Register and share your invite link to earn from video plays and referrals.

Teknium 🪽
@Teknium
Cofounder and Lead Engineer - Hermes Agent @NousResearch, prev @StabilityAI Github: HuggingFace:
6.3K Following    129.9K Followers
Wild looking back at this now. This was an early glimpse of what eventually became a much larger part of Ares. Since then I’ve been building out deterministic model routing, semantic memory injection, governed tool execution, receipts/evidence, context management, heterogeneous local compute (I combined my crate with NVIDIA PAIR -- how I came across the bug that i patched and that merged into the NVIDIA/PAIR repo), and resumable agent execution. The original goal hasn’t changed: make capable agent systems more efficient, inspectable, and increasingly local-first. What started as “how much can I run in 16-32GB?” has turned into “how much of the agent stack can I make deterministic, verifiable, and owned by the operator?” -- I owe everything about my drive and direction right now to the low key encouragement by @Teknium
Show more
If you're in Bangkok be sure to check out this event!
bringing the full open-weights agent coalition to bangkok this friday. sep 25. doors open 18:00(ICT) at cleverse. 100% free. • desktop app, tui, browser extension, and bot mode live demos • multimodal reasoning & video generation with @MiniMax_AI (m3 + h3) + attendee credits • official memory partner: @honchodotdev deep dive + developer credits • thai voice-first agent showcase with botnoi group • exclusive @NousResearch merch giveaway + compute credit raffle • hands-on onboarding & builder networking over food and drinks hosted by me and officially sponsored by @NousResearch rsvp:
Show more
This is a much bigger deal than just “watching the agent work”. The agent gets its own remote desktop and persistent browser session. You can take over for logins, 2FA, CAPTCHAs, or anything that needs human input, then hand control back and it continues where you left off. This is what human-agent handoff should feel like. Really love where Hermes Desktop is heading. Congrats to @Teknium and the team!
Show more
Here's a handy walkthrough of the new Bot Screen feature by the illustrious @tonbistudio Docs:
Much needed!
Introducing Simple mode in Hermes Desktop. A cleaner interface without the developer instrumentation. Switch back to Advanced anytime and your full workspace returns exactly as you left it. @NousResearch
Show more
Damn, the cost numbers keep getting smaller even as I'm doing more: July 2026 - @claudeai 4.8 via @Replit: -- 10 commits / day -- $1K spent -- ~$3 / commit August 2026 - @thsottiaux 4.6 Sol via @t3dotcodes: -- 15.5 commits / day, -- $350 spent -- $0.75 / commit (75% reduction vs. July) September 2026 - @Kimi_Moonshot K3 via @NousResearch Hermes: -- 17.5 commits / day -- $175 spent -- $0.33 / commit (50% reduction vs. August) I do think control plane matters, and for ultimate speed, workflow efficiency and just feeling like you're running a million miles an hour, go @NousResearch (@Teknium is the goat). Now I just need to build the first good Hermes iOS client...
Show more
Impressive!
@Teknium @witcheer i am proud to say that my Hermes Agent finished 39/491 on the recent @DGA CTF it's competed with some of the best OSINT Team in the world and of course finished all CTF challenges before deadline.
Show more
The new GPT-6-Sol and GPT-6-Luna are now available in Hermes Agent in Nous Portal and OpenRouter, soon through Codex subscriptions as well!
Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more affordable models to support work at scale. We’ve also made caching and inference more efficient, and we’re passing the savings directly to you: 50% lower API prices for Sol and Luna compared with GPT‑5.6 promotional pricing.
Show more
Anthropic's Claude Opus 5.5 is now available in Hermes Agent via Nous Portal!
Hermes Agent and comfyui is over powered.!! Left it over night to do a character swap ref video (that Elon/sam rap) but with some other references. Broke it down, swapped out, checked reference video and redone until it got it perfect.. Brooo!
Show more
Welcome back to Hermes Agent, Claude New official plugin that uses Claude SDK without the tradeoffs to enable Claude Code subscriptions to work in Hermes Agent again! Check it out and install it here:
Show more
0
315
3.6K
242
Forward to community
🫡🫡🫡 Glad to hear it :)
After jumping around from - Zcode -> Deepseek Harness -> Command Code -> Opencode and then finally back to Hermes, I just realized how well rounded and feature rich is Hermes Agent, there is nothing like it in the market today.
Show more
Just FYI, it's all live now :) Plugin's each get a whole page when clicked into, their readme piped in. We also now have sort by recent, show all plugins by author, and more. Check out the catalog:
Show more
Love hearing stories like this 🫡🫡
My buddy only knew Gemini when it came to AI. Today I set up Hermes Agent for him, and he's literally calling me every half hour, totally blown away and calling me the modern-day Tesla. He got more done in one day than he did in two years with Gemini.
Show more
What part of your Hermes setup have you customized the most? Profiles, Skills, tools, permissions, something else?
Hermes Agent Plugin devs - would you like a whole page dedicated to your plugin on the plugins explorer? So a user can click in and see more details, and you can link to your plugin there?
GLM-5.3 FlashX is now available in Hermes Agent through Nous Portal and OpenRouter!
Every time I think “I wish my computer could do this,” it turns into another little project 😂 This is why I love Omarchy.@dhh I can build my own widgets, bring apps into them, add tabs, and shape the whole desktop around how I work. Here’s what I’ve been building: my own agent workspace, with Claude, Codex, and Hermes in one place. My computer is starting to feel like something I made.
Show more
Hermes Agent can now stream its THINKING into other AI apps. This is sick. Connect Open WebUI, LibreChat, opencode or another OpenAI-compatible client to Hermes... And Hermes can stream the model's reasoning LIVE before the final answer. Hermes isn't just an agent anymore. It's becoming a backend. 🤯
Show more