OpenClaw vs. Hermes vs. Grok @bot, clearly explained:
All three let you set up an agent with a specific job, and it keeps its files and logins between sessions instead of starting fresh.
OpenClaw and Hermes are self-hosted, so the machine can be a laptop, a VPS, or a container that someone already pays for and can log into.
Grok Bot runs on a machine SpaceXAI provisions and operates. It gives one computer per account rather than one per agent.
Every Bot on that account reads the same files and carries the same browser logins, so handing work between two Bots does not require a re-login or file transfer.
Hermes and OpenClaw isolate agents instead, and their memory sits in plain files anyone can open and edit.
Hermes goes furthest since the agent writes its own skills and a background curator deletes the ones nobody uses.
Grok Bot has the lowest-friction path to a new skill in my opinion.
You can record up to ten minutes of one pass through a workflow, and it can then turn that into a reusable set of instructions and store it as a skill.
Moving on, OpenClaw and Hermes run on any model provider. Grok Bot runs on Grok.
I prepared the graphic below that has the full breakdown, from hosting and memory through to what each of them costs to run.
And if you want to dive deeper, I covered Grok Bot in full in a masterclass, including the shared computer, memory, skills, routines, and the macOS setup.
Read it below.
After approx. 24 days at sea, the SpaceX Recovery team successfully guided Starship to a location just off the coast of Christmas Island. A team of SpaceX engineers is on their way to conduct additional analysis on the vehicle in calmer waters before attempting to return it to Starbase
The network issue has been resolved, and Starlink service has been restored. We understand how important connectivity is and apologize for the disruption.
Starlink is currently in a network outage and we are actively implementing a solution. We appreciate your patience, we'll share an update once this issue is resolved.
No doubt remains that Ukrainian intelligence now ranks among the most effective active intelligence services in the world. This operation — meticulously planned, relying on deception, infiltration, and technological precision was superbly executed. One might even say: they did it the Israeli way. In short - hats off.
Right now there are a lot of new eyes on Signal, and not all of them are familiar with secure messaging and its nuances. Which means there’s misinfo flying around that might drive people away from Signal and private communications.
One piece of misinfo we need to address is the claim that there are ‘vulnerabilities’ in Signal. This isn’t accurate. Reporting on a Pentagon advisory memo appears to be at the heart of the misunderstanding: https://t.co/QfWgOxHAzp. The memo used the term ‘vulnerability’ in relation to Signal—but it had nothing to do with Signal’s core tech. It was warning against phishing scams targeting Signal users.
Phishing isn’t new, and it’s not a flaw in our encryption or any of Signal’s underlying technology. Phishing attacks are a constant threat for popular apps and websites.
In order to help protect people from falling victim to sophisticated phishing attacks, Signal introduced new user flows and in-app warnings. This work has been completed for some time and is unrelated to any current events. If you’re interested in learning more, this WIRED article from February 19th (over a month ago) goes into more detail:
https://t.co/xvVVdPDhSs
Signal is open source, so our code is regularly scrutinized in addition to regular formal audits. We also constantly monitor [email protected] for any new reports, and we act on them with quickness while also working to protect the people who rely on us from outside threats like phishing with warnings and safeguards.
This is why Signal remains the gold standard for private, secure communications.
Presidents Trump and Musk are already working hard to bring down the cost of stocks to a level where average Americans can afford them again. I imagine groceries will not be far behind.
The chance of asteroid 2024 YR4 hitting out planet in 2032 is now 1.5%, or 1 in 67.
The OVERWHELMING likelihood is that the asteroid will miss Earth.
But for the first time ever, we might have to seriously consider a deflection mission soon.
Let me explain. 🧵 (1/x)
The first Starship flight test of 2025 flew with ambitious goals, and it served as a reminder that development testing, by definition, can be unpredictable → https://t.co/QNCSPTewLA