I am three hardware steps away from completing an ablative laser rig for cutting 3 µm microscopic features and fusion welding. Safety goggles are not enough.

Today marks 6 months of Hermes Agent 6 months ago, all of our workflows looked very different Today, thousands of us use Hermes to build, automate, research, code, run agents, and manage real workflows every day I think we forget how fast this happened For me, Hermes changed almost everything about how I work So today is a good day to say thank you. Thank you @NousResearch, @Teknium, every contributor, and this entire community for building something that became much more than just another AI tool Happy 6 months, Hermes. 🥳 What has Hermes changed for you?

We put Meta’s new Muse Glimmer 30B model on deck in our agentic AI game tournament for hours. Find out how it performed and how AMD brings 30B agentic AI to the PC, locally, on-device, and without cloud token costs. Learn more: amd.com/en/blogs/2026/run-me…

the smallest agentic model from @AntLingAGI just dropped, and i'm pulling it onto a single rtx 3090 right now. full precision, the whole thing sitting on one gamer card with room to spare. this is the part nobody tells you about the open model wave in 2026. every week a new model lands, they keep getting smaller and sharper, and my 3090 keeps getting more capable without me spending a cent on hardware. the card i bought to play games now runs agentic work at full precision, offline, 100% mine. 7.9 billion parameters moe, 1.3 billion active, and on the public index it's already scoring like models four times its size. built for agents, thinking you toggle on or off, 256k context. on one rtx 3090. i'm benching it now, tokens per second, how far the context stretches before it breaks, and a real agentic build to see if it does the work or just chats well. receipts incoming soon. what a time to own a gpu.

By popular demand, we are extending our 90% off discount on DeepSeek V4 Flash 0731 for the next 3 days. Try it today at portal.nousresearch.com

Seeing videos and clips from @QuakeCon showing up in my feed, and I'm teary-eyed reminiscing about the event, and definitely wish I was there this year!! Man those were fun times.... youtube.com/watch?v=bQwmDSCq…

So much in the Herald Release of Hermes Agent - Voice Activated Chats (Replace your google home and alexas!) - Plugins and Kanban for the Desktop GUI App - Agent2Agent Protocol - Outbound Webhooks - Massive performance optimizations and token efficiency milestones reached - Buzz Integration - Nous Portal's 20% Discount on all models - Way more reliable local and open models - New office/productivity skills - Grounded research skill - Secrets lockdown with Ironproxy and like 500 other things. Check them all out!

holy shit. a 3bit quant just built me a working game, driving hermes agent from one sentence, tested it itself, and won me over. that is deepseek v4 flash 0731 IQ3_XXS, dancing on one dgx spark, the smallest 3bit that fits on 128gb. i gave it one line, "build a simple space shooter game i can test right now". and watch it plan for build, wrote it in a single file, ran it, debugged its own test, and verified the result before it ever showed me. it oneshot a working game, tested correctly, and it felt genuinely reliable. a 3bit quant is not supposed to do that. the numbers so you know it is real: 16.5 tok/s decode, 332 prefill, 128k context, no spec decode, every layer on the gpu, 284b total, 13b active. i think you are watching the 284b weights come through, even squeezed to 3bit there is enough model left to actually reason, and you can see it in how it works the problem. you might never run this. watch it anyway. a 284b model on a box on a shelf, taking one sentence and shipping a game, fully local, nothing leaving the network. this is what open weights on hardware you own looks like now.

Hermes Agent is now dramatically more efficient, especially for smaller/weaker/local models! With the help of @nvidia's Nemo Relay and several other strategies Hermes was able to identify a ton of optimizations beyond just saving tool execution time or memory - but also turns needed to complete tasks, schema improvements to reduce context load, and token efficiency gains by tracing through wasted turns and tool errors across all 250,000 conversations I've had with my Hermes. All of the below are now in Hermes Agent, update to start saving now or wait until tomorrow for the full version update release.

and this already happened, at scale. a whole wave of ai startups raised big, shipped a wrapper, couldn't survive their own api bill, and quietly disappeared. every one of them could tell you which frontier model they used. not one could tell you what their workload cost per task, or whether a smaller model would've done the same job. it was never about using ai, anyone can use ai. it's about managing the workload and the cost of running it, which model for which job, on what hardware, at what price. that's the engineering, and it's the part that decides who's still here next year.

dear open labs, and i mean this with love. you keep dropping these trillion parameter giants and they're genuinely beautiful and i can't run a single one of them, none of us can, they land on huggingface to a standing ovation and then they just sit there, because the only machines that can load them are the same datacenters we were all trying to get free of. i watched local ai turn into something real this year, people running 27b models on one gaming card, an 8gb board doing work that needed a server a year ago, whole little communities forming around whatever fits on the hardware already sitting on the desk, and that's the part that actually reaches people, the revolution nobody's putting on a keynote slide. so here's the fair ask, give us the 40b dense, give us the 120b moe, the sizes a person with one good card or a 128gb box at home can actually hold and run and learn from and build on, because not everything has to be shaped for an enterprise with a rack to spare. the frontier is thrilling and i'll keep cheering every open weight you ship, i mean that, but the ground is where most of us live and the ground is quietly running out of models it can lift. build for the hardware we already own. that's where the next wave comes from, it always was. with love, from someone running yours on a laptop at midnight.