ClawChart is a free browser-based tool that visualizes your OpenClaw agent configuration (openclaw.json) as an interactive node graph. It shows how your channels, agents, skills, models, and tools connect — and lets you browse 5,700+ skills and run security audits, all without sending your config to any server.

Is my openclaw.json config safe to paste into ClawChart?

Yes. ClawChart processes your configuration entirely in your browser using client-side JavaScript. Your openclaw.json is never transmitted to any server. Shareable links use URL hash fragments, which browsers never send to servers.

What is an OpenClaw skill?

OpenClaw skills are modular capabilities you can add to your AI agents — for example, gmail, browser, github, or voice-call. They are installed via the clawhub CLI and extend what your agents can do. ClawChart's skills directory lists 5,700+ available skills with security grades and install counts.

How do I install an OpenClaw skill?

Run 'clawhub install ' in your terminal. For a specific agent workspace, use 'clawhub install --workdir ~/.openclaw/workspace- '. ClawChart generates the exact install command for you when you click 'Add to agent' in the Skills Explorer.

What does the ClawChart security audit check?

The security audit checks for: sandbox disabled with exec tool allowed (critical), open DM policies (medium), missing fallback models (medium), skills from the known-vulnerable list (critical), non-ClawHub skill sources (low), and more. Each issue is severity-scored and includes a recommended fix.

Yes. Graph visualization, security audits, skills browsing, and shareable links are all free. Downloading your edited config as a JSON file has a small one-time cost per download — no subscription or account required.

ClawChart

Visualize your OpenClaw agent configuration as an interactive graph

Start from a template

Or paste your config

⌘+Enter to visualize