← Back to LLM Wiki
LLM Wiki · Agent Runtime · Claw Ecosystem

OpenClaw

The flagship agent runtime in the Claw ecosystem. TypeScript, 50+ integrations, plugin-based, and designed to run on customer-owned edge hardware.
OpenClaw is not an LLM — it is the runtime that turns an LLM into a deployable agent. Built on Qwen-Agent for the inner loop and wrapped in a TypeScript control plane, it ships with department-specific loadouts, 50+ first-party integrations, and a plugin system for everything else. The target form factor is a Mac Mini on the customer's desk: data sovereignty first, cloud economics as a fallback.
Agent Runtime TypeScript Qwen-Agent Edge Deploy On-Premise

Quick Facts

Category
Agent runtime (not a model)
Language
TypeScript
Inner loop
Qwen-Agent · Qwen3-Coder (default) · any OpenAI-compatible endpoint
Control plane
Claude Code Slack (operator conversations)
Security layer
FrawdBot (behavioral analysis, 21K lines of detection)
Integrations
50+ first-party; plugin system for the rest
Target hardware
Mac Mini · MacBook Pro · on-prem Linux
Deployment time
6–12 hours end-to-end
License
Open source (see Claw ecosystem on GitHub)

Summary

OpenClaw is the enterprise-tier runtime in the Claw ecosystem — the flagship among six sibling runtimes (NanoClaw, MicroClaw, PicoClaw, ZeroClaw, ExoClaw) that share a common architecture and differ on form factor and host environment. Where OpenClaw fits is the largest envelope: a managed agent that runs on customer-owned Mac hardware, connects to internal tools via 50+ first-party integrations and a plugin system, and is operated through a Slack-based control plane.

The design philosophy is on-premise first. The inference engine and all tool calls live on the customer's hardware. The LLM (Qwen3-Coder by default, but pluggable) is self-hosted. FrawdBot behavioral analysis is bundled in — not an upsell — so insider-threat detection runs against every agent action. Only the operator interface (Claude Code Slack) touches the outside world.

Architecture

Deployment Model

A typical OpenClaw deployment takes 6–12 hours from first call to production-ready agent:

  1. Hardware — Mac Mini M-series delivered or provided by the customer. Tailscale tunnel established for management.
  2. Base install — OpenClaw runtime, Qwen-Agent, chosen LLM weights (Qwen3-Coder default), FrawdBot, observability stack (OTEL + Langfuse + ClickHouse).
  3. Department loadout — select one or more loadouts. Customize system prompt, tool allowlist, and approval policies.
  4. Integrations — OAuth or service-account setup for Slack, Gmail, Linear, etc. Plugin installs for anything beyond the 50+ first-party list.
  5. Control plane — Claude Code Slack channel provisioned. Operators added.
  6. Ship — agent goes live. SRE dashboard accessible via Tailscale.

When to Choose OpenClaw

OpenClaw is the default pick when any of the following apply: the deployment must stay on customer-owned hardware, the workload benefits from department-specific tool bundles, the customer wants Slack as the agent control plane, or regulatory requirements preclude a cloud-managed agent. For other profiles, another Claw runtime is typically a better fit:

Tradeoffs

Related

References

  1. Organized AI on GitHub
  2. The Agent Infrastructure Stack — Organized AI
  3. The Infrastructure Playbook — Organized AI
  4. Edge Compute Economics — Organized AI
  5. The Observability Architecture — Organized AI