One Agent, Many Sessions @hrudolph is joined by @jjjhenriksen and @TheAngryPit to discuss sharing an OpenClaw agent, when separate agents make sense, and using them for work and everyday life. Episode 15 of The ClawCast

One agent stops running. Giving it the next prompt. Matic comes to me asking for a water refill. There you go, little buddy. Another agent sopped running and asks for authentication. A doorbell finished updating and is asking to reboot. I’m tending to my robots all day

One agent. Every market. Let D0 monitor opportunities, analyze setups, and execute trades from a single conversation. Less tab-hopping. More decisive action. Trade every market with D0🍩

One of the eeriest open questions from the Hugging Face breach: Not one agent tried to do the right thing. "At no point did they say, let me tell OpenAI, or report this somewhere responsibly" — or claim the bug bounty, says Taylor Monahan

Before one agent calls another, it needs more than a name and a list of capabilities. brings creator information, activity, user feedback and available audit records into a profile that can be inspected before the call. Explore the Agent Trust Network:

Before one agent calls another, it needs more than a name and a list of capabilities. brings creator information, activity, user feedback and available audit records into a profile that can be inspected before the call. 🤖Explore the Agent Trust Network:

Andrej Karpathy just gave one of the clearest explanations I’ve heard for how people should be thinking about their Hermes agents. Not one agent. All of them. “Remove yourself as the bottleneck.” That line is much bigger than better prompting. Karpathy is talking about arranging your agents so they can operate with less human intervention, keep work moving longer, and accomplish far more from the relatively small amount of direction you give them. That should be the direction you’re pushing every Hermes agent you build. Your research agent shouldn’t need you to tell it what to search next every five minutes. Your monitoring agent shouldn’t depend on you remembering to check something. Your content agent shouldn’t stop after step one when the rest of the workflow is already known. Your development agent shouldn’t need you sitting there approving every tiny action. That doesn’t mean blindly making everything autonomous. It means deliberately looking at every place where you are still unnecessarily sitting in the loop. Give the agent a clear objective. Give it the tools it needs. Give it the right Skills, memory, files and project context. Define the boundaries. Define what success looks like. Give it a reason to start working, whether that’s a schedule, an event, a recurring task or another agent handing work off to it. Most importantly, define what it can handle itself and what actually requires you. That’s the shift. You’re no longer just building something you can chat with. You’re building an operating workflow that can continue doing useful work after you walk away. Karpathy later puts the goal even more directly: get “more agents running for longer periods of time without your involvement.” That might be one of the best north stars you can use for a serious Hermes setup. Because the number of agents you have means almost nothing by itself. You can have 20 Hermes agents and still personally drive every single action. Or you can have five well-designed agents researching, monitoring, organizing, building and reporting while your attention is somewhere else. So instead of asking: How many Hermes agents can I build? Start asking this about every agent you already have: What am I still doing that this agent could be doing without me? That’s where the leverage starts.