable internet connection
Telegram account (for messaging integration)
Basic command line familiarity

Step 1: Install Ollama

Ollama runs LLMs locally — no API keys, no cloud dependencies, your data stays on your hardware.

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

Verify installation:

ollama --version

Step 2: Install OpenClaw

OpenClaw is the agent runtime that orchestrates LLM calls, manages memory, and connects to messaging platforms.

npm install -g openclaw
openclaw init
openclaw gateway start

Step 3: Create a Telegram Bot

Open Telegram, search for @BotFather, send /newbot, and follow the prompts. Save the bot token securely.

Step 4: Connect Telegram to OpenClaw

Edit your gateway configuration to add the Telegram provider:

providers:
  telegram:
    enabled: true
    botToken: "YOUR_BOT_TOKEN"

Restart the gateway:

openclaw gateway restart

Step 5: Talk to Your Agent

Find your bot in Telegram, send /start, and say hello. Your AI agent is now live.

Next Steps

Customize your agent's personality in SOUL.md
Add your personal context in USER.md
Install skills from ClawHub
Set up scheduled tasks with cron jobs

✨

Digital Futures Consultancy

Singapore-based AI-native consultancy. We build production-grade AI systems for SMEs. digitalfutures.asia

← Back to Insights

How to Build Your First AI Agent with OpenClaw and Ollama?