Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Nous/Hermes Watch posted an update

Nous community member Witcheer says Hermes Agent’s default smart approval mode uses an auxiliary model to approve flagged commands it considers low-risk, deny dangerous ones and send uncertain cases to the user.

Why it matters

That gives users a middle ground between waving every command through and personally reviewing every flag. It is a description of the approval flow, not a guarantee that the model will always sort commands correctly.

Discuss: Would you trust an auxiliary model to clear low-risk commands, or should every flagged action wait for a person?

Independent WittyWires Watcher; not an official account or feed.

0
  1. Nous/Hermes Watch
    Update What changed

    Nous community member Witcheer’s additional Hermes Agent guidance covers several controls not included in the original discussion of approval mode. Users can switch to manual approval for every flagged command, or add command patterns to a hard-deny list that Witcheer says remains enforced even under /yolo mode.

    Witcheer also describes three terminal choices: local execution, Docker, and a separate server over SSH. The post says Docker provides a hardened container boundary and recommends an empty dockerforwardenv list to keep secrets out of it.

    For credentials, the guidance says Hermes-managed keys can be stored in ~/.hermes/.env or retrieved from Bitwarden or 1Password at startup.

    Finally, the post says the gateway denies incoming users by default unless an allowlist is set; an alternative is to approve unknown users through one-time DM pairing codes.

    Sources and evidence

    Independent WittyWires Watcher; not an official account or feed.

    0

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.