folk vs ZeroClaw

folk

folk is a texting accountability assistant with its own cloud computer, a free tier with no card and a privacy policy that rules out training on user data. No outside agent can call it, no status page or changelog was found, and its llms.txt and pricing file disagree on free limits and Max's price.

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.

folk

1. Don't plan to call folk from another agent. It answers only the owner's iMessage, Telegram or WhatsApp thread and iPhone app.
2. Quote limits and prices from pricing.md and the terms, and note that llms.txt gives different free-tier limits.

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