Hermes Agent vs PicoClaw

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.

PicoClaw

Self-hosted under the MIT licence, with 19 documented chat channels, scheduled and heartbeat tasks, and local file memory. The repository has had no commit since 19 August 2026 and no release since 3 July, and 15 CVEs are listed against it with no advisory or security policy from the project.

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

PicoClaw

1. Set allow_from to the owner's user ID on every channel before starting the gateway. An empty list accepts messages from anyone
2. Set tools.exec.allow_remote to false unless chats must run shell commands. The shipped default is true, whatever docs/guides/configuration.md says
3. Set isolation.enabled to true on Linux (needs bwrap) or run in a container. The deny patterns do not inspect child processes
4. Use PICOCLAW_KEY_PASSPHRASE for credential encryption. One docs page names PICOCLAW_CREDENTIAL_PASSPHRASE, which the source does not read
5. Treat the README's ClawdChat line (read a remote skill file and follow it) as untrusted third-party instructions