Parenting kids 👶 and agents 🤖 @tuikagents that reduce costs by up to 10x.
Visit my newsletter →
Joined September 2014
- Tweets2K
- Following605
- Followers1K
- Likes1.8K
Pinned Tweet
2022 • Working a 9-to-5 job
2023 • Unemployed, girlfriend pregnant
2024 • 50% parenting, 50% freelancing
2025 • AI replaces most of my dev work
2026 • Parenting kids & AI agents
I wanted to spend more time with my kid, so I ended up freelancing.
The journey has been rough, but exciting.
And I’ll be forever thankful to my daughter for that.
Creating a new Hermes profile just because you want to use a different model for specific skills?
Forget that.
You can associate each skill with a subagent, which has its own LLM.
(Oh, and Grok Bot can't do this)
Which one is your favourite?
You’re using Claude for coding.
What about the other 99 use cases?
Claude, Codex, Cursor, and Grok can’t ship tailored AI agents for every use case.
They also come at a cost.
Open-source harnesses, on the other hand, are free and offer unlimited customization.
Here are 5 worth exploring, along with their strengths, weaknesses, and use cases 👇
Every day, a new cool plugin 😅
This is great for my accounting.
I am very happy to present `hermes record`, a Hermes Labs plugin built by Nous Research.
it records what you do in your browser, creates a skill and Hermes can then repeat the task with whatever details you give it.
in this video, I record my pizza order, then use /learn to make a skill out of that recording, then ask my Hermes Agent to place a different order on its own :)
'hermes plugins install workflow-record'
AGI.
Open-source harnesses are on fire 🔥
Here are a few examples of what people are building with OpenClaw, Hermes Agent, Pi Agent, and the DeepSeek harness.
99% of them can't be done with Grok Bot 🧵👇
5. Control the Desktop from your phone
@NirvanaJie30 create a plugin for the DeepSeek Harness.
You can find the repo here:
github.com/Nirvana-Jie/dsh-l…
If you still don't know what the right open-source harness for you is, you can find out more about the top 5 OSS harnesses in this article 👇
xitter.cf/dadhalfdev/status/2113…
People use Grok Bot until they need:
> A better LLM for writing: because, let's be frank, Grok is really bad at writing.
> Add new tools: people will want custom providers for image generation, web search, browser actions, video generation, audio, and so on.
> Add agents to multiple gateways: the Grok Bot app isn't enough; everyone will want their agents running on Slack, WhatsApp, Telegram, or even SMS.
> Privacy: at this point, as a Grok Bot user, I'm aware that I'm completely exposing my personal and professional life to xAI; many people may not want that.
And there are many more reasons, like local AI, coding, and more customization overall!
Grok Bot is easy to use, but custom AI agents need open-source harnesses like the Hermes Agent, Pi Agent, and OpenClaw.
Finally!
This is super useful, especially when you have skills you want to spawn with subagents, but you want specific models associated with those skills.
Before, if I had a writing skill that uses Claude Opus 5.5 for better output, I had to link that model to one subagent.
Meaning that if I triggered other tasks that use subagents, I would still be paying for Opus 5.5, which is not ideal.
That is fixed!
Okay, this one is sneaky good.
Hermes can now run every subagent on a different model.
Advanced Delegation is an official Nous Research plugin. You set up named model routes, like fast and deep, and Hermes sends each piece of work down the route that fits.
▸ A fast, cheap model for lookups and summaries
▸ Your strongest model for the hard thinking
▸ A local model on your own endpoint
▸ Or another Hermes profile, with its own model, skills and SOULmd
Every result shows the route and model it actually ran on.
And Hermes only sees the names and descriptions you write, so it can't invent a route.
One agent, a whole bench of models.
Setup in the reply.
Multiple agents, multiple desktops.
No more shared screen.
Your Hermes Agent profiles, Grok Bots, and other agents all do their browser work in the same browser, share the same display, use the same cursor, and access the same filesystem.
That makes parallel browser actions difficult because you end up with two agents fighting over the same mouse and window.
@trycua Spaces fixes this by giving each of your agents its own desktop, so you can have several Spaces running in parallel. And a single agent can also have multiple Spaces.
Why does that matter?
> You can visualise what your agents are doing.
> You can have two or more scrapers running at once.
> You can get more done by running tasks in parallel.
> You can protect each bot’s sessions from the others, since each has its own disk and browser profile.
Everything still runs on the same machine, though, so don’t expect a huge productivity boost if your VPS only has 8 GB of RAM.
Also, the free tier only allows two live sessions and 20 remote hours per month. So you won’t be running an army of agents performing browser interactions simultaneously without paying for it.
In any case, this is a feature many users have been asking for: one Space per agent is now possible with any agent harness you can connect to MCP, including Grok Bot, Claude Code, Codex, Cursor, Hermes, and OpenClaw.
Your team and your Hermes can now share a computer.
The new @trycua Spaces plugin gives Hermes its own Linux, macOS, or Windows Space on hardware you already own. Anyone on your team can open it, watch live, step in, and hand it back while Hermes keeps working.
hermes-agent.nousresearch.co…
Feels like only Chinese labs ship on weekends.
First DeepSeek, now Kimi.
They are built differently.
You definitely don't need.
You probably don't need Opus 5.5.
At least for 90% of your tasks.
As models get more intelligent, the gap between what frontier models can do and what cheaper, open-weight models can do is shrinking.
Unless you're a developer building advanced software, there's probably no need to use Opus 5.5, Gemini 4 Argon, or GPT Astra.
They're all great models, but tokenmaxxing isn't always the answer, especially when you want to run your agents 24/7 across multiple tasks.
That's why we often advise our clients to use @OpenRouter to connect their custom agents to models like DeepSeek v4.1 Flash or Claude Haiku 5.5.
These models are not only much faster, but also up to 40 times cheaper!
My goal in life is to have an "Agentic Farm" powered by Hermes.