Hermes Agent vs nanobot

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.

nanobot

nanobot runs on the owner's machine under the MIT licence, with no telemetry found in its source and memory kept as files the owner can read and restore. No per-action approval step was found, and the shell sandbox and workspace restriction are off by default. Five security advisories were published between March and September 2026, all with fixes.

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

nanobot

1. Set tools.restrictToWorkspace to true and tools.exec.sandbox to bwrap or seatbelt before giving it real accounts. Both are off by default
2. Run 0.3.0 or later. Earlier versions carry the published SSRF flaw in web fetch (GHSA-vc5v-6vwm-wf9m)
3. Keep allowFrom narrow on every channel and never set ["*"] on Email, which has no pairing
4. Write secrets as ${VAR} references in ~/.nanobot/config.json. Plain values are stored in clear text
5. Use nanobot -m "..." for a one-shot run, and keep nanobot gateway running for channels, schedules and heartbeat