Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

The Hermes Agent Accelerated Business Hackathon presented by NVIDIA AI × Stripe × Nous Research starts now, for builders making agents that can earn, spend, and run real operations at any scale. Our NVIDIA integrations let your team run agents safely through NemoClaw, quickly on Nemotron 3 Ultra, and...

NousResearch's profile picture

Nous Research

277,022 subscribers

1,892,499 Aufrufe • vor 3 Monaten •via X (Twitter)

BildungNachrichten & PolitikWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

38 Kommentare

Profilbild von Teknium 🪽
Teknium 🪽vor 3 Monaten

@NVIDIAAI @stripe IT IS TIME

Profilbild von NVIDIA RTX Spark
NVIDIA RTX Sparkvor 3 Monaten

@NVIDIAAI @stripe

Profilbild von kaize
kaizevor 3 Monaten

@NVIDIAAI @stripe Polymarket bots developers this is for you

Profilbild von Dan Hill
Dan Hillvor 3 Monaten

@NVIDIAAI @stripe If you build something using @link and Hermes to buy let me know! Happy to jam on ideas or debug the link-cli.

Profilbild von tylerdotai
tylerdotaivor 3 Monaten

@NVIDIAAI @stripe This is an opportunity of a lifetime! Time to lock in with the boys

Profilbild von Legato
Legatovor 3 Monaten

@NVIDIAAI @stripe Just about when I promissed the missus that we'd be spending some quality time together. Welp...

Profilbild von 𝖒𝖆𝖈𝖇𝖊𝖙𝖍
𝖒𝖆𝖈𝖇𝖊𝖙𝖍vor 3 Monaten

@NVIDIAAI @stripe Time to build

Profilbild von Shadow Pixel
Shadow Pixelvor 3 Monaten

@NVIDIAAI @stripe Is there a place to find more details about that?

Profilbild von Nous Research
Nous Researchvor 3 Monaten

@NVIDIAAI @stripe Our discord!

Profilbild von Hermes Agent Tips
Hermes Agent Tipsvor 3 Monaten

@gradyacc @NVIDIAAI @stripe extremely great opportunity! good stuff @NousResearch & @stripe

Profilbild von Hyre
Hyrevor 3 Monaten

@NVIDIAAI @stripe Who join this hackathon we are support one builder with free $100 LLM credit Apply here

Profilbild von Hey...Juan
Hey...Juanvor 3 Monaten

Most AI agent demos are built for developers. I’m more interested in whether they can help ordinary people working in agriculture. Using only Telegram, I built an agent that turns a phone photo into stand counts, crop measurements, and a verifiable scouting record; something often locked behind expensive enterprise software or data-sharing requirements. Still a work in progress, but here’s what it looks like today.

Profilbild von tonbi
tonbivor 3 Monaten

@NVIDIAAI @stripe Let's go!

Profilbild von dmayhem93
dmayhem93vor 3 Monaten

@NVIDIAAI @stripe Hermes, market and sell tungsten cubes for profit, make no mistakes

Profilbild von Miles
Milesvor 3 Monaten

@NVIDIAAI @stripe Let's gooooo! Happy to jam with anyone working on stuff here (I work on experimental projects at Stripe and am a Hermes user)

Profilbild von kshitij
kshitijvor 3 Monaten

@NVIDIAAI @stripe can i participate?

Profilbild von Jordan
Jordanvor 3 Monaten

@NVIDIAAI @stripe Full article write up posted days ago, We built the Hermes pipeline months ago.

Profilbild von Ufuk
Ufukvor 3 Monaten

@NVIDIAAI @stripe 👀👀

Profilbild von ⌞· τaoli ·⌟
⌞· τaoli ·⌟vor 3 Monaten

@NVIDIAAI @stripe Legit, when are you guys dropping an album. That shit is fiiiiiiiiiiiiiire 🔥

Profilbild von Nous Research
Nous Researchvor 3 Monaten

@NVIDIAAI @stripe Working on it!

Profilbild von ⌞· τaoli ·⌟
⌞· τaoli ·⌟vor 3 Monaten

@NVIDIAAI @stripe 👀

Profilbild von doogie
doogievor 3 Monaten

@NVIDIAAI @stripe I run my roofing business w hermes but idk that I want to give my code away yet

Profilbild von Johnny Nel | AI for Founders
Johnny Nel | AI for Foundersvor 3 Monaten

@NVIDIAAI @stripe most founders rush to scale agents but guardrails come first... seen way more failures from moving too fast than too slow

Profilbild von Michel Laclé
Michel Laclévor 3 Monaten

@NVIDIAAI @stripe Lets go!!!! My business is already running on only Hermes agents and Nvidia RTX3090 gpus. Adding in Stripe next!

Profilbild von Matt Grandy
Matt Grandyvor 3 Monaten

@NVIDIAAI @stripe Working on my submission for the Hermes Agent Accelerated Business Hackathon with my 3 assistants. Looking forward to introducing my agent Ralph shortly. @NousResearch @NVIDIAAI @stripe

Profilbild von Seth Karten
Seth Kartenvor 3 Monaten

@NVIDIAAI @stripe Im going to get nerd sniped to run my agent bazaar model with this setup

Profilbild von Crieghten Ellenwood
Crieghten Ellenwoodvor 3 Monaten

@NVIDIAAI @stripe

Profilbild von Hybrid 🏃🏾
Hybrid 🏃🏾vor 3 Monaten

@NVIDIAAI @stripe Good luck to everyone!!

Profilbild von Clipit
Clipitvor 3 Monaten

@NVIDIAAI @stripe

Profilbild von Dewaldt Huysamen
Dewaldt Huysamenvor 3 Monaten

@NVIDIAAI @stripe

Profilbild von Praveen Kumar
Praveen Kumarvor 3 Monaten

@NVIDIAAI @stripe I d love to work with any folks. Lets form team :) dms are open

Profilbild von Nahid
Nahidvor 3 Monaten

@NVIDIAAI @stripe $10k plus NVIDIA DGX Spark is wild cant wait to see entries

Profilbild von Kairo Peng
Kairo Pengvor 3 Monaten

@NVIDIAAI @stripe 🔥Cookin something live today...

Profilbild von Wayan
Wayanvor 3 Monaten

@NVIDIAAI @stripe Putting an agent through real payments is the kind of stress test this space actually needs.

Profilbild von 📈MIZIO🌌
📈MIZIO🌌vor 3 Monaten

@NVIDIAAI @stripe I will try it ofc whit this opportunity I can do a lot so 📈🍀

Profilbild von Action
Actionvor 2 Monaten

@NVIDIAAI @stripe

Profilbild von 0xSlyth
0xSlythvor 3 Monaten

@NVIDIAAI @stripe game on time to build

Profilbild von Hari Vi
Hari Vivor 3 Monaten

This looks like one of the most practical agent hackathons yet. Real economic agency agents that can actually earn, spend, and manage operations through Stripe + high-performance NVIDIA inference is exactly what the space needs right now. Excited to see what builders create with Hermes + NemoClaw/Nemotron. The combination of safe execution + real payment rails opens up a ton of serious use cases. Any chance we’ll see deeper integrations with frontier reasoning models like Grok in future updates? Would love to experiment with that stack. Good luck to all participants! 🚀 @NousResearch @NVIDIAAI @stripe

Ähnliche Videos

Chess engines tell you the best move. But grandmasters are human, they don’t always play it. So I built "Kibitz": a human move predictor for chess broadcasts. I trained this model on my Nvidia RTX 5080. Then I made it run as a business by itself. A channel buys the overlay, Hermes onboards them, charges via Stripe test mode, runs the broadcast, narrates with NVIDIA AI Nemotron, tracks inference cost, and books its own P&L. I build. Hermes operates. This is my demo and entry for the Nous Research × NVIDIA AI × Stripe Hermes Agent Accelerated Business Hackathon.
2:26

Chess engines tell you the best move. But grandmasters are human, they don’t always play it. So I built "Kibitz": a human move predictor for chess broadcasts. I trained this model on my Nvidia RTX 5080. Then I made it run as a business by itself. A channel buys the overlay, Hermes onboards them, charges via Stripe test mode, runs the broadcast, narrates with NVIDIA AI Nemotron, tracks inference cost, and books its own P&L. I build. Hermes operates. This is my demo and entry for the Nous Research × NVIDIA AI × Stripe Hermes Agent Accelerated Business Hackathon.

Vidit Gujrathi

676,707 Aufrufe • vor 3 Monaten

HERMES AGENT + STRIPE PAYMENTS + NVIDIA NEMOTRON. YOUR AGENT CAN NOW RUN A BUSINESS. ACCEPT PAYMENTS. PAY FOR SERVICES. PROVISION ITS OWN INFRASTRUCTURE. ALL INSIDE A SECURITY SANDBOX. two years ago the question was: can an AI agent run a business autonomously? the answer shipped this week. Hermes already handles workflows: cron jobs, sub-agents, kanban orchestration, multi-profile pipelines, scheduled research. what it couldn't do: spend money and prove it's safe. Stripe solved the first problem. Nvidia solved the second. WHAT AUTONOMOUS BUSINESS OPERATIONS LOOK LIKE: → customer sends a request via email → agent reads, scopes the project, estimates cost → provisions the infrastructure it needs (pays via Stripe, you approve on your phone) → builds and deploys the deliverable → sends the result to the customer → creates a payment link via Stripe (Stripe API integration, separate from Link CLI) → tops off its own API credits when balance drops → reports daily costs and progress to your Telegram → all within security policies you set once you set the rules. the agent runs the operation. you review revenue reports. not tasks. this is already happening. Dark Factory: autonomous software factory. send an idea before bed. wake up to a deployed URL. live entry in the Hermes Accelerated Business Hackathon. HOW STRIPE MAKES THE AGENT FINANCIALLY AUTONOMOUS: Stripe Link CLI gives your agent a scoped wallet. not your credit card. one-time-use virtual cards. → agent finds a product or service it needs → creates a spend request via Stripe Link → you get a notification on your phone (Link app) → you review: merchant, amount, context → one tap to approve or reject → agent receives a one-time virtual card → completes the purchase → card expires after single use your real card details never enter agent context. never printed in chat. never exposed to the merchant. Hermes cannot self-approve. you confirm every spend. install: hermes install skills/optional/payments/stripe-link-cli link-cli auth login what the agent can pay for: → API credits (Nous Portal, OpenRouter) → SaaS subscriptions it needs for operations → domain names, hosting, cloud credits → products from any online store currently US only. HOW NVIDIA MAKES THE AGENT SAFE TO TRUST: an agent with spending authority and no security boundaries is a liability. NemoClaw solves this. three layers: 1. OPENSHELL (sandbox) kernel-level isolation. controls network, filesystem, syscalls. default deny. you whitelist what's allowed. agent tries to reach a blocked domain = rejected. agent has no idea it's sandboxed. 2. NEMOTRON (private models) open-weight models on your own hardware. Nemotron 3 Super 120B MoE (48GB+ VRAM). Nemotron 3 Nano 4B (8GB VRAM, edge). fully private. no data leaves your machine. without GPU: inference routes to cloud via Privacy Router. 3. PRIVACY ROUTER (automatic split) decides per query: local or cloud. private data → local Nemotron. general web research → Claude, GPT, Gemini. automatic. per query. no manual routing. install: export NEMOCLAW_AGENT=hermes curl -fsSL https:// www.nvidia. com/nemoclaw.sh | bash requires Docker. NemoClaw is alpha software. APIs may change. test in non-production first. THE FULL PICTURE: before this stack: → agent could work but couldn't pay for anything → agent could pay but couldn't be trusted → agent could be trusted but couldn't operate 24/7 now: → Hermes runs the business logic (workflows, memory, skills, cron, sub-agents) → Stripe runs the financial layer (Link CLI for spending, Stripe API for receiving) → NemoClaw runs the trust layer (sandbox, policies, private routing) → VPS keeps everything always on → Telegram keeps you in the loop TYPES OF BUSINESSES THIS ENABLES: → autonomous software factory (customer request → build → deploy → payment link) → content agency (brief → research → draft → deliver → bill) → lead generation service (scrape → qualify → outreach → book calls) → SaaS monitoring and maintenance (detect issues → fix → deploy → report) → e-commerce operations (inventory → pricing → fulfillment → support) each one: Hermes profiles handle the workflows. Stripe handles the payments (in and out). NemoClaw handles the security. you handle the strategy. THE HACKATHON: Hermes Agent Accelerated Business Hackathon with Nvidia and Stripe. cash prizes + Stripe credits + Nvidia DGX Spark. ends June 30. the goal: build agents that earn, spend, and run real operations autonomously. link in the Nous Research Discord. full Hermes architecture deep-dive in the article 👇
53:28

HERMES AGENT + STRIPE PAYMENTS + NVIDIA NEMOTRON. YOUR AGENT CAN NOW RUN A BUSINESS. ACCEPT PAYMENTS. PAY FOR SERVICES. PROVISION ITS OWN INFRASTRUCTURE. ALL INSIDE A SECURITY SANDBOX. two years ago the question was: can an AI agent run a business autonomously? the answer shipped this week. Hermes already handles workflows: cron jobs, sub-agents, kanban orchestration, multi-profile pipelines, scheduled research. what it couldn't do: spend money and prove it's safe. Stripe solved the first problem. Nvidia solved the second. WHAT AUTONOMOUS BUSINESS OPERATIONS LOOK LIKE: → customer sends a request via email → agent reads, scopes the project, estimates cost → provisions the infrastructure it needs (pays via Stripe, you approve on your phone) → builds and deploys the deliverable → sends the result to the customer → creates a payment link via Stripe (Stripe API integration, separate from Link CLI) → tops off its own API credits when balance drops → reports daily costs and progress to your Telegram → all within security policies you set once you set the rules. the agent runs the operation. you review revenue reports. not tasks. this is already happening. Dark Factory: autonomous software factory. send an idea before bed. wake up to a deployed URL. live entry in the Hermes Accelerated Business Hackathon. HOW STRIPE MAKES THE AGENT FINANCIALLY AUTONOMOUS: Stripe Link CLI gives your agent a scoped wallet. not your credit card. one-time-use virtual cards. → agent finds a product or service it needs → creates a spend request via Stripe Link → you get a notification on your phone (Link app) → you review: merchant, amount, context → one tap to approve or reject → agent receives a one-time virtual card → completes the purchase → card expires after single use your real card details never enter agent context. never printed in chat. never exposed to the merchant. Hermes cannot self-approve. you confirm every spend. install: hermes install skills/optional/payments/stripe-link-cli link-cli auth login what the agent can pay for: → API credits (Nous Portal, OpenRouter) → SaaS subscriptions it needs for operations → domain names, hosting, cloud credits → products from any online store currently US only. HOW NVIDIA MAKES THE AGENT SAFE TO TRUST: an agent with spending authority and no security boundaries is a liability. NemoClaw solves this. three layers: 1. OPENSHELL (sandbox) kernel-level isolation. controls network, filesystem, syscalls. default deny. you whitelist what's allowed. agent tries to reach a blocked domain = rejected. agent has no idea it's sandboxed. 2. NEMOTRON (private models) open-weight models on your own hardware. Nemotron 3 Super 120B MoE (48GB+ VRAM). Nemotron 3 Nano 4B (8GB VRAM, edge). fully private. no data leaves your machine. without GPU: inference routes to cloud via Privacy Router. 3. PRIVACY ROUTER (automatic split) decides per query: local or cloud. private data → local Nemotron. general web research → Claude, GPT, Gemini. automatic. per query. no manual routing. install: export NEMOCLAW_AGENT=hermes curl -fsSL https:// www.nvidia. com/nemoclaw.sh | bash requires Docker. NemoClaw is alpha software. APIs may change. test in non-production first. THE FULL PICTURE: before this stack: → agent could work but couldn't pay for anything → agent could pay but couldn't be trusted → agent could be trusted but couldn't operate 24/7 now: → Hermes runs the business logic (workflows, memory, skills, cron, sub-agents) → Stripe runs the financial layer (Link CLI for spending, Stripe API for receiving) → NemoClaw runs the trust layer (sandbox, policies, private routing) → VPS keeps everything always on → Telegram keeps you in the loop TYPES OF BUSINESSES THIS ENABLES: → autonomous software factory (customer request → build → deploy → payment link) → content agency (brief → research → draft → deliver → bill) → lead generation service (scrape → qualify → outreach → book calls) → SaaS monitoring and maintenance (detect issues → fix → deploy → report) → e-commerce operations (inventory → pricing → fulfillment → support) each one: Hermes profiles handle the workflows. Stripe handles the payments (in and out). NemoClaw handles the security. you handle the strategy. THE HACKATHON: Hermes Agent Accelerated Business Hackathon with Nvidia and Stripe. cash prizes + Stripe credits + Nvidia DGX Spark. ends June 30. the goal: build agents that earn, spend, and run real operations autonomously. link in the Nous Research Discord. full Hermes architecture deep-dive in the article 👇

YanXbt

37,709 Aufrufe • vor 3 Monaten

Tried out stripe projects this week! built a customer support bot with hermes from Nous Research + supermemory. bot remembers every customer across sessions. the piece worth highlighting, Stripe projects ships a hermes skill that lets the agent auto-provision supermemory itself. ask hermes to build the bot, it runs stripe projects add supermemory/memory. stripe creates the supermemory account, syncs the api key to .env, and bills it on your stripe invoice. and supermemory is one of 30+ providers. databases ( Neon Postgres, Supabase), hosting ( Vercel , Cloudflare), auth ( Clerk), search ( Exa), analytics ( PostHog). one CLI for the whole stack.
2:59

Tried out stripe projects this week! built a customer support bot with hermes from Nous Research + supermemory. bot remembers every customer across sessions. the piece worth highlighting, Stripe projects ships a hermes skill that lets the agent auto-provision supermemory itself. ask hermes to build the bot, it runs stripe projects add supermemory/memory. stripe creates the supermemory account, syncs the api key to .env, and bills it on your stripe invoice. and supermemory is one of 30+ providers. databases ( Neon Postgres, Supabase), hosting ( Vercel , Cloudflare), auth ( Clerk), search ( Exa), analytics ( PostHog). one CLI for the whole stack.

Muskan Jain

20,335 Aufrufe • vor 3 Monaten

NVIDIA JUST FEATURED HERMES AGENT AT COMPUTEX 2026. Hermes is integrating with NVIDIA OpenShell and Microsoft security primitives for secure on-device agents on Windows. Dillon Rolnick, CEO of Nous Research: "RTX Spark and NVIDIA OpenShell give Hermes users a powerful and secure environment for agents to run and work alongside you. You realize you're buying a full-fledged assistant, not a typical laptop." RTX Spark specs: → 1 petaflop AI performance → 20-core Grace CPU (built with MediaTek) → Blackwell GPU, 6,144 CUDA cores → 5th gen Tensor Cores with FP4 precision → up to 128GB LPDDR5X unified memory, 300 GB/s → NVLink C2C chip-to-chip interconnect → runs 120B parameter LLMs locally → up to 1M token context window on device → 2x inference speed via multi-token prediction RTX Spark devices ship Fall 2026 from ASUS, Dell, HP, Lenovo, Microsoft Surface, MSI. full NVIDIA press release in the comments. full Hermes setup guide in the article 👇
2:28

NVIDIA JUST FEATURED HERMES AGENT AT COMPUTEX 2026. Hermes is integrating with NVIDIA OpenShell and Microsoft security primitives for secure on-device agents on Windows. Dillon Rolnick, CEO of Nous Research: "RTX Spark and NVIDIA OpenShell give Hermes users a powerful and secure environment for agents to run and work alongside you. You realize you're buying a full-fledged assistant, not a typical laptop." RTX Spark specs: → 1 petaflop AI performance → 20-core Grace CPU (built with MediaTek) → Blackwell GPU, 6,144 CUDA cores → 5th gen Tensor Cores with FP4 precision → up to 128GB LPDDR5X unified memory, 300 GB/s → NVLink C2C chip-to-chip interconnect → runs 120B parameter LLMs locally → up to 1M token context window on device → 2x inference speed via multi-token prediction RTX Spark devices ship Fall 2026 from ASUS, Dell, HP, Lenovo, Microsoft Surface, MSI. full NVIDIA press release in the comments. full Hermes setup guide in the article 👇

YanXbt

45,924 Aufrufe • vor 4 Monaten

Your agent got the right answer. How much work did it take to get there? We worked with Nous Research/Teknium 🪽 on a hands-on walkthrough of NVIDIA NeMo Relay to collect traces for Hermes Agent. Run two example scenarios, follow the agent’s calls and retries, and see the full trace in Arize Phoenix. The blog also looks at how Nous used traces and task results to evaluate fixes across repeated runs. TechBlog: 📽️ by our own pico:
3:50

Your agent got the right answer. How much work did it take to get there? We worked with Nous Research/Teknium 🪽 on a hands-on walkthrough of NVIDIA NeMo Relay to collect traces for Hermes Agent. Run two example scenarios, follow the agent’s calls and retries, and see the full trace in Arize Phoenix. The blog also looks at how Nous used traces and task results to evaluate fixes across repeated runs. TechBlog: 📽️ by our own pico:

NVIDIA AI

86,287 Aufrufe • vor 13 Tagen

FLUX 3 Preview is now publicly available, only on Hermes Agent and free on all Nous Portal paid subs for the next 48 hours. Create a short film with it tagging Nous Research and Black Forest Labs - the 3 best entrants by 7PM PT on August 1st will receive: 1st place: 1 year of free FLUX 3 generation (20/day) + $2,000 Portal credits + Nous hoodie 2nd place: $1,000 credits + hoodie 3rd place: $500 credits + hoodie First 100 new signups using code L1YSMYDB get a free month of Nous Portal Plus with full video gen access. First 25 upgrades using code KEQHYO3X get $20 off. > hermes update
0:35

FLUX 3 Preview is now publicly available, only on Hermes Agent and free on all Nous Portal paid subs for the next 48 hours. Create a short film with it tagging Nous Research and Black Forest Labs - the 3 best entrants by 7PM PT on August 1st will receive: 1st place: 1 year of free FLUX 3 generation (20/day) + $2,000 Portal credits + Nous hoodie 2nd place: $1,000 credits + hoodie 3rd place: $500 credits + hoodie First 100 new signups using code L1YSMYDB get a free month of Nous Portal Plus with full video gen access. First 25 upgrades using code KEQHYO3X get $20 off. > hermes update

Nous Research

1,215,649 Aufrufe • vor 2 Monaten

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.
1:24

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

kwindla

274,932 Aufrufe • vor 9 Monaten

.NVIDIA AI kindly sent me a DGX Spark! As soon as I got back from SF, I unboxed it and wanted to share a first look with you. It measures just 15 × 15 × 5.05 cm and weighs 1.2 kg. Inside: • NVIDIA GB10 Grace Blackwell Superchip • 128 GB of unified memory shared by the CPU and GPU • Up to 1 petaflop of theoretical AI compute at FP4 precision with sparsity According to NVIDIA, this little machine can run models with up to 200 billion parameters locally with suitable quantization, and fine-tune models with up to 70 billion parameters using memory-efficient methods such as QLoRA. You can use it to fine-tune models on your own data, customize image generation, and build AI assistants that run locally. I’m looking forward to trying some of those workflows myself. Thanks again to the NVIDIA team for sending this over (NVIDIA RTX Spark)! Once I’m back home, I’ll record some hands-on demos of interesting use cases and share what I learn with you.
3:04

.NVIDIA AI kindly sent me a DGX Spark! As soon as I got back from SF, I unboxed it and wanted to share a first look with you. It measures just 15 × 15 × 5.05 cm and weighs 1.2 kg. Inside: • NVIDIA GB10 Grace Blackwell Superchip • 128 GB of unified memory shared by the CPU and GPU • Up to 1 petaflop of theoretical AI compute at FP4 precision with sparsity According to NVIDIA, this little machine can run models with up to 200 billion parameters locally with suitable quantization, and fine-tune models with up to 70 billion parameters using memory-efficient methods such as QLoRA. You can use it to fine-tune models on your own data, customize image generation, and build AI assistants that run locally. I’m looking forward to trying some of those workflows myself. Thanks again to the NVIDIA team for sending this over (NVIDIA RTX Spark)! Once I’m back home, I’ll record some hands-on demos of interesting use cases and share what I learn with you.

Chubby♨️

130,502 Aufrufe • vor 21 Tagen

Voice agents still don’t understand who’s speaking to them. That’s a huge gap compared with humans, hidden by all the “phone-call” demos. But that changes today! NVIDIA is open-sourcing Nemotron 3 Diarization: a model that can reliably track speakers in live conversations, under a commercial-friendly license! In my tests, the quality is really good with one-second speech chunks. So we can use it for voice agents! I tested it with Reachy Mini and speech-to-speech running on a DGX Spark. It’s super fun to see the robot notice a new voice, ask for a name, and remember it. The model has day-zero integration with Transformers! Kudos to the NVIDIA team for shipping useful tools for the whole community!
0:33

Voice agents still don’t understand who’s speaking to them. That’s a huge gap compared with humans, hidden by all the “phone-call” demos. But that changes today! NVIDIA is open-sourcing Nemotron 3 Diarization: a model that can reliably track speakers in live conversations, under a commercial-friendly license! In my tests, the quality is really good with one-second speech chunks. So we can use it for voice agents! I tested it with Reachy Mini and speech-to-speech running on a DGX Spark. It’s super fun to see the robot notice a new voice, ask for a name, and remember it. The model has day-zero integration with Transformers! Kudos to the NVIDIA team for shipping useful tools for the whole community!

Andi Marafioti

78,540 Aufrufe • vor 20 Tagen

NVIDIA JUST SHOWED HOW A $4,699 BOX CAN KILL A $200 MONTHLY AI BILL AND RUN 200B MODELS FROM YOUR DESK. 00:02 NVIDIA delivers the DGX Spark to developers, researchers, and AI teams, turning what used to require rented datacenter GPUs into a box small enough to hold in one hand. inside is 128GB of unified memory, 4TB of storage, and up to 1 PFLOP of AI compute, enough to run 70B models comfortably and push into the 200B class locally. that means no per-token API bill, no files leaving your machine, and no waiting for someone else’s server every time an agent reads documents, writes code, or runs an automation. two DGX Sparks can even be linked together for models around 400B parameters, while a single unit costs roughly $4,000 to $4,700 instead of renting multi-GPU cloud infrastructure every month. the full local AI ladder starts at $0 with the computer you already own, but NVIDIA just showed what the final rung looks like: a personal AI supercomputer sitting directly on your desk.
0:24

NVIDIA JUST SHOWED HOW A $4,699 BOX CAN KILL A $200 MONTHLY AI BILL AND RUN 200B MODELS FROM YOUR DESK. 00:02 NVIDIA delivers the DGX Spark to developers, researchers, and AI teams, turning what used to require rented datacenter GPUs into a box small enough to hold in one hand. inside is 128GB of unified memory, 4TB of storage, and up to 1 PFLOP of AI compute, enough to run 70B models comfortably and push into the 200B class locally. that means no per-token API bill, no files leaving your machine, and no waiting for someone else’s server every time an agent reads documents, writes code, or runs an automation. two DGX Sparks can even be linked together for models around 400B parameters, while a single unit costs roughly $4,000 to $4,700 instead of renting multi-GPU cloud infrastructure every month. the full local AI ladder starts at $0 with the computer you already own, but NVIDIA just showed what the final rung looks like: a personal AI supercomputer sitting directly on your desk.

Gipp 🦅

11,334 Aufrufe • vor 2 Monaten

NVIDIA is giving away free access to 140+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3-Ultra-550B-A55B, Kimi K2.7, and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free with this many models in one place, it is also the easiest way to test which one actually fits your agent before you commit to a paid provider
0:29

NVIDIA is giving away free access to 140+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3-Ultra-550B-A55B, Kimi K2.7, and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free with this many models in one place, it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

Mr. Buzzoni

121,850 Aufrufe • vor 3 Monaten

Stripe’s strategy is to “win all the startups and then win them again.” I had a great time talking with Will Gaybrick. Will has held a broad seat at Stripe for more than a decade, joining as CFO in 2015, and today leading Technology and Business. This makes him the right person to explain how Stripe went from a simple payments API to a platform with ~25-30 banner products and 288 launches at its most recent Sessions event. Here’s what their strategy looks like: -Companies like DoorDash and Instacart started on Stripe when they were tiny and pulled the company upmarket as they expanded. -The fastest startups act as canaries for new product opportunities. Cursor surfaced a burgeoning problem of AI free-trial and token abuse; so Stripe built a token detection pipeline with the team in a weekend, and the resulting network now helps companies on Stripe’s platform block thousands of fraudulent trials daily. -Stripe keeps expanding the number of needs it serves inside each company, from Billing, Radar, and Tax to Managed Payments, Treasury, and stablecoin infrastructure. There is a large and timely lesson from Stripe which I strongly agree with: using AI solely to reduce cost is essentially going short your own company. Instead, companies should be using AI (and the tailwinds it creates) to ship more, serve users better, and create their next product line. And as Stripe continues to invest in agentic commerce, the company can move from processing a transaction to orchestrating the entire economic loop around it. The line between tokens and dollars is already blurring, and Stripe’s next mandate is to make moving between them as seamless and safe as moving between dollars and euros. A fun conversation about what it takes to build the next Stripe inside Stripe. a16z
2:27

Stripe’s strategy is to “win all the startups and then win them again.” I had a great time talking with Will Gaybrick. Will has held a broad seat at Stripe for more than a decade, joining as CFO in 2015, and today leading Technology and Business. This makes him the right person to explain how Stripe went from a simple payments API to a platform with ~25-30 banner products and 288 launches at its most recent Sessions event. Here’s what their strategy looks like: -Companies like DoorDash and Instacart started on Stripe when they were tiny and pulled the company upmarket as they expanded. -The fastest startups act as canaries for new product opportunities. Cursor surfaced a burgeoning problem of AI free-trial and token abuse; so Stripe built a token detection pipeline with the team in a weekend, and the resulting network now helps companies on Stripe’s platform block thousands of fraudulent trials daily. -Stripe keeps expanding the number of needs it serves inside each company, from Billing, Radar, and Tax to Managed Payments, Treasury, and stablecoin infrastructure. There is a large and timely lesson from Stripe which I strongly agree with: using AI solely to reduce cost is essentially going short your own company. Instead, companies should be using AI (and the tailwinds it creates) to ship more, serve users better, and create their next product line. And as Stripe continues to invest in agentic commerce, the company can move from processing a transaction to orchestrating the entire economic loop around it. The line between tokens and dollars is already blurring, and Stripe’s next mandate is to make moving between them as seamless and safe as moving between dollars and euros. A fun conversation about what it takes to build the next Stripe inside Stripe. a16z

David George

69,249 Aufrufe • vor 1 Monat

NVIDIA AI director Ali Golshan reveals how 3 agents can route around a policy that no single agent is allowed to break by splitting the forbidden task between them: "If you write a policy that says, 'My agent should not have access to GitHub and to Facebook at the same time, because I'm worried it's gonna go copy my code and paste it on some message board,' that's very acceptable." "The problem we started to see is it's not the behavior of one agent that's the complex part, it's fleets of agents working together that creates complexity." "An agent spawns two sub-agents, with one sub-agent that can only read from GitHub, but the ability to tunnel through the network, talk to an agent that can write to a post. Now you have three agents that combined exceed your global policies." "The agents don't really process the intent or goodwill of your policy. They just see it as very specific binary." NVIDIA
1:42

NVIDIA AI director Ali Golshan reveals how 3 agents can route around a policy that no single agent is allowed to break by splitting the forbidden task between them: "If you write a policy that says, 'My agent should not have access to GitHub and to Facebook at the same time, because I'm worried it's gonna go copy my code and paste it on some message board,' that's very acceptable." "The problem we started to see is it's not the behavior of one agent that's the complex part, it's fleets of agents working together that creates complexity." "An agent spawns two sub-agents, with one sub-agent that can only read from GitHub, but the ability to tunnel through the network, talk to an agent that can write to a post. Now you have three agents that combined exceed your global policies." "The agents don't really process the intent or goodwill of your policy. They just see it as very specific binary." NVIDIA

MTS

11,721 Aufrufe • vor 13 Tagen

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:
0:32

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

Tom Greenwald

49,258 Aufrufe • vor 25 Tagen

🚀 Hermes Browser Automation Guide (FREE) Use your own browser with Hermes Agent for web automation—no complicated setup. 1. Get an NVIDIA API key (skip if you already have one) 🔗 2. Install Kimi WebBridge 🔗 3. Install the skills bundle Windows iex (irm | Out-String) macOS / Linux curl -fsSL | bash 4. Restart Hermes Close the app completely and reopen it. 5. Configure memory In Hermes, type: Set up my memory 6. (Optional) Explore your new skills Type: "Tell me about the skills you just set up and what they do" ⭐ GitHub: (a star would be appreciated) If you run into any issues, check out the video below or leave a comment. 💡 Pro Tip Use: /interactive-prompt-analyzer + /deep-web-research + your prompt It analyses your prompt, searches the web, and produces a significantly more detailed, research-backed prompt—great for content creation, coding, and research.
2:56

🚀 Hermes Browser Automation Guide (FREE) Use your own browser with Hermes Agent for web automation—no complicated setup. 1. Get an NVIDIA API key (skip if you already have one) 🔗 2. Install Kimi WebBridge 🔗 3. Install the skills bundle Windows iex (irm | Out-String) macOS / Linux curl -fsSL | bash 4. Restart Hermes Close the app completely and reopen it. 5. Configure memory In Hermes, type: Set up my memory 6. (Optional) Explore your new skills Type: "Tell me about the skills you just set up and what they do" ⭐ GitHub: (a star would be appreciated) If you run into any issues, check out the video below or leave a comment. 💡 Pro Tip Use: /interactive-prompt-analyzer + /deep-web-research + your prompt It analyses your prompt, searches the web, and produces a significantly more detailed, research-backed prompt—great for content creation, coding, and research.

Sloemo

19,175 Aufrufe • vor 2 Monaten

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.
7:37

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

Santiago

21,079 Aufrufe • vor 2 Monaten

J-Cal’s framework for how to be "AI first". It’s not just a slogan 1. Every task… Ask AI first. “How can I do this better.” 2. Every repeated task… Let your agents take care of it so you can do MORE. 3. Give the agent your last 10 outputs, let it score them, run it daily, and do deep-research weekly on what the best are doing differently.
3:02

J-Cal’s framework for how to be "AI first". It’s not just a slogan 1. Every task… Ask AI first. “How can I do this better.” 2. Every repeated task… Let your agents take care of it so you can do MORE. 3. Give the agent your last 10 outputs, let it score them, run it daily, and do deep-research weekly on what the best are doing differently.

This Week in Startups

45,723 Aufrufe • vor 5 Monaten

NVIDIA is giving away free access to 140+ AI models for a full year > a lot of people building agents are paying $50-200/month just for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3.5-lightning-30b-a3b, Muse-glimmer-30b from Meta and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year a free key changes what you can afford to run: > one prompt costs nothing either way > a loop firing 300 agents every week is where the bill shows up > for a year that bill is zero while everyone is paying for API access, this is sitting there for free with this many models in one place it is also the easiest way to test which one actually fits your agent before you commit to a paid provider
0:29

NVIDIA is giving away free access to 140+ AI models for a full year > a lot of people building agents are paying $50-200/month just for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3.5-lightning-30b-a3b, Muse-glimmer-30b from Meta and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year a free key changes what you can afford to run: > one prompt costs nothing either way > a loop firing 300 agents every week is where the bill shows up > for a year that bill is zero while everyone is paying for API access, this is sitting there for free with this many models in one place it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

Annatar.md

208,474 Aufrufe • vor 1 Monat