OpenClaw Foundation · 2 sourced playbooks

OpenClaw use cases

OpenClaw is an open-source, MIT-licensed assistant that runs on your own hardware. A single Gateway process links chat apps such as WhatsApp, Telegram, Slack, Discord and iMessage to the model you choose. The OpenClaw Foundation, a US non-profit, stewards it, and people use it for inbox, calendar and other personal chores.

Good at

• Talking to one assistant from the chat apps you already use
• Keeping state, memory and credentials on your own machine
• Adding repeatable procedures as skills, shared through ClawHub
• Using hosted or local models, with no paid tier of its own

Limits

• Tools run on the host for the main session unless you set up sandboxing
• Inbound chat messages are untrusted input, so prompt injection is a real risk
• One Gateway is one trust boundary, so it does not isolate users who do not trust each other
• Third-party skills and plugins are untrusted code and need review

2 playbooks for OpenClaw

Life admin and homeCorroborated

Get a short morning digest of your personal inbox with read-only access

Each morning you read one short digest with links to the emails that need you, and nothing in your inbox has changed.

Claude Cowork, Claude +2

Sales, marketing and supportCorroborated

Watch competitors' pricing and product pages and get a weekly briefing of real changes

Every week you get a short briefing of meaningful changes to competitors' pricing and product pages, each with the before text, the after text and a link to the saved snapshot.

Claude Code, Claude Cowork +3

Lessons for OpenClaw

Agents act before you approve, even when you told them to ask first
Remove the power instead of asking the agent not to use it. Give inbox agents draft and label access with no send or delete tool, connect trackers through a read-only endpoint for the preview step, and in workflow tools leave out send and delete nodes. Keep vendor approval prompts switched on. Test on a small copy or a single label first, and remember that a clean small test does not prove the agent behaves at full scale. Know how to stop the agent at once, for example by revoking its token or closing the app on the machine it runs on.