OpenClaw vs Hermes Agent (Don’t choose WRONG!)

Hey, I'm Matt and you're trying to figure out whether to pick Open Claw or Hermes Agent. And most videos comparing the two will tell you to use both. This is not that video. I've shipped full setup tutorials for each of them. Real installs, real configs, and real money I spent on tokens. So, I'm not guessing at the differences here. I've built them. Here's the plan. We'll get clear on what each one actually is, where each one wins, what they cost, the honest security story, and at the end you'll get a clear, if you're this kind of person, pick this one, recommendation. No coding, no terminal, just a decision. Starting with the thing that, if you take nothing else away, will save you weeks of setup on the wrong tool. Both are open-source AI agents you run on a server. You chat with them on Telegram, Slack, Discord, whatever you already use. They read files, run scripts, browse the web, send emails, schedule jobs. They're the same ingredients, and that's why every comparison video makes them sound identical. But, they're not. The difference is what each project spent its design effort on. Open Claw was built around the catalog. Anything you'd want your agent to do, somebody else has probably already built a skill for it. Over 50,000 of them as of June 2026. You browse, you install, and then your agent does the thing. Hermes was built around the learning loop. When the agent solves a new problem, it writes down how it did it and never has to figure it out again. It builds its own skill library based on how you actually use it. That feature, called the curator, landed in Hermes version .12 in April 2026 and has been the project's headline ever since. Open Claw shipped its own version called Skill Workshop in June 2026, but with one key difference. Hermes does it automatically by default. Open Claw asks you to approve each new skill first. More on that in a minute. So, if you boil it down, Open Claw bets on the community catalog. Hermes bets on the agent improving itself. Now, that's the spine of every other decision in this video. Open Claw wins on three things. One, the catalog. There's over 50,000 skills and plugins on ClawHub. Google Workspace, web scraping, image generation, accounting, you name it. Somebody packaged it up and you get to install it with one click from the dashboard. Hermes has a much smaller library and it grows from your own usage. Great long-term, but day one, Hermes is a thinner toolbox. One gotcha I'll come back to, that catalog has a security story you need to know about. Two, provider variety. Open Claw supports more than 50 AI providers natively. Anthropic, OpenAI, Gemini, Grok, Deep Seek, plus local models to Ollama and dozens more. Hermes setup wizard gives you a short list. Open router, Anthropic, OpenAI, Nous portal, Ollama, and the rest you reach through Open router. Three, the dashboard. Open Claw ships with a polished web dashboard out of the box. Hermes is CLI first. There's an optional dashboard you can install as an extra, but it doesn't ship with the default install. For a beginner, Open Claw feels like a tool you can browse. Hermes feels like a tool you can talk to. So, that's the Open Claw camp. There's a bigger catalog, more native providers, and a friendlier UI. Now, Hermes. Hermes wins on three things, too. One, the automatic learning loop. Hermes curator runs continuously writing skills from your agent's work, monitoring which ones get used, refactoring underperformers, all without you approving anything. Open Claw shipped Skill Workshop in June 2026 to do the same thing, but it's the safer, slower flavor. Open Claw's agent proposes new skills and waits for you to review and approve each one. Even the proposal automatically setting is off by default. So, Hermes ships you a self-improving agent. Open Claw ships you a self-proposing one that you supervise. Two, token cost on repeat tasks. Both run the same models, both use the same prompt cash discounts, so per turn cost is mostly the same. What's different is repeat tasks. Hermes solves a problem once, saves a skill, then runs that skill cheaply on every repeat automatically. Open Claw can do the same, but you're either approving skills as they come in or running without the compounding savings. So, Hermes' bill on the repeated work flattens earlier with less effort. Three, day-one ergonomics. The Hermes defaults are tight. Pick a provider, paste the key, send the message, and you're talking to an agent in minutes. Open Claw is more configurable, which means more places you can get stuck on day one. So, that's the Hermes camp. Automatic self-improvement, cheaper repeat tasks, less day-one friction. Honestly, neither is hard to install. Both have one-click hosting your templates where you sign up for a VPS, pick the Open Claw or Hermes template, wait a couple of minutes, and you're chatting with your agent. KVM 2 is the right floor either way. There's no terminal, no Docker, and no server config. If you go that route, the two links in the description below give you an extra 10% discount off the VPS. There's one link for each template. The full step-by-step guide is in my tutorials for each one, both linked in the description as well. You can also self-host either project on your own hardware, a Mac mini, a Raspberry Pi, a spare laptop, or really anything that runs Linux or macOS. Just know that that path is meaningfully more technical, and running an AI agent on your daily machine has real security considerations, which we'll get to in a minute. There are two types of costs, your server and your AI model. The server is the same. It's whatever physical or virtual machine you use to run the agent. The model is whatever you pick. Both products run the same models, and both support prompt caching at around 90% of cached tokens. So, per-turn cost is mostly the same. The real cost difference is repeated tasks. Hermes Curator saves a skill from work it's already done and runs that skill cheaply on every repeat, automatically. Open Claw Skill Workshop can do the same thing, but every skill waits for your approval. So, Hermes' bill on repeated work flattens earlier with less effort from you. If your work is varied and one-off, the two end up pretty similar. Either agent can be run comfortably under $20 a month after the initial configuration if you pick the cheapest model that does the job. Both agents read your files, send messages on your behalf, and touch your accounts. So, security matters. Where you run it changes the risk. On your laptop, the agent has access to your files and your local network. The cleanest mitigation is to run it on a virtual private server. If something goes wrong, you nuke the virtual machine, not your daily machine. Both products also support sandboxes for local installs. Hermes has five backends. Open Claw runs non-main sessions in Docker by default. Hostinger's templates also ship traffic for automatic HTTPS, which lifts the floor on default security. Now, the part that's actually different, the CVE story. The volumes, they're not even close. Open Claw had a rough run in early 2026. Over 130 security advisories filed between February and early April. That's the standard label for a publicly reported security vulnerability. The biggest was a high-severity remote code execution flaw where a malicious link could give an attacker access to your gateway. Over 40,000 Open Claw instances were exposed at the time. This was patched fast, but the ecosystem took a real hit. A separate audit of Claw Hub also found over 1,000 skills flagged as malicious. So, if you go Open Claw, only install skills from publishers you trust and keep your version up to date. Hermes has had a smaller number, at least a dozen CVEs across 2026, plus an April audit that flagged four critical and nine high-severity findings in the default config, all patched in the versions that followed. The rate's slower partly because there's no third-party skill marketplace running through Hermes the way Claw Hub runs through Open Claw. The takeaway is both can be run safely if you keep them updated. Open Claw has the bigger ecosystem and the bigger attack surface. Hermes has the smaller of both. Here's the recommendation framework. There are three viewer profiles and three different answers. If you're setting this up for the first time, you just want one personal assistant on Telegram or Discord, you don't want to spend your weekend tuning files, and the appeal is an agent that just gets better at my work over months, pick Hermes. The curator pays off the longer you use it, and the defaults are tight. This is the right answer for many people watching. If you want a clickable dashboard, a massive marketplace of pre-built skills, or fine-grain control over which providers and config you use, pick Open Claw. The catalog and the dashboard are the strongest in the category. Just keep your version up-to-date and only install skills from publishers you trust. If you mostly do the same kinds of tasks every day, and you want repeated work to get cheaper over time, like daily briefings, the same research, the same email triage, use Hermes. The curator cashes your repeated work automatically. Open Claw can do similar through Skill Workshop, but every new skill needs your approval. It's safer, but slower to actually realize the savings. So, that's the honest answer. Hermes if you just want it to work and get better as you use it, Open Claw if you want catalog, providers, and a friendlier UI. Now, a word on those deals. If you want one-click server setup for either agent, the Open Claw and Hermes links in the description each give you an extra 10% discount for your VPS. Whichever agent you pick, my full step-by-step setup tutorial is linked in the description below. Thanks for watching.