Pablo

AI Systems Architect | Founder, Vektra Industries |
Building the harness humans will need over the next 50 years.

|

[Pablo @pablothethinker]

I've been working on this concept inspired by Anthropic's new research on J-Space but made for @NousResearch's Hermes Agent by @Teknium.

I am calling it Hermespace.

It's still in development and the concept is new. I want to make it more in-depth on what this space can truly do for Hermes Agents and how it helps in everyday usage.

https://t.co/VyB6eS1xOT

[Pablo @pablothethinker]

@tonysimons_ I got some serious Cyberpunk 2077 vibes from your agent all the way.

[Pablo @pablothethinker]

I have been enjoying cognitive research for AI agents and developing new frameworks and interconnected systems to improve and optimize memory.

Especially by researching not just human brains and how we operate but also other species with great memory, such as elephants, dolphins, and whales.

All have great memory, and if applied correctly through research, a new system can be made. This is what I am working on right now with ILO (Hermes Agent).

It shall indeed be exciting to see how it evolves.

[Pablo @pablothethinker]

I just spoke for more than 10 minutes full use of the Hermes Desktop voice system and brain dump everything within me to my Hermes Agent.

An large and big brain dump for my agent in every way to learn about me and my mission, to understand me more and do what is needed.

Let's see what happens.

ILO my Hermes Agent just gave herself Mission Zero.

[Tommy @Shaughnessy119]

Renting vs Owning Your AI Intelligence

The American dream was owning a home. I think the future version is owning your AI brain. Something you build intelligence equity in instead of renting it and enriching the man

Over the next few decades everyone is going to accumulate a ton of intelligence around AI. Your memories, context, skills, workflows, integrations, databases, emails, corrections, operating knowledge and all the apps you build and everything in between including your psychology and your dreams. It will become one of the most valuable assets a person or a company owns

The scarce thing is no longer access to intelligence, it is the accumulated system around the model that makes intelligence yours.

The question becomes do you rent that intelligence or own it?

Path one is the default. You spend your life, personal or business, working inside ChatGPT or Claude. And to be fair, you can genuinely build really cool things this way. Memory, projects, custom GPTs, skills, connectors, automations and most people will probably go this route.

Everything you create runs inside their product. There is no runtime you can take with you, nothing you can fork, and no way to point what you built at a different provider's model. You inherit every product decision they make on pricing, features, memory behavior and what they allow you to do or not to do (censorship on security asks or medical or otherwise).

You can export your content, but content is not the system. An export is not a runnable copy of your memory, tools, automations and routing. When you leave, the system stays behind.

Path two is you own the entire layer around the model. A whole ecosystem of open source agents is emerging to make this possible. The strongest release in my view is @NousResearch's Hermes Agent. Most alternatives are developer frameworks you have to assemble yourself. Hermes is a complete agent you just run.

Here is what you own with it

- Host locally or on the cloud and you own everything
- Persistent memory, searchable session history, databases and every interaction from day one
- Editable personality, skills, workflows and scripts
- Subagents, tools and scheduled automations
- Model and provider choice and MCP connectors
- Portable profiles, histories and backups
- Switch models at will for cost, reasoning, or to avoid censorship and model restrictions
- MIT licensed runtime you can self host, fork and modify
- Every application, automated cron job or integration you have created in its entirety
- Transcend a single walled garden with access to any integration accessible via an API/MCP.
- Eventually you’ll click a button and fine tune an open source model based on all of your own accumulated data and you can use it to power your agent

ChatGPT and Claude have versions of half this list. Memory, skills, connectors, scheduled tasks. The difference is physical. Theirs are features inside their app, backed by their database, living on their servers. In Hermes every one of these is on a computer you control. Your memory is a database you can open. Your skills are text files you can read, edit and copy. Your automations are cron entries you can inspect. Your agent's personality is a config you can rewrite. Files can be backed up, moved, forked and pointed at any model on earth. Features can only be used. When you own you can tear down the walls and rebuild the kitchen.

For a person, this is the AI brain you build and control for life. It compounds everything you choose to preserve and moves with you across jobs, devices and providers. Swap models at will for cost or reasoning, or run several at once through Mixture of Agents.

You'll never log in one day to find your entire AI brain, everything you built around a model over decades, gone because of a ban, a deprecation or a policy change.

For a business, this is a core asset the company actually owns. Employee knowledge becomes company owned skills, workflows and automations that remain after people leave and grow enterprise wide while they are there. That system can be deployed across the org, licensed out, or transferred within the business. Sharing your Hermes build and skills to new employees and enterprise wide will be a whole new era of productivity.

Net, whatever you build with Hermes as a business you own entirely. You can license it out or sell the agent itself. The agent itself can become the product. You can't sell your ChatGPT or Claude session. You can obviously sell what you create with ChatGPT/Claude in chat but you can't sell the core AI architecture you've built around the model.

Here is the part I think people will only get in hindsight. Models are becoming cheaper, better and more interchangeable every year. GLM 5.2/Kimi are so good that the government is considering banning them because they are so cheap to use it threatens the U.S. funding capex cycle. The scarce thing is no longer access to intelligence, it is the accumulated system around the model that makes intelligence yours.

When you’re in virtual reality side by side with your agent exploring the virtual cosmos or its 2am and you’re discussing the next company idea, you’re going to want your AI to be the full encapsulation of everything you’ve built over the years. That juice, that style, that data accumulated around the model in your AI brain is where the crazy stuff will happen. Evolutionary jumps come from variation. A world where everyone runs the same three models is a monoculture of ideas. A hyper personalized architecture around the model (or unique fine tuned models themselves) is the variation, the EV+ differentiation that produces the outlier results, companies and agents.

We’ve already seen Harnesses greatly upskill models. Now imagine how much a personalized harness upskills your entire AI experience when you build it over time.

Here is an example with zenith harness taking base models to the top of FrontierSWE via adaptive self improvement https://t.co/58gbcs70Dw

Let’s Walk Down A Decade in Each Path

Ten years in ChatGPT or Claude and it will genuinely know you. Your projects, your preferences, your whole history. But let's look at what actually compounded. Their system got smarter about you, and their system is identical for every user on earth using one company's models, their prices, their rules, their memory format, their ceiling. You cannot rewire how it remembers, restructure how it works, or point your decade of accumulated context at a better or cheaper model. Every correction you gave them deepened their retention moat and, depending on your settings, may have trained their next model.

Ten years with Hermes agent and that same decade compounded into a system you hold and have been innovating on the whole time. You rewired its memory, stacked hundreds of skills it wrote from watching you work, wired in your own subagents, tools, databases, automations and integrations, tuned its personality and its routing until it fits nobody on earth but you. Depending on the scaffolding around a model (the agent harness) your experience with AI takes a huge leap forward, as much as a full model generation upgrade. And that is from generic harnesses built for everyone. Now imagine the harness effect at the level of each person. This is an architecture engineered around your brain, your workflows and your taste for ten straight years. The model underneath is just a component. GLM today, Kimi tomorrow, local when it matters, eventually a model fine tuned on your own decade of data. With Hermes agent you are building the entire scaffolding and architecture around a model that grows and compounds over decades which provides a truly unique experience.

I strongly believe people will want to own their AI brain long term (and everything built around it) and Hermes agents will create, and in themselves become, massive companies and projects in their own right. The journey will start with manually building your agent, then granting it some automation, then fully graduating it to autonomy.

Even Sam Altman from OpenAI agrees with the need for Open Source harnesses: https://t.co/4UL4rOeErn

You don't have to be a master AI builder with some grand plan, you just have to decide you want to own your AI brain you'll spend decades building. All the cool stuff will come later

Start your multi decade journey and own your AI brain for life: https://t.co/CUQAcvhJmu

Ty to Kevin Simback for thoughts and comments

[Pablo @pablothethinker]

I am back!

Time to get to work!

[Pablo @pablothethinker]

@julientalbot974 @XMoney I don't know I just got it when I opened X.

I was truly surprised and still am.

[Pablo @pablothethinker]

I just also got access to @XMoney!! What?!?

What a day!

My first client for an AI Agent and now this?

I can't stop, I need to keep pushing beyond my limits.

I won't stop till I win.

[Pablo @pablothethinker]

@tonysimons_ That's why my clients I am setting up are only going to use Hermes Agent.

I can't look back to Openclaw after experiencing Hermes.

[Pablo @pablothethinker]

@MosiMoradian I do have an Acer gaming PC as my server so this shall definitely be up my alley

[Pablo @pablothethinker]

Good morning everyone, new updates have been pushed to HermesCube (experimental), which shall be part of the Hermespace framework.

This is what is in the system.

Any actual testing and usage will truly be appreciate it from your experience with it and how it works to improve.

[Pablo @pablothethinker]

Opencode Go + DeepSeek v4 Pro =

[Pablo @pablothethinker]

@mathelirium Very interesting indeed and useful.

[Pablo @pablothethinker]

@Teknium 💙

[Pablo @pablothethinker]

The new Hermes Update represents the future of open source even more.

It reminds me that this is the path.

The ability to create such a beautiful harness that gives any AI model its own Iron Man suit allows them to be more than they are now.

This leads us to the Age of Quicksilver, a next-level update and optimization of what Hermes shall truly be.

What is shown here demonstrates great craftsmanship from @NousResearch.

Outstanding work, and I look forward to the next update.

[Nous Research @NousResearch]

Hermes Agent v0.19.0: The Quicksilver Release

Changelog below

[Pablo @pablothethinker]

@nicomaru0929 That's the best thing right here: all of this connection and learning from everyone around the world.

Truly a pleasure to meet you, Anri, and may your day be outstanding.

[Pablo @pablothethinker]

And X gave me a welcome gift as well?

Honestly, I followed @sudoingX's article on why to get Premium+ on X, and it's worth it.

I have always seen the potential but was too scared to share my journey, which is everything I've been doing lately.

I understand why going all the way on this platform is worth it—it's not just about the money.

It's about the ability to grow more than ever, more than on any other platform, and the opportunity to build a career on X just by sharing your passion.

I'm truly glad to be part of this timeline.

[Pablo @pablothethinker]

I just also got access to @XMoney!! What?!?

What a day!

My first client for an AI Agent and now this?

I can't stop, I need to keep pushing beyond my limits.

I won't stop till I win.

[Pablo @pablothethinker]

The Second Layer of Hermespace:

[Pablo @pablothethinker]

Here's the second layer of Hermespace that I am currently working on.

The need for a new memory system emerged from the large context increase issues I ran into during Hermespace development (which I have already improved, but this second layer shall indeed improve it all).

It's an experimental memory system for Hermes Agents to improve memory and optimize the compression of such memories.

This is inspired by what a dodecahedron is and the concept of it in multiverse theory.

I was reminded of Animation vs. Geometry, where near the end a dodecahedron is made and Orange steps in to see infinite versions of himself, which then loops back to the beginning of the video, representing the infinite realities of events.

I wanted to do the same for the data and memories Hermes Agents constantly develop when working with their user.

If this is achieved—and I think I am close—this shall lead to solving the memory issue by quite a lot. It's basically making the backrooms of the Hermes Agents' memory system.

Still in development, and the readme is subject to change to fit the current database when I am done with it.

Here is the project:

https://t.co/TUEtFvBSng

[Pablo @pablothethinker]

I've been working on this concept inspired by Anthropic's new research on J-Space but made for @NousResearch's Hermes Agent by @Teknium.

I am calling it Hermespace.

It's still in development and the concept is new. I want to make it more in-depth on what this space can truly do for Hermes Agents and how it helps in everyday usage.

https://t.co/VyB6eS1xOT

[Pablo @pablothethinker]

@garyvee Literally that was me today man and it feels really good to finally just be focusing on doing what I want to allow room for the future me to grow even taller.

[Pablo @pablothethinker]

Today has been a great day, one of many to come.

I told myself I would keep working hard to get out of this cart-pushing job.

And it happened today: following the advice from @coreyganim, I mustered the courage to take my first step with my first client to build their first AI agent for their business.

It was a good 45-minute conversation where I realized I can do it and that this is possible. Moreover, this will change the course of my timeline.

Thank you, Corey, for sharing your knowledge and experience.

I've been wanting to do this for a long time, and even with some doubt, I showed them what is possible with the power of AI agents.

I know I can do this and I will succeed.