Hermes Agent vs OpenClaw

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.

OpenClaw

Self-hosted under the MIT licence, with state, memory and credentials kept on the owner's machine and no paid tier. A fresh install runs tools on the host with full access, no approval prompt and no sandbox, and the project has published 722 security advisories since January 2026, 14 of them critical.

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

OpenClaw

1. Set a session permission mode of guarded or workspace, or tools.exec.mode, before connecting mail. The default runs host commands without approval
2. Turn on agents.defaults.sandbox for any agent that reads mail, web pages or attachments. Sandboxing is off by default
3. Set tools.message.crossContext.allowAcrossProviders and allowWithinProvider to false to confine sends to the current conversation
4. Route incoming mail to a restricted reader agent, as the IMAP and Gmail guides show, and deny gateway, cron, sessions_spawn and sessions_send for it
5. Run openclaw security audit after setup, and treat the Gateway token as an owner credential. POST /tools/invoke accepts it with full operator access