Personal Productivity

How Da7em Uses Hermes Agent Daily for Research and Video Editing

Built by Da7em · · Source: X

Quick answer

Da7em runs Hermes Agent as a daily personal agent that keeps their memory, skills and instructions across models. They say it edits their published test videos, proofreads academic research, translates books and audited their ERP app.

Result: Da7em says Hermes has become essential and edits all their published test videos without them touching the work. In a session they call average, out of 1,013, they report 94.4% of about 4 billion tokens came from cache.

What they built

Da7em says they have used Hermes Agent every day since it launched, and this post is their independent review. It describes a personal setup more than a single project: one agent that carries their memory, skills and instructions across sessions and across whichever model they plug in. According to Da7em, it handles personal tasks, light work and organization, edits every test video and model comparison they publish, proofreads academic research, translates books and documents, and ran a security audit on their ERP application.

How it works

The post is a review, so it does not give step by step setup details. Here is what it does explain:

  • Models: They mostly use GLM 5.3 for light and medium tasks and sometimes switch to GPT Sol 6.1. They say the model choice makes little difference in ninety percent of cases, because the memory, skills and instructions sit in a layer above the model.
  • Memory: They explained their research method and preferences once and say the agent has kept to them across sessions and updates. They also had Fable pass its style and way of thinking on to Hermes, and say that made it twice as useful.
  • Where they talk to it: The desktop app is their main workspace. Away from home they message it, and they send voice notes on Telegram that are transcribed by their own speech-to-text model running locally.
  • Cost and hardware: They say there is no Hermes quota. You bring your own key, run a local model, or subscribe through Nous Portal. They once ran a full agent in a virtual machine with 2 GB of RAM and say it was stable.

Da7em also lists problems. Steering messages are often ignored until a task finishes. Computer use breaks under heavy work or with weaker models. The worst one, they say, is that a weak model can damage the memory and setup. MiniMax M3 broke their Hermes more than once, so they now stick to stable models and want an approval step for edits to the memory, the soul file and AGENTS.md.

The result

Da7em says Hermes has become essential to them and that they do not touch the videos it edits. For a session they call average, out of 1,013, they report 219 million input tokens, 15.7 million output tokens and 3.77 billion cached tokens, with 94.4% coming from cache.

How to build something similar

  • Pick an agent that stores memory and instructions in files you control, then write down once how you work and what you do not want.
  • Start with one recurring job, such as proofreading, and correct the agent until the saved instructions produce what you expect.
  • Connect a chat channel like Telegram so you can send tasks from your phone.
  • Keep the memory and instruction files backed up or under version control before you try a new or weaker model.

The original post

I have been using Hermes Agent every day since day one, and I think it is finally time for a full review. As always, this is completely independent. Not paid, not sponsored. The good and the bad, nothing held back. This review covers what I use Hermes Agent for, why you should consider it, and how it stacks up against OpenClaw, Claude Code, Codex, and Grok Bot. Hermes has become essential for me. Let me show you why, starting with the first thing most of you asked. Which models do I use inside Hermes? The best thing about Hermes is that it is truly model-neutral. It does not degrade the models. Whatever a model can do, you get directly. I use GLM 5.3 a lot, and for light and medium tasks it is excellent. Sometimes I switch to GPT Sol 6.1, and I have noticed that the best place to run GPT is Hermes, even better than Codex. I have tried a lot of models in Hermes, and they were all excellent. So use any model that suits you, as long as the plan is generous, and run two or three at once if you want. Here is the important part: in ninety percent of use cases, your choice of model will not make a big difference. The model here is still just a brain behind bigger layers, and those layers are what control how it behaves. Usage limits and cost There is no Hermes quota. Plug in your key, run a local model, or subscribe through Nous Portal. That is all it takes. You can push Hermes to the max with excellent models without paying a single dollar. And if you decide to pay, you get great value for it. Caching is great too Out of 1,013 sessions, here's one that came out right at the average: 219 million input tokens 15.7 million output tokens 3.77 billion cached tokens About 4 billion tokens in total 94.4% from cache. Hermes is one of the best I have used for token efficiency, and the transparency is total. While you work, you see the real speed of every provider and every detail. Light on the machine Hermes is not heavy at all. One day I set up a full Hermes agent inside a virtual machine with just 2 GB of RAM, and it ran with very high stability on every kind of task I gave it. That shocked me. Codex, for comparison, eats tens of gigabytes of RAM. That difference tells you what an engineering masterpiece Hermes Agent is. The layer above the model One of the biggest things that sets Hermes apart is that the agent is separate from its brain. The model is the brain, and you can swap it without losing your memory, your skills or your setup. Anywhere else, when I use GLM 5.3 I get GLM's usual strengths and weaknesses, and when I use Sol 6.1 I get Sol's. In Hermes there is a layer above the model that gives it a soul, a style and an understanding of how I work, so switching models matters far less. At some point the models feel eighty percent alike in style, in method and in the things you care about. What is left is raw capability, so the most capable models go to the hardest problems. You own the layer you actually invest your time in. And the beautiful part is that this layer, the identity, the memory, the skills and every tool, is completely mine. Look at Claude Code getting people banned today, at model performance suddenly dropping, at Codex being stingy with usage one time and slow the next. Those are constraints, and Hermes does not have them. If Claude Code decides to change or remove something, you have no say. In Hermes you can always change whatever you want. That is sovereignty, freedom and empowerment. Memory that grows with you When I opened the skills and memory tree, I found that Hermes had reached the point where it knows me better than any other agent. It grew with me through this whole journey, and that is what makes it the ideal partner for my work. The journey command shows you a star map of your memory and skills, and you can edit or delete anything in it. It is one of the greatest things in Hermes. One example: when Fable came out I loved it, so I had Fable pass its style and way of thinking on t
Da7em (@Da7_Tech) · November 8, 2026 · View on X

Want to build something like this?

Join the Shipping Skool community free. Paid members get live bootcamp calls every week.

Join Shipping Skool — Free

More use cases

← All AI agent use cases