Poke vs ZeroClaw

Poke

Hosted assistant that answers in Apple Messages, WhatsApp, Telegram and RCS and acts in Gmail, Outlook, calendars and MCP servers. Plan prices and a status page are public. No approval settings, credential storage, model providers or retention periods are documented, and customer content trains models unless Maximum Privacy is selected.

ZeroClaw

Supervised autonomy is the default, so tools outside a short read-only list wait for the owner's approval, and secrets are encrypted in the config file. The docs state that command execution is not written to an audit log, and the project publishes no privacy policy or terms.

Poke

1. POST JSON to https://poke.com/api/v1/inbound/api-message with a Bearer key from Kitchen. Legacy pk_ keys work only on the deprecated /api/v1/inbound-sms/webhook
2. Expect only {"success": true} back. Poke's answer goes to the owner's message thread, not to the caller
3. Do not retry a POST blindly. No idempotency key is documented, and a repeated message may make Poke act twice
4. Treat an API key as full access to the owner's mail, calendar and integrations. Create one key per automation and revoke it when done
5. Avoid the prefilled integration link with apiKey in the query string for real secrets. Enter the key in the form or use npx poke@latest mcp add -k

ZeroClaw

1. Keep [risk_profiles.<alias>] level = "supervised". full runs every tool not listed in always_ask, and the YOLO preset removes the sandbox and path rules too
2. Add sending and account tools such as send_via, google_workspace and http_request to always_ask so a session-level Always grant cannot skip the prompt
3. List senders in [peer_groups.<name>] external_peers. ["*"] accepts anyone on that channel
4. Set [web_fetch].allowed_domains and [http_request].allowed_domains. Fetches run unprompted and the OS sandbox does not block egress
5. Run one-shot tasks with zeroclaw agent -a <alias> -m "<task>". A cron or webhook turn has no prompt, so shell calls fall to the command policy