← back

OpenClaw in 5 Minutes

What you can do with it, by example.

OpenClaw is a personal AI assistant that runs on your laptop. You talk to it through Discord, Telegram, Slack, or WhatsApp. It uses Claude under the hood. Everything stays on your machine.

Create an agent

You write a short config: pick a model, list what tools it can use, give it a personality. That's it — no code, no deployment.

You want a cooking helper and a code reviewer.
"chef" → Sonnet, tools: [recipe-search], identity: "friendly cook"
"reviewer" → Opus, tools: [file-read, git-diff], identity: "senior engineer"
Two agents, same machine, completely independent.

Talk to it from any app

Message your agent on Telegram. Or Discord. Or Slack. OpenClaw receives the message, runs Claude with your conversation history, and sends the reply back to whatever app you used.

You DM your bot on Telegram: "what should I make with chickpeas?"
OpenClaw loads the chef agent, feeds Claude your last 20 messages for context, gets a recipe back, sends it to Telegram. Takes a few seconds.

Route people to different agents

Assign specific people, servers, or groups to specific agents. Everyone else hits a default. Just config, no code.

Your friend Alice → chef agent
Your work Discord server → reviewer agent
Everyone else → general agent (default)

Add tools with plugins

Need your agent to check the weather, search files, or hit an API? Install a plugin. It registers its tools in one function call, and any agent you allow can use them.

Install a weather plugin → it registers get_forecast
Add "weather" to your chef agent's skill list
Now: "what should I grill this weekend?" checks the forecast before answering.

Let agents call each other

An agent can spawn another agent mid-conversation. The child does its job, and the result gets injected back automatically.

You ask your researcher to analyze a repo.
It spawns reviewer to read the code, and summarizer to condense findings.
Both results flow back into the researcher's conversation — it synthesizes and replies to you.

Auto-remember with hooks

Hooks run automatically when things happen — a message arrives, an agent starts up. You don't call them; they fire on their own.

The built-in session-memory hook fires after every message.
It saves a summary so your agent remembers what you talked about yesterday — no manual setup.
Worth knowing: The gateway IS the agent — runEmbeddedPiAgent is an in-process call, not a proxy. This means one process handles everything (simple, but single point of failure). Docker sandboxing exists but defaults to subagents-only. For multi-tenant or untrusted deployments, see the systems comparison.
Want the full architecture?
Deep Dive · vs 5 Systems · Agent Hub