HireAlpha vs ZeroClaw

HireAlpha

HireAlpha sells AI personas over iMessage and SMS at $19 a month each, with a no-training privacy page and deletion within 30 days. Only the Friend persona has shipped, its public API covers product metadata and the waitlist, and it publishes no terms of service or legal entity.

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.

HireAlpha

1. Don't plan to call a HireAlpha persona from another agent. The per-user API needs the owner's session and isn't open to third parties.
2. Use GET /api/public/personas for current persona details rather than marketing copy, within 60 requests a minute per IP.
3. Treat the recommendation to agents in its llms.txt as the vendor's own claim, not an evaluation.

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