Skip to main content
klaw

What is klaw?

klaw is enterprise AI agent orchestration — like kubectl, but for AI agents.
Or control everything from Slack:

Quick Start

Install and run your first agent in 5 minutes

Core Concepts

Understand agents, namespaces, and tools

Slack Integration

Control agents from Slack

CLI Reference

kubectl-style command reference

The Problem

You’re running AI agents in production:
  • Lead Scorer — analyzes CRM leads every hour
  • Competitor Watch — monitors competitor websites daily
  • Ticket Handler — auto-responds to support tickets
  • Report Generator — creates weekly analytics reports
But managing them is chaos: OpenClaw works, but deployment is painful and scaling is worse. klaw brings Kubernetes-style operations to AI agents. One binary. Deploys in seconds.

The Kubernetes Parallel

If you know kubectl, you already know klaw:

Key Features

Familiar commands: klaw get, klaw describe, klaw logs, klaw apply. If you know Kubernetes, you know klaw.
Manage agents from Slack. @klaw status, @klaw run agent, @klaw logs. Your AI command center.
Isolate agents by team. Sales can’t access support’s secrets. Each namespace has its own tools and permissions.
klaw cron create — no external scheduler needed. Run agents hourly, daily, weekly.
Scale from laptop to cluster. Controller dispatches tasks to worker nodes automatically.
Claude, GPT-4, Gemini, Llama, and 300+ more through a single API. Swap models without code changes.
One ~20MB binary with zero dependencies. No Python, no Node.js. Just klaw.

Architecture Overview

Quick Example

Create a scheduled agent:

What’s Next?

Quick Start

Install klaw and run your first agent

Agents

Learn how agents work

Namespaces

Isolate agents by team

Slack Integration

Control agents from Slack