🛡
IronClaw
Security-hardened · Deny-by-default · Mandatory allowlist · Audit logged
MIT core (free) Syscall-level sandbox 53 compatible official skills Linux · macOS · WSL2 Claude · OpenAI · Ollama

IronClaw is a security-hardened fork of the OpenClaw architecture. Where OpenClaw optimises for flexibility, IronClaw optimises for a minimal, auditable attack surface. Every skill must be explicitly allowlisted. Every outbound network call is blocked until you grant the specific host. Every security event is logged — mandatorily. If your agent handles credentials, production infrastructure, or shared access, IronClaw's defaults are worth the extra setup time.

Skills resources for IronClaw

IronClaw uses the same skill architecture as OpenClaw — all 53 official skills are compatible. We don't maintain a separate skills database for IronClaw:

Skills Guide: Write Your Own Custom Skills
Skills Database: 53 Verified Official Skills

Install commands are identical: ironclaw skill install <name> — then run ironclaw allowlist add <name> to activate it.

At a Glance

LicenseMIT core (free); advanced audit tooling commercial
Installnpm install -g ironclaw
RequiresNode.js 22.16+ or Node 24; Linux or macOS (WSL2 on Windows)
Port18790 (can run alongside OpenClaw on 18789)
SandboxDeny-by-default, seccomp-bpf (Linux) / sandbox-exec (macOS)
Skill activationInstall + ironclaw allowlist add <skill>
Audit logMandatory — gateway won't start without writable log path
Compatible skillsAll 53 official OpenClaw skills
Typical monthly costSame as OpenClaw — depends on model choice, not IronClaw itself

Related on This Site

  • OpenClaw hub — the base framework IronClaw forks from; simpler setup, same skill ecosystem
  • NemoClaw — a different security approach: Docker + OpenShell policy sandbox rather than syscall enforcement
  • OpenClaw Security Hardening — if you want OpenClaw with better security but don't need IronClaw's full enforcement
  • Weekly News Digest — IronClaw security advisories and CVE summaries every Monday