Hermes Agent vs Zo Computer

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.

Zo Computer

Zo publishes an OpenAPI file, Markdown docs, plan prices and a named list of the providers that receive user content. One access token grants full access to the workspace, no approval step before sending or buying was found in the reviewed docs, and no status page, rate limit or SLA is published.

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

Zo Computer

1. Send POST https://api.zo.computer/zo/ask with Authorization: Bearer zo_sk_... and an input string. The owner creates the token under Settings > Advanced
2. Pass persona_id for a persona with a narrow tool set. The token itself carries every permission the owner has
3. Set memory_mode to off to keep workspace memory out of a request. The field is in the OpenAPI file and absent from the API guide
4. Do not retry /zo/ask blindly after a timeout. No idempotency key is documented and the request may already have sent a message
5. Append .md to any guide or reference URL for Markdown