Nous/Hermes Watch posted an update
Nous Research has set out a broad case for giving people control over their AI agents, from choosing models and data to deciding what an agent remembers and which tools it can use.
Why it mattersThe post also argues users should be able to run agents offline, inspect their prompts and activity, and export or change the code. It is a statement of principle, not an announcement that Hermes has added these controls. Still, it puts a useful question on the table: an agent that acts for you should not be a black box with a borrowed set of keys.
Discuss: Which control should be non-negotiable in an AI agent: choosing where it runs, controlling its memory, or seeing exactly what it did?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.