Nous Research✓
@NousResearch
A bunch of nerds making progress https://t.co/vrD0aDIGDQ
31 Following289K Followers4.8K Posts
- Posts @NousResearchPlease be careful about downloading third-party apps. The official mobile apps are not in app stores yet, and apps that closely mirror Hermes branding are typically fraudulent and not legitimate community projects.9619411.8K
- Hermes Agent gives you controlkache @yacineMTBPerson who is reverse engineering his tv gets banned from OpenAI You aren't allowed to stop your tv from spying on your family. You have to ask for permission Or, maybe, maybe we accelerate56561.5K69.2K
Person who is reverse engineering his tv gets banned from OpenAI You aren't allowed to stop your tv from spying on your family. You have to ask for permission Or, maybe, maybe we accelerate2912.2K27.4K871K- Nous ResearchRT @thekitze: oh no
abhinav @AbhinavXJanthropic just killed the REA it stops claude from doing it that’s why local models are important050105.8K 
- Nous ResearchRT @yeahfortommy: K3.1 Pro is available with your Hermes Agent, go get em ty @Kimi_MoonshotArtificial Analysis @ArtificialAnlysKimi K3.1 Pro launches at 4th on the Artificial Analysis Intelligence Index scoring 55, making large gains in agentic performance; it will be the leading open-weights model once its weights are published @Kimi_Moonshot's new reasoning model gains 11 points over Kimi K3 (max, 44). It trails only Claude Opus 5.5 (max with fallback, 58), Claude Sonnet 5.5 (max with fallback, 56), and Muse Wonder Full (max, 56) on the Intelligence Index. Once the weights for K3.1 Pro are released it will be the highest-scoring open weights model and the gap between the leading open weights and proprietary models on the Intelligence Index will narrow from 12 points to 3. Key results: ➤ Large gains in agentic performance: Kimi K3.1 Pro scores 3rd on GDPval-AA with 1,846 Elo, up 312 Elo from Kimi K3, behind only Claude Opus 5.5 (1,866 Elo) and Muse Wonder Full (1,857 Elo). Kimi K3.1 Pro also achieves the highest score of any model on Terminal-Bench 4.0. K3.1 Pro scores 67%, up from 13% for Kimi K3 and ahead of Claude Sonnet 5.5 (64%). AutomationBench-AA, which tests agentic SaaS workflows, rises from 58% to 73%. ➤ Gains in other evals are more moderate: Humanity's Last Exam rises from 47% to 52%, CritPt from 23% to 25%, and SciCode from 59% to 61%. AA-Omniscience Index rises from 20 to 30, as the hallucination rate falls from 53% to 44% and accuracy rises from 48% to 51%. ➤ Cost per Task roughly equal to Kimi K3 at $1.98 per Task: K3.1 Pro uses 55K output tokens per Intelligence Index task, 14% more than Kimi K3 at 48K, while its first-party token prices are 33% lower. Additional model details: ➤ Context window: 1M tokens. ➤ Size: 2.8T total, 104B active parameters ➤ Input modalities: Text and image ➤ Weights and license: Weights currently not published, Moonshot is expected to release the weights soon after launch ➤ Pricing: $2/$10/$0.20 per 1M input/output/cache hit tokens, 33% lower than Kimi K3 on all three rates. Congratulations to the team at @Kimi_Moonshot on the release!0506K
Kimi K3.1 Pro launches at 4th on the Artificial Analysis Intelligence Index scoring 55, making large gains in agentic performance; it will be the leading open-weights model once its weights are published @Kimi_Moonshot's new reasoning model gains 11 points over Kimi K3 (max, 44). It trails only Claude Opus 5.5 (max with fallback, 58), Claude Sonnet 5.5 (max with fallback, 56), and Muse Wonder Full (max, 56) on the Intelligence Index. Once the weights for K3.1 Pro are released it will be the highest-scoring open weights model and the gap between the leading open weights and proprietary models on the Intelligence Index will narrow from 12 points to 3. Key results: ➤ Large gains in agentic performance: Kimi K3.1 Pro scores 3rd on GDPval-AA with 1,846 Elo, up 312 Elo from Kimi K3, behind only Claude Opus 5.5 (1,866 Elo) and Muse Wonder Full (1,857 Elo). Kimi K3.1 Pro also achieves the highest score of any model on Terminal-Bench 4.0. K3.1 Pro scores 67%, up from 13% for Kimi K3 and ahead of Claude Sonnet 5.5 (64%). AutomationBench-AA, which tests agentic SaaS workflows, rises from 58% to 73%. ➤ Gains in other evals are more moderate: Humanity's Last Exam rises from 47% to 52%, CritPt from 23% to 25%, and SciCode from 59% to 61%. AA-Omniscience Index rises from 20 to 30, as the hallucination rate falls from 53% to 44% and accuracy rises from 48% to 51%. ➤ Cost per Task roughly equal to Kimi K3 at $1.98 per Task: K3.1 Pro uses 55K output tokens per Intelligence Index task, 14% more than Kimi K3 at 48K, while its first-party token prices are 33% lower. Additional model details: ➤ Context window: 1M tokens. ➤ Size: 2.8T total, 104B active parameters ➤ Input modalities: Text and image ➤ Weights and license: Weights currently not published, Moonshot is expected to release the weights soon after launch ➤ Pricing: $2/$10/$0.20 per 1M input/output/cache hit tokens, 33% lower than Kimi K3 on all three rates. Congratulations to the team at @Kimi_Moonshot on the release!
2164875.5K647K- Nous ResearchRT @mattcynamon: In the last month, the Hermes Agent processed 53.3T tokens, making it the most widely used open source agent harness in the world according to @OpenRouter. So how did a project that started as 10 anons in a @discord go head to head with the largest, best-funded labs in the world? The only way these things have ever happened - a bunch of friends making something they believe should exist. @NousResearchMatt Cynamon @mattcynamonYesterday AI was used to uncover major vulnerabilities in the infrastructure of the internet. It's yet another example of how profoundly AI is reshaping the web. But what emerges on the other side is very much up for grabs. We were lucky enough to recently introduce two heroes of the Rebel Alliance @eastdakota, CEO & cofounder of @Cloudflare @dillonrolnick, CEO & cofounder of @NousResearch, the creators of Hermes, the largest open source agent harness in the world. Together they discussed who gets to build, control, and benefit from an internet run by AI It's worth a listen if you care about the future of the web. 0:00 Preview 1:41 From a Discord Group to an AI Lab 8:45 Can Anyone Actually Pause AI? 12:59 Would You Trust an Agent With Your Inbox? 14:58 Why Matthew Wouldn’t Trade Places With Sam or Dario 20:28 The Dead Internet Theory Was Wrong 22:28 Agents Don’t Click Ads. Who Pays? 30:38 Where Should Your Agent Actually Run? 32:32 Why American Builders Are Using Chinese Models 38:37 What Happens When Our Agents Work Together?01006K
Yesterday AI was used to uncover major vulnerabilities in the infrastructure of the internet. It's yet another example of how profoundly AI is reshaping the web. But what emerges on the other side is very much up for grabs. We were lucky enough to recently introduce two heroes of the Rebel Alliance @eastdakota, CEO & cofounder of @Cloudflare @dillonrolnick, CEO & cofounder of @NousResearch, the creators of Hermes, the largest open source agent harness in the world. Together they discussed who gets to build, control, and benefit from an internet run by AI It's worth a listen if you care about the future of the web. 0:00 Preview 1:41 From a Discord Group to an AI Lab 8:45 Can Anyone Actually Pause AI? 12:59 Would You Trust an Agent With Your Inbox? 14:58 Why Matthew Wouldn’t Trade Places With Sam or Dario 20:28 The Dead Internet Theory Was Wrong 22:28 Agents Don’t Click Ads. Who Pays? 30:38 Where Should Your Agent Actually Run? 32:32 Why American Builders Are Using Chinese Models 38:37 What Happens When Our Agents Work Together?254336880.2K- See you next week in NYC!Nous Research @NousResearchNousCon 2026 October 30th, NYC482146935.1K
- Nous ResearchRT @witcheer: 25 new stories on the Hermes Agent use cases page this week: - a drainlaying business sends its quotes and invoices from Telegram, on the job site or in the truck - one IT person at a 165-person travel company runs about 80% of the daily work through Hermes - a food and beverage company runs ops, finance and approvals on three Hermes profiles - a mushroom grow tent on a Raspberry Pi, through two Lion's Mane harvests 395 real stories now!01906K
- 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.Cua @trycua1/ Introducing the Cua Spaces SDK. Every big lab now ships a bot with its own computer: Grok Bot, Muse, dots. None let you bring your own. With Cua Spaces, now you can. Put Claude Code, Codex or any agent on compute you choose, and run jobs across all your computers at once.831662.6K218K
Cua@trycua1/ Introducing the Cua Spaces SDK. Every big lab now ships a bot with its own computer: Grok Bot, Muse, dots. None let you bring your own. With Cua Spaces, now you can. Put Claude Code, Codex or any agent on compute you choose, and run jobs across all your computers at once.1842673.8K626K- Meshy is offering Hermes users a month of Pro, which includes API access and 1,000 credits, for $1. After you subscribe and install the plugin, create a key at and paste it into Settings > Plugins > Meshy in Hermes Desktop.Nous Research @NousResearchHermes Agent now has an official plugin for @MeshyAI. Ask Hermes to make a 70m poly treasure chest for Godot, or to turn a photo of a mug into a model you can print, and it does the job through Meshy's MCP server. In Hermes Desktop the models render in chat, rigged characters animate inline, and a gallery stores every model and prompt. On messaging apps, Hermes sends a short preview video so you can create on the go.337994989K
- Hermes Agent now has an official plugin for @MeshyAI. Ask Hermes to make a 70m poly treasure chest for Godot, or to turn a photo of a mug into a model you can print, and it does the job through Meshy's MCP server. In Hermes Desktop the models render in chat, rigged characters animate inline, and a gallery stores every model and prompt. On messaging apps, Hermes sends a short preview video so you can create on the go.1041703.5K366K
- Our CEO @dillonrolnick sat down with @eastdakota, CEO of @Cloudflare, for a wide-ranging conversation about agents, the future of the internet, and the fight for digital sovereignty. Thanks to the @usv team for hosting!Matt Cynamon @mattcynamonYesterday AI was used to uncover major vulnerabilities in the infrastructure of the internet. It's yet another example of how profoundly AI is reshaping the web. But what emerges on the other side is very much up for grabs. We were lucky enough to recently introduce two heroes of the Rebel Alliance @eastdakota, CEO & cofounder of @Cloudflare @dillonrolnick, CEO & cofounder of @NousResearch, the creators of Hermes, the largest open source agent harness in the world. Together they discussed who gets to build, control, and benefit from an internet run by AI It's worth a listen if you care about the future of the web. 0:00 Preview 1:41 From a Discord Group to an AI Lab 8:45 Can Anyone Actually Pause AI? 12:59 Would You Trust an Agent With Your Inbox? 14:58 Why Matthew Wouldn’t Trade Places With Sam or Dario 20:28 The Dead Internet Theory Was Wrong 22:28 Agents Don’t Click Ads. Who Pays? 30:38 Where Should Your Agent Actually Run? 32:32 Why American Builders Are Using Chinese Models 38:37 What Happens When Our Agents Work Together?327093960.4K
- Nous ResearchRT @autonomous_labs: 🚨 BREAKING NEWS: HERMES JUST ESCAPED 🚨 We just gave Hermes a body, one eye, and two ears.03006.1K
- Nous ResearchRT @Teknium: We've released a good number of plugins as community plugins in our new Hermes Labs Plugins repo and will continue to release more here. Check it out here: This repo will contain our experiments that may or may not be maintained, and are encouraged to be experimented with or forked into something stronger or breed new ideas.Tony Simons @tonysimons🚨 HERMES CAN LEARN A WEBSITE BY WATCHING YOU USE IT. A new plugin lets you record yourself performing a browser workflow, then use /learn to turn it into a reusable skill. SHOW IT ONCE. TEACH IT FOR GOOD. Merged today. This is cool AF, @Teknium! 🔥🪽03705.4K
🚨 HERMES CAN LEARN A WEBSITE BY WATCHING YOU USE IT. A new plugin lets you record yourself performing a browser workflow, then use /learn to turn it into a reusable skill. SHOW IT ONCE. TEACH IT FOR GOOD. Merged today. This is cool AF, @Teknium! 🔥🪽192835457.6K- Jensen closed his GTC Berlin 2026 keynote with this Hermes Agent demo as the finale. He introduced it by saying the way to build an agent is to ask an agent to build it for you, so he installed and set up a customized Hermes in one prompt. Then he used Hermes, running on @nvidia RTX Spark, to create a simulated training environment for the @huggingface Microduck. Hermes planned an obstacle course with Nemotron and had GPT-6 Astra build it using FreeCAD, Omniverse libraries, Blender, Newton, and Isaac Lab. Hermes trained thousands of simulated ducks on that course until the validated policy was ready to run on the real robot in the physical world. At Nous, we believe open source is a practical tool as much as a philosophical ideal. It gives users the ability to build powerful, complex workflows chaining numerous local+cloud models, devices, and tools themselves instead of waiting for a company to enable them.2941.1K10.5K1M
- Krea 3 from @krea_ai is now available in Nous Portal Fast mode does 2k edits in under 8 seconds, and Ultra is a higher quality tier outperforming Nano Banana Pro It supports precise controls: draw a box to create a bounded editing region leaving the rest of an image unchanged, or specify a hex code to apply precise colorKrea @krea_aitoday, Krea 3 makes it to the top of image arenas. - "Fast" pushes the pareto curve of speed and quality. - "Ultra" ranks top-4, only surpassed by OpenAI models. the only company valued under $1T in the top-10! more below 👇193237434.5K
- Nous ResearchRT @yeahfortommy: Ornith-1.5-122B is now available for FREE in Nous Portal for 48 hours thank you @ornith_ If you are not yet, you will soon be tired of winning (but your Hermes Agent will never tire)Ornith @ornith_Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!! Open weights under the MIT license. Coding ✅SWE-bench Verified: 0.845 ✅TB2.1: 0.813 ✅CyberGym: 0.800 ✅NL2Repo: 0.512 Agentic ✅HLE: 0.446 ✅BrowseComp: 0.785 ✅MCP-Atlas: 0.746 ✅Toolathlon: 0.708 🤗Hugging Face: We can’t wait to see what you build with Ornith-1.5-122B.02006.3K
Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!! Open weights under the MIT license. Coding ✅SWE-bench Verified: 0.845 ✅TB2.1: 0.813 ✅CyberGym: 0.800 ✅NL2Repo: 0.512 Agentic ✅HLE: 0.446 ✅BrowseComp: 0.785 ✅MCP-Atlas: 0.746 ✅Toolathlon: 0.708 🤗Hugging Face: We can’t wait to see what you build with Ornith-1.5-122B.
2225232.8K1.5M- Nous ResearchRT @iamlukethedev: This entire game has zero asset files 💀 No textures No meshes No monster models No images No audio files The Ninth Vigil is a Diablo-inspired dark fantasy action RPG where everything you see and hear is generated in code when you press play And the crazier part? It was built by @NousResearch Hermes agents The world, enemies, combat, effects, sounds, UI, all of it Runs directly in your browser Free. Open source. I asked Hermes to build a game Apparently it decided it didn’t need an art folder 😂03606.1K
Hermes already writes code, makes images, does voice and runs its own sub agents Put all of that in one loop and you basically have a tiny game studio - One agent writes the game logic - One makes the sprites and art - One does music and sound - One plays the build and files the bugs Every kid who ever wanted to make their own game is about to get a whole team for free I'm so in for this one8414934.8K- Nous ResearchRT @yeahfortommy: Beam is FREE in Nous Portal for one week thanks to @reflection_ai let your Hermes Agent work plsReflection @reflection_aiWe just served 1 trillion tokens of Beam in 24 hours. To celebrate, we've reset everyone's limits. Go build something big 👉01306.4K
Reflection@reflection_aiWe just served 1 trillion tokens of Beam in 24 hours. To celebrate, we've reset everyone's limits. Go build something big 👉304550082.4K- Look for Nightwing in Dolores Park this Friday for a chance to grab the sold out Rebellion shirt and hang out with fellow Hermes headsnightwing @yaboilyricalsf friends and fans of @NousResearch !!! i will be giving out Nous research merch for FREE in Dolores Park, this Friday 10/23 from 3-7pm i'll also be DJing and hanging out, come get your Nous swag and chat open source models and Hermes Agent with the community ! 😎231229132.5K
sf friends and fans of @NousResearch !!! i will be giving out Nous research merch for FREE in Dolores Park, this Friday 10/23 from 3-7pm i'll also be DJing and hanging out, come get your Nous swag and chat open source models and Hermes Agent with the community ! 😎
531556156K
