IronClaw FAQ — Common Setup & Configuration Questions
Current stable is 1.1.0 — a ground-up rebuild of the runtime, storage, extension host and web UI, with no migration path from 0.29.x. Answers below about install commands, ports, the allowlist and configuration keys are accurate for 0.29.1 and do not describe 1.x.
For a clean 1.1.0 install, see the 1.1.0 quick start. Background: the 1.0.0 rearchitecture · 1.1.0 stable and 1.1.1-rc.1. This page is queued for a 1.x rewrite.
The most common IronClaw questions from the community — covering PostgreSQL requirements, skill allowlisting, WASM sandboxing, and how IronClaw's security-first design compares to a standard OpenClaw setup. Updated weekly.
Top Questions
What changed in IronClaw 1.4.0?
1.4.0 went stable on 2026-08-28 with 81 commits since 1.3.0, and the theme is work surviving things. A durable notification inbox means approvals and auth prompts outlive the session that raised them — the difference between an agent that runs long and one you can leave running overnight. Background subagents can run and deliver after the parent turn ends, with per-child delivery, activation provenance, a cap on autonomous wakes and healing sweeps for orphans. Sandboxes are now persistent per user on the local-Docker profile, so installs survive between commands, while the Railway preview profile keeps its ephemeral worker-per-command model. And a managed egress proxy holds credentials so sandboxed code can use them without ever receiving them. See the security guide and configuration for detail.
Does IronClaw require PostgreSQL to work?
Yes. IronClaw uses PostgreSQL as its primary database backend for agent memory, audit logs, and skill state. You need to install PostgreSQL 15 or higher and enable the pgvector extension before running the IronClaw onboarding wizard — the wizard fails at the database step if PostgreSQL isn't reachable. After installing PostgreSQL, connect to your target database and run CREATE EXTENSION vector; to enable the extension. Source: IronClaw GitHub
How do I install and authorize a skill in IronClaw?
IronClaw uses an explicit allowlist model: first install the skill with ironclaw skill install <name>, then authorize it with ironclaw allowlist add <name>. Skills that aren't on the allowlist are blocked from executing even if installed — this is by design, not a bug. The daily-brief skill is the recommended first test because it requires no network access and validates the full install-authorize-run cycle cleanly. See the full skill allowlisting guide for details. Source: IronClaw setup guide
How much longer does IronClaw setup take compared to OpenClaw?
Expect 15–20 minutes for a fresh IronClaw install versus under 10 for OpenClaw. The extra time goes to the onboarding wizard's security steps: sandbox scope configuration, audit log destination, and entering your first allowlist entry. This is intentional — IronClaw requires explicit opt-in for every capability rather than using permissive defaults. Once the initial configuration is done, day-to-day agent use is comparable in speed to OpenClaw. Source: IronClaw beginner guide
← Back to IronClaw hub · See also: Quick Start · Skill Allowlisting · Security