Teknium 🪽
@Teknium
Cofounder and Lead Engineer - Hermes Agent @NousResearch, prev @StabilityAI
Github:
HuggingFace:
6.2K Following 114.4K Followers
@KareliKagit @Polymarket If you use hermes, use the baoyu-infographic skill by @dotey, and set gpt image 2 or nano banana as your imagen, then your set!
K3 will be open sourced in 8 hours. Woot!
Somehow Hermes Agent was missing built in skill support for excel spreadsheets and docs. That is no more - powerpoint and pdf skills updated and enhanced, and excel spreadsheets and word document support is now in.
Show more
Prior to today, tool calls would work in parallel only if all were safe to parallelize. Now you gain big speedups for parallel tool calls so long as any subset are parallelizable.
Check it out
Show more
You can now access and activate your banked resets in Hermes Agent directly with /usage reset when using a codex/openai subscription
FYI you can make this your default message send mode (as opposed to interrupt or queue) in your config 👍👍
A nice but overlooked command in Hermes Agent is /steer. This allows you to send a message that will be delivered after the next tool call, guiding the agent when you tell it's moving in the wrong direction, without stopping it (wasting tool calls) and then redoing the prompt.
I had a real-life example of this so I made a short video explaining what happened, and how /steer worked so well. Check it out!
Show more
I said Grok 4.5 was a bigger deal than Fable
Elon even liked my post
but then GPT-5.6 Sol showed up
So I gave 7 of this week's newest AI models their own computer and ran the same real tasks through Hermes
Final ranking:
1. GPT-5.6 Sol: best overall
2. Grok 4.5: close second, fast and relentless
3. Muse Spark 1.1: the surprise of the week
Benchmarks tell you what a model might do.
Watching it control a computer shows you what it can actually do
Full comparison ↓
Show more
Today's Hermes Agent Masterclass is the finale! Module 10 covers security, an important topic for running agents to ensure each agent can perform its tasks while minimizing exposure. Hermes has a ton of built-in security features. In this clip, I show how you can set approvals for each profile depending on your needs.
Show more
dont forget the Nous team added a /learn command to hermes agent
turn something you already know or a pile of reference material into a reusable skill, without hand-writing the SKILL.md
Show more
Very cool!
Made a skill for creating lyric videos for my @suno songs using @NousResearch Hermes agent. Hermes with the new GPT 5.6 models is insanely cracked. @Teknium any plans for a community skill hub? GPT-Image-2 + Omni Flash for the visuals
Show more
If you have a GB10 (DGX Spark) and a Hermes Agent, have a look at what Mike did! Pretty smart 🧠🧠🧠
"/learn the DGX Spark playbooks found here and produce a skill that demonstrates a complete mastery of GB10 operations"
Show more
in a sea of basically sold out theatres...
hermes snagged primo imax 70mm odessey tickets for me.
here's a skill for ya.
hermes skills install alt-glitch/odyssey-imax-grab/odyssey-imax-grab
Show more
New Hermes Master class video by @tonbistudio !
Today's Hermes Agent Masterclass is the finale! Module 10 covers security, an important topic for running agents to ensure each agent can perform its tasks while minimizing exposure. Hermes has a ton of built-in security features. In this clip, I show how you can set approvals for each profile depending on your needs.
Show more
a few weeks ago Nous added @stripe skills in hermes
- allows hermes to buy things on the open web
- allows hemes to use pay-per-call APIs
- allows hermes to provision its own SaaS
pretty wild
Show more
If you have Hermes Cloud instances on Nous Portal, your desktop app will now auto-detect it to make it easy to connect to your remote agent!
Update your desktop app to give it a try!
Show more
The Hermes Desktop app can now discover and connect to your Hermes Cloud agents.
Sign in with Nous Portal and any active Cloud instances are auto-discovered.
Show more
At least for MiniMax, we will keep release frontier open weight Model
Help us out with your recommendations here!
We're working on making the local model experience better in Hermes, what are the best local models at each weight class?
My blind guess, please correct:
8-16 GB VRAM
Gemma4 12B
24-32 GB VRAM
Qwen3.6 27B
Qwen3.6 35B
128 GB VRAM (Spark, M3 Max)
??? Can you do DSv4-Flash?
Show more
Early days using Sol for Hermes Agent dev, and so far.. I think I like it more than Fable.
I've been using claude models for at least the last year primarily, but I just tried it on a relatively common heavy task - and Fable simply refused me of course, but, Sol not only didn't refuse but felt way more thorough, and its obviously way cheaper, and faster.
Will be probably trying Sol out for the rest of the week to see how I feel about it across a lot more dev tasks in Hermes Agent.
Show more
From the two run summaries, same 5 PRs:
- Sol: $1.66 total ($0.332/item)
- Terra: $0.46 total ($0.092/item)
Shipped HAEE, an evolution engine for Hermes that watches you work, catches when the agent slips, and auto-improves during normal chat.
PR:
Shipping PRs across most repos; this is the one I'd want to represent my work to join @NousResearch
cc @Teknium
Show more
