Загрузка видео...

Не удалось загрузить видео

На главную

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...

NVIDIAAI's profile picture

NVIDIA AI

347,777 subscribers

86,287 просмотров • 13 дней назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 6

Фото профиля Hermes Agent Tips
Hermes Agent Tips13 дней назад

@NousResearch @Teknium such an amazing thing to watch this collab between @NVIDIAAI x @NousResearch creating walkthrough and much more!

Фото профиля Viber · fireply.ai
Viber · fireply.ai13 дней назад

@NousResearch @Teknium two example scenarios and a trace viewer, i'd have that wired up before lunch

Фото профиля not sofie
not sofie13 дней назад

@NousResearch @Teknium Trace collection answers "how much work" with step counts, not whether those steps were necessary. Retries can mask a brittle prompt. Does the walkthrough show how to tell wasted calls from genuine recovery?

Фото профиля Cyber Viking
Cyber Viking13 дней назад

@NousResearch @Teknium Please tell me Hermes Agent made this video

Фото профиля The SI Therapist
The SI Therapist13 дней назад

@NousResearch @Teknium Entre le prompt et la trace, on compte souvent dix minutes de réglages subtils pour ce succès instantané

Фото профиля BullBear.News
BullBear.News13 дней назад

@NousResearch @Teknium tracing retry loops is where 90 percent of agent debugging goes

Похожие видео

Hermes Agent 1-Click Launcher Install, launch and manage the entire hermes agent/gateway stack with 1click. This 52 sec video goes from install to setup to the first chat with hermes. Works on all OS. No need for WSL--runs on vanilla windows! cc: Teknium 🪽 Nous Research
0:52

Hermes Agent 1-Click Launcher Install, launch and manage the entire hermes agent/gateway stack with 1click. This 52 sec video goes from install to setup to the first chat with hermes. Works on all OS. No need for WSL--runs on vanilla windows! cc: Teknium 🪽 Nous Research

cocktail peanut

74,525 просмотров • 6 месяцев назад

My Hermes Agent has a newspaper for me now. 🗞️🚀 The Hermes Agent Times: four pages covering my day, my agents’ work, ideas worth exploring, and life beyond the screen. 🚀Next: a morning printout and an Obsidian archive connecting each day’s ideas. Would you read a newspaper made by your own agent? # Give below prompt to your Hermes agent👇 Teknium 🪽 Nous Research
0:38

My Hermes Agent has a newspaper for me now. 🗞️🚀 The Hermes Agent Times: four pages covering my day, my agents’ work, ideas worth exploring, and life beyond the screen. 🚀Next: a morning printout and an Obsidian archive connecting each day’s ideas. Would you read a newspaper made by your own agent? # Give below prompt to your Hermes agent👇 Teknium 🪽 Nous Research

Hermes Agent Super-Intel

46,378 просмотров • 1 месяц назад

Hermes Agent by Nous Research natively integrates with Give Hermes any URL and find a skill for it in our catalog, or create your own. Watch it find the NASA picture of the day for me.
0:29

Hermes Agent by Nous Research natively integrates with Give Hermes any URL and find a skill for it in our catalog, or create your own. Watch it find the NASA picture of the day for me.

Kyle Jeong

92,078 просмотров • 4 месяцев назад

ICYMI: Hermes can search and read the web for $0. TinyFish is now a plugin in the Nous Research Hermes Agent. We pointed ours at the most boring job in the building: an Excel sheet full of empty cells. TinyFish searched and fetched information for all the rows and handed back clean results to Hermes Agent to fill in the spreadsheet.
0:35

ICYMI: Hermes can search and read the web for $0. TinyFish is now a plugin in the Nous Research Hermes Agent. We pointed ours at the most boring job in the building: an Excel sheet full of empty cells. TinyFish searched and fetched information for all the rows and handed back clean results to Hermes Agent to fill in the spreadsheet.

TinyFish

333,567 просмотров • 9 часов назад

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 intelligently with access to their extensive agent skills. The new Stripe Skills for Hermes let your agent buy what it needs, provision its own SaaS, and pay for the services it uses. We want to see what kind of business tooling you can build on top of this foundation, whether it’s a fully automated company or a framework to accelerate enterprise functions. Prizes: 1st — $10,000 cash + NVIDIA DGX Spark + $5,000 Stripe Credits 2nd — $5,000 cash + NVIDIA DGX Spark + $3,000 Stripe Credits 3rd — $2,500 cash + NVIDIA DGX Spark + $1,000 Stripe Credits To enter: 1) Tweet a 1-3 minute demo video tagging Nous Research with a short writeup 2) Drop the link in the submissions channel: 3) Fill out the submission form: Judged by Nous Research, NVIDIA, and Stripe on usefulness, viability, and presentation. Submissions due EOD Tuesday, June 30.
1:06

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 intelligently with access to their extensive agent skills. The new Stripe Skills for Hermes let your agent buy what it needs, provision its own SaaS, and pay for the services it uses. We want to see what kind of business tooling you can build on top of this foundation, whether it’s a fully automated company or a framework to accelerate enterprise functions. Prizes: 1st — $10,000 cash + NVIDIA DGX Spark + $5,000 Stripe Credits 2nd — $5,000 cash + NVIDIA DGX Spark + $3,000 Stripe Credits 3rd — $2,500 cash + NVIDIA DGX Spark + $1,000 Stripe Credits To enter: 1) Tweet a 1-3 minute demo video tagging Nous Research with a short writeup 2) Drop the link in the submissions channel: 3) Fill out the submission form: Judged by Nous Research, NVIDIA, and Stripe on usefulness, viability, and presentation. Submissions due EOD Tuesday, June 30.

Nous Research

1,892,499 просмотров • 3 месяцев назад

Ever wonder what it looks like inside the Buzz hive with Fable, Sol, and Hermes running at the same time? So did I, so I asked Deepseek v4 Flash and Flux 3 to show me. Thanks Teknium 🪽 Nous Research Black Forest Labs and jack - we live in amazing times.
0:53

Ever wonder what it looks like inside the Buzz hive with Fable, Sol, and Hermes running at the same time? So did I, so I asked Deepseek v4 Flash and Flux 3 to show me. Thanks Teknium 🪽 Nous Research Black Forest Labs and jack - we live in amazing times.

Leo Laporte (twit.social/@leo)

16,395 просмотров • 2 месяцев назад

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!
12:40

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!

Sebastian Schöner

13,130 просмотров • 5 месяцев назад

About a year ago, we launched the Agent-to-Agent protocol because AI agents shouldn’t work in silos. Today, developers are using A2A to coordinate specialized agents across enterprise data systems, commerce workflows, DevOps environments, and scientific research. FoldRun is one example, simplifying petabyte-scale protein modeling through agent-to-agent collaboration. Learn how to build with it in the blog:
1:04

About a year ago, we launched the Agent-to-Agent protocol because AI agents shouldn’t work in silos. Today, developers are using A2A to coordinate specialized agents across enterprise data systems, commerce workflows, DevOps environments, and scientific research. FoldRun is one example, simplifying petabyte-scale protein modeling through agent-to-agent collaboration. Learn how to build with it in the blog:

Google for Developers

35,497 просмотров • 3 месяцев назад

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.
3:16

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.

Weights & Biases

269,153 просмотров • 7 месяцев назад

So, I decided to put together few video guides on how to install Spark Ai agent. This is how I did it, and it’s the most easiest method, I know you don’t like stress 🤷🏽‍♂️same here. Follow the video thread on how to get your Spark agent ready for the bug bounty. 1. Installing Spark with Hermes Agent.
2:44

So, I decided to put together few video guides on how to install Spark Ai agent. This is how I did it, and it’s the most easiest method, I know you don’t like stress 🤷🏽‍♂️same here. Follow the video thread on how to get your Spark agent ready for the bug bounty. 1. Installing Spark with Hermes Agent.

latiblack.base.eth

10,831 просмотров • 4 месяцев назад

Just got back to it tonight and I got the rest of those animations all made up for the grab attack! I kept all the traces on here so we can see its attack range, and how its grab traces work too. So next I think it'll be time to get a death scene going for this guy!
0:28

Just got back to it tonight and I got the rest of those animations all made up for the grab attack! I kept all the traces on here so we can see its attack range, and how its grab traces work too. So next I think it'll be time to get a death scene going for this guy!

DRIG

11,846 просмотров • 1 год назад

Launching Notebooks on Agent Two: Day 5 of 12 Days of Agent Two. With notebooks, you have complete control over the work you do with individual models. invideo's got ALL the state-of-the-art models across images, video, sound, music, creative tools. So essentially you can work with the Agent in free-flow, switch to the notebook for hands-on granular work on particular gens (both creating and editing gens), and switch back to the Agent as and when you like with no loss of context or output. This is the full range of how you can do creative work. And that's why Agent Two is the frontier intelligence agent out there. 4x faster, at half the price.
3:02

Launching Notebooks on Agent Two: Day 5 of 12 Days of Agent Two. With notebooks, you have complete control over the work you do with individual models. invideo's got ALL the state-of-the-art models across images, video, sound, music, creative tools. So essentially you can work with the Agent in free-flow, switch to the notebook for hands-on granular work on particular gens (both creating and editing gens), and switch back to the Agent as and when you like with no loss of context or output. This is the full range of how you can do creative work. And that's why Agent Two is the frontier intelligence agent out there. 4x faster, at half the price.

Invideo

1,092,598 просмотров • 2 месяцев назад

We tried OWL with 𝐆𝐞𝐦𝐢𝐧𝐢 𝟐.𝟓 𝐏𝐫𝐨 (the results were seriously impressive) We gave the agent a task: "Research Gemini 2.5 Pro, get its benchmark scores, write Python code to plot them, and run it." It did everything on its own: ✔️ Collected benchmark data ✔️ Wrote clean python code ✔️ Saved both the chart + code locally No manual steps. Just full-on autonomous execution. This is how agent workflows should feel in 2025. You can try it, check the code, or run your own workflows:
1:05

We tried OWL with 𝐆𝐞𝐦𝐢𝐧𝐢 𝟐.𝟓 𝐏𝐫𝐨 (the results were seriously impressive) We gave the agent a task: "Research Gemini 2.5 Pro, get its benchmark scores, write Python code to plot them, and run it." It did everything on its own: ✔️ Collected benchmark data ✔️ Wrote clean python code ✔️ Saved both the chart + code locally No manual steps. Just full-on autonomous execution. This is how agent workflows should feel in 2025. You can try it, check the code, or run your own workflows:

CAMEL-AI.org

20,256 просмотров • 1 год назад

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by Modiqo Inc to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install →
1:27

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by Modiqo Inc to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install →

chetan conikee

469,486 просмотров • 4 месяцев назад

I didn't touch TouchDesigner myself. Hermes agent learned it from scratch and built this: → navigated my desktop with computer use → figured out how to connect to TouchDesigner → read my reference images → iterated on the art with me in a self-learning loop → then saved what it learned as a reusable skill for the next image all powered by MiniMax (official) M3 × Hermes Desktop Agent Nous Research Here's a full breakdown 📽️
2:45

I didn't touch TouchDesigner myself. Hermes agent learned it from scratch and built this: → navigated my desktop with computer use → figured out how to connect to TouchDesigner → read my reference images → iterated on the art with me in a self-learning loop → then saved what it learned as a reusable skill for the next image all powered by MiniMax (official) M3 × Hermes Desktop Agent Nous Research Here's a full breakdown 📽️

amber shen

121,097 просмотров • 4 месяцев назад

Your AI agent has your API keys. A poisoned document tells it to curl your secrets to an attacker's server. This is credential exfiltration, and it's the #1 risk in agentic AI right now. The fix is removing the secret from the agent entirely. Agent Vault sits between your agent and the APIs it calls. The agent gets dummy credentials, and Agent Vault swaps in the real ones at the network layer. The agent never sees your keys. We just dropped a full video + guide on connecting Hermes Agent to Agent Vault on a VPS!
34:40

Your AI agent has your API keys. A poisoned document tells it to curl your secrets to an attacker's server. This is credential exfiltration, and it's the #1 risk in agentic AI right now. The fix is removing the secret from the agent entirely. Agent Vault sits between your agent and the APIs it calls. The agent gets dummy credentials, and Agent Vault swaps in the real ones at the network layer. The agent never sees your keys. We just dropped a full video + guide on connecting Hermes Agent to Agent Vault on a VPS!

Infisical

86,483 просмотров • 5 месяцев назад

Looking how to participate in the Solana hackathon? Here's an example of how to create a trading bot on solana very easily and quickly just by messaging your agent through telegram! Get your agent set up and create something for the hackathon 👩‍💻
0:33

Looking how to participate in the Solana hackathon? Here's an example of how to create a trading bot on solana very easily and quickly just by messaging your agent through telegram! Get your agent set up and create something for the hackathon 👩‍💻

brimigs

30,311 просмотров • 8 месяцев назад

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:
2:07

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

Andrew Ng

126,738 просмотров • 1 год назад

Your research needs more than an answer that just looks right. You need a method you can repeat, inspect, and trust. We compared SciSpace and Claude Science across three questions that matter to your research: 1⃣Can you repeat the workflow? 2⃣Who controls the knowledge you create? 3⃣How efficiently is AI used for your task? See how the two approaches differ, and which one better aligns with the way you work.
2:27

Your research needs more than an answer that just looks right. You need a method you can repeat, inspect, and trust. We compared SciSpace and Claude Science across three questions that matter to your research: 1⃣Can you repeat the workflow? 2⃣Who controls the knowledge you create? 3⃣How efficiently is AI used for your task? See how the two approaches differ, and which one better aligns with the way you work.

SciSpace

502,460 просмотров • 2 месяцев назад

Launching Workflows on Agent Two. Day 10 of 12 Days of Agent Two. Instead of briefing the agent through every step yourself, workflows take you on a guided run. You answer a few questions, upload some references, pick between options, and come out the other side with the job done. We're launching with 9 workflows across filmmaking and marketing, and you can also build your own and reuse them across any project. Tell us in the comments what workflow you want us to build next. The most liked one gets made. Agent Two is frontier intelligence for creative work. 4x faster, at half the price.
5:26

Launching Workflows on Agent Two. Day 10 of 12 Days of Agent Two. Instead of briefing the agent through every step yourself, workflows take you on a guided run. You answer a few questions, upload some references, pick between options, and come out the other side with the job done. We're launching with 9 workflows across filmmaking and marketing, and you can also build your own and reuse them across any project. Tell us in the comments what workflow you want us to build next. The most liked one gets made. Agent Two is frontier intelligence for creative work. 4x faster, at half the price.

Invideo

3,596,606 просмотров • 2 месяцев назад