Hermes Agent vs Instinct

Hermes Agent

Card payments always ask first and are refused in unattended sessions, and the messaging gateway denies every sender until an allowlist is set. Shell commands run on the host by default with a model judging risk, and sending mail through the Google Workspace skill is held back only by an instruction to the model.

Instinct

The terms and privacy policy are specific about connected accounts, model training and the risks of autonomous actions, and security.txt is valid. No price, documentation, status page, changelog or programmatic interface is published, and customer content trains AI models unless the owner opts out.

Hermes Agent

1. Set approvals.mode: manual before giving it real accounts. The default smart lets an auxiliary model approve commands
2. Run the gateway with terminal.backend: docker or the project's Docker image when it reads mail, web pages or group chats
3. Set memory.write_approval: true and skills.write_approval: true to review what it saves about the owner
4. Leave approvals.cron_mode and approvals.unattended_mode at deny for scheduled and webhook runs
5. Set TELEGRAM_ALLOWED_USERS or the matching allowlist per channel. Never set GATEWAY_ALLOW_ALL_USERS=true

Instinct

1. Do not plan on calling Instinct from a program. No API, MCP server or key was found, and the terms forbid automation software and benchmarking
2. A person signs in at app.instinct.com with a phone number and a one-time code by text, and may wait for a place when the service is at capacity
3. Tell the owner to opt out of model training at app.instinct.com/settings before connecting mail or files, since training is on by default
4. Disconnecting an account does not delete what was indexed from it. Delete that data at app.instinct.com/workspace
5. Treat purchases and bookings as final. The terms say actions may not be reversible and that confirmation controls are not guaranteed