Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🎉Introducing PyFlue: The Python-Native Agent Harness Framework.🧰 💡Flue for Python: Fred K. Schott fks CEO of HTML has launched Flue: The Agent Harness Framework for TypeScript. It brings programmable harness right into your agents rather than DIY plumbing. Python ecosystem already has 🦾 powerful AI/ML tools and frameworks and... research initiatives but most frameworks asked users to build your own harness. Superagentic AI bringing this concept of Flue to Python 🐍 ecosystem. Here is PyFlue even even better 🤖 Agent = Model 💻 + Harness 🧰 + Memory 🧠 Almost all the feature of Flue plugged with LangChain Deepagents harness built by Harrison Chase and team Viv Sydney Runkle and more coming soon. 👉 Stop building agent loops, start using a harness. 💻 Try PyFlue Now : ⭐️ GitHub: 📚Docs: 📙 Blog Post: #HarnessEngineering #AgentHarnessesshow more

Shashi 🇬🇧🇺🇸

2,711 subscribers

69,688 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

this is huge news from Cursor, they've pulled of the impossible and turned their ai-wrapper into a in-destructible moat sam altman literally called it cursor's ai agent harness is available for anyone to build on, which means ai models are now a commodity > 1-time install and now anyone can run cursor's agent locally or via cloud. use any model (e.g. gpt 5.5) but with the added cursor harness that makes it 10X better. > its so good that 3 of cursors biggest competitors are embedding it into their products. > now cursor DOESN'T DEPEND on anthropic or openai. their own model (composer 2) competes directly! yesterday sam altman said the ai model and harness are one and the same and today cursor turned their harness into a self-owned moat fucking masterclass (coming from a former cursor / ai wrapper hater)

this is huge news from Cursor, they've pulled of the impossible and turned their ai-wrapper into a in-destructible moat sam altman literally called it cursor's ai agent harness is available for anyone to build on, which means ai models are now a commodity > 1-time install and now anyone can run cursor's agent locally or via cloud. use any model (e.g. gpt 5.5) but with the added cursor harness that makes it 10X better. > its so good that 3 of cursors biggest competitors are embedding it into their products. > now cursor DOESN'T DEPEND on anthropic or openai. their own model (composer 2) competes directly! yesterday sam altman said the ai model and harness are one and the same and today cursor turned their harness into a self-owned moat fucking masterclass (coming from a former cursor / ai wrapper hater)

Ejaaz

949,859 views • 2 months ago

The entire AI industry is racing to build the smartest model. Satya Nadella just admitted that is not where the money is. The model is not the product. The harness is. That is the exact line. And it changes what Microsoft is actually competing on. OpenAI, Anthropic, Google, xAI, Meta every frontier lab is pouring hundreds of billions into training compute, chasing the next capability jump. Each betting that raw model intelligence is the moat. Microsoft is doing the opposite. It is building the harness the orchestration layer that sits above the model, connecting it to tools, data, permissions, sub-agents, and enterprise workflows. And it is letting OpenAI, Anthropic, and MAI compete to plug into it. "You need the model. But the model is not the product. The harness is." So do the math on what a harness actually does. A raw model dropped into an enterprise answers questions. That is a chatbot. A harness turns that same model into an agent that reads the SharePoint, edits the ERP entry, pulls the GitHub PR, updates Salesforce, and files the Excel report with the right permissions, the right audit trail, and the right sub-agent for each sub-task. The model provides the intelligence. The harness converts intelligence into work. Now here's where it gets interesting. "Even the best model in the world will feel broken without a great harness. And an okay model with a great harness can feel like magic." If that is true, the enterprise buyer is not buying model quality. The enterprise buyer is buying the harness. Which means model quality becomes a commodity input over time, and harness quality becomes the sustainable moat. Compare that to the strategy the entire frontier lab industry is executing. Everyone else is chasing the numerator raw intelligence. Almost nobody at scale is racing to build the denominator the orchestration layer that determines whether that intelligence can actually be deployed profitably inside a real company. The frontier model race has a 10 to 20 percent chance of producing a single dominant winner. Nadella just told the industry he does not need to be that winner. If OpenAI wins, Microsoft wins. If Anthropic wins, Microsoft wins. If MAI wins, Microsoft wins. If someone Microsoft has never heard of trains a better model in 2027, Microsoft still wins. Because the compute they train on, the harness they get plugged into, the enterprise contracts they get delivered through, and the products they sit inside are all Microsoft. He is not building the best AI model. He is building the layer that the best AI model has to run on to make anyone money. I wonder which position looks more valuable in ten years.

The entire AI industry is racing to build the smartest model. Satya Nadella just admitted that is not where the money is. The model is not the product. The harness is. That is the exact line. And it changes what Microsoft is actually competing on. OpenAI, Anthropic, Google, xAI, Meta every frontier lab is pouring hundreds of billions into training compute, chasing the next capability jump. Each betting that raw model intelligence is the moat. Microsoft is doing the opposite. It is building the harness the orchestration layer that sits above the model, connecting it to tools, data, permissions, sub-agents, and enterprise workflows. And it is letting OpenAI, Anthropic, and MAI compete to plug into it. "You need the model. But the model is not the product. The harness is." So do the math on what a harness actually does. A raw model dropped into an enterprise answers questions. That is a chatbot. A harness turns that same model into an agent that reads the SharePoint, edits the ERP entry, pulls the GitHub PR, updates Salesforce, and files the Excel report with the right permissions, the right audit trail, and the right sub-agent for each sub-task. The model provides the intelligence. The harness converts intelligence into work. Now here's where it gets interesting. "Even the best model in the world will feel broken without a great harness. And an okay model with a great harness can feel like magic." If that is true, the enterprise buyer is not buying model quality. The enterprise buyer is buying the harness. Which means model quality becomes a commodity input over time, and harness quality becomes the sustainable moat. Compare that to the strategy the entire frontier lab industry is executing. Everyone else is chasing the numerator raw intelligence. Almost nobody at scale is racing to build the denominator the orchestration layer that determines whether that intelligence can actually be deployed profitably inside a real company. The frontier model race has a 10 to 20 percent chance of producing a single dominant winner. Nadella just told the industry he does not need to be that winner. If OpenAI wins, Microsoft wins. If Anthropic wins, Microsoft wins. If MAI wins, Microsoft wins. If someone Microsoft has never heard of trains a better model in 2027, Microsoft still wins. Because the compute they train on, the harness they get plugged into, the enterprise contracts they get delivered through, and the products they sit inside are all Microsoft. He is not building the best AI model. He is building the layer that the best AI model has to run on to make anyone money. I wonder which position looks more valuable in ten years.

Vikram M

21,463 views • 16 days ago

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,343 views • 1 year ago

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

LobeHub

185,173 views • 5 months ago

You need to try Hermes RIGHT NOW. OpenClaw was the breakthrough. Hermes feels like the evolution. Here’s why AI power users are quietly switching: • Hermes learns from you over time • It creates its own reusable skills • Memory stays curated instead of bloated • Agents improve every 10 turns automatically • It actually feels stable on day 30 The wildest part: Hermes agents build workflows from your behavior. One user asked their agent to configure Twingate once. The agent: → learned the process → created a reusable skill → stored it for future tasks → improved its own workflow automatically That’s not prompt engineering anymore. That’s agent evolution. Meanwhile most people are still babysitting broken OpenClaw setups and manually importing marketplace skills. Hermes took a different path: Less clutter. Less tweaking. More autonomy. And it’s working. It already flipped OpenClaw in OpenRouter token usage and became one of the fastest-growing AI repos on GitHub. The bigger shift: We’re entering the era where the model matters less than the harness around it. GPT-5.5, Grok, Qwen: They’re already powerful enough. The real edge now is: • memory systems • self-improvement loops • skill creation • agent orchestration Hermes understands that. Most people still think AI agents are glorified chatbots. The people using Hermes are building AI teammates.

You need to try Hermes RIGHT NOW. OpenClaw was the breakthrough. Hermes feels like the evolution. Here’s why AI power users are quietly switching: • Hermes learns from you over time • It creates its own reusable skills • Memory stays curated instead of bloated • Agents improve every 10 turns automatically • It actually feels stable on day 30 The wildest part: Hermes agents build workflows from your behavior. One user asked their agent to configure Twingate once. The agent: → learned the process → created a reusable skill → stored it for future tasks → improved its own workflow automatically That’s not prompt engineering anymore. That’s agent evolution. Meanwhile most people are still babysitting broken OpenClaw setups and manually importing marketplace skills. Hermes took a different path: Less clutter. Less tweaking. More autonomy. And it’s working. It already flipped OpenClaw in OpenRouter token usage and became one of the fastest-growing AI repos on GitHub. The bigger shift: We’re entering the era where the model matters less than the harness around it. GPT-5.5, Grok, Qwen: They’re already powerful enough. The real edge now is: • memory systems • self-improvement loops • skill creation • agent orchestration Hermes understands that. Most people still think AI agents are glorified chatbots. The people using Hermes are building AI teammates.

Dami-Defi

17,062 views • 1 month ago

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

Dan Shipper 📧

66,339 views • 2 months ago

Anthropic's Claude Ai Agents Team just Educated how to build production AI agents in under 30 mins. For Free. From the engineers who built the stack. CANCEL Your Weekend Plans, and Learn to Build AI Agents Today. Bookmark it. Watch it. Build your first production agent this weekend. $5,000/month. $7,000/month. $12,000/month. People are building agents for clients and charging $$$ as Beginners. You're still stuck in the thinking about AI phase. This video fixes that tonight. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward. ↓ Ivan Nardini runs Developer Relations for AI at Google Cloud. He just gave away the entire production agent stack in 30 minutes. This is the talk that separates people deploying AI agents that actually scale from people whose agents break the moment they leave localhost. Here's everything inside. I break down a production AI video like this every week. Follow Himanshu Kumar. ↓ The 4-part agent stack that actually scales. Most devs are duct-taping frameworks together and calling it an "AI agent." Ivan lays out the real stack: Agent Development Kit (ADK): open-source, code-first framework for building, evaluating, and deploying agents. Supports Claude models through Vertex AI directly. Model Context Protocol (MCP): lets your agent talk to any tool or data source with one standard. Vertex AI Agent Engine: managed platform for deploying, monitoring, and scaling agents in production. No DevOps headaches. Agent-to-Agent Protocol: open protocol so agents built on different frameworks can actually work together. This is the stack replacing every hacky agent setup in production right now. Full MCP + Claude breakdowns drop weekly on Himanshu Kumar. ↓ Building your first real agent. Ivan builds a birthday planner agent live. LLM Agent class. Name it. Define instructions. Pick the model. He uses Claude 3.7 Sonnet. You could use Opus 4.7 for better reasoning. Full agent built in minutes. Not weeks. Watch the build once and you'll never structure an agent the wrong way again. I post agent architectures people pay $500 courses to learn. Himanshu Kumar. ↓ Multi-agent systems without the chaos. Single agents are easy. Multi-agent systems are where 99% of builders fail. Ivan extends the birthday planner by: Adding a calendar service through MCP tools Creating an orchestrator agent to route requests between agents Handling state and context across agent handoffs This is production multi-agent architecture. Clean. Scalable. Debuggable. Most tutorials hand-wave this part. This one shows you every step. Multi-agent orchestration content drops weekly on Himanshu Kumar. ↓ Deployment without the DevOps nightmare. This is where most AI projects die. You build a cool agent locally. It works. You try to deploy it. Everything breaks. Vertex AI Agent Engine fixes this: Minimal code deployment Automatic monitoring of latency, CPU, and memory Built-in observability and logging No infrastructure setup needed You provide config and requirements. The platform handles the rest. This is how agents actually get to production. Deployment guides for Claude agents post every week. Himanshu Kumar. ↓ Agent-to-Agent Protocol: the future nobody's talking about. Most people don't know this exists yet. The A2A Protocol lets agents built in different frameworks communicate seamlessly. Your Claude agent. My LangChain agent. Someone else's CrewAI agent. All talking to each other. All solving parts of the same problem. All without custom integration code. This is the infrastructure layer of the coming AI economy. Getting in early on A2A Protocol is like getting in early on HTTP in 1995. A2A deep dive coming soon. Himanshu Kumar. ↓ 30 minutes from the team shipping this in production. You'll learn more from this than from 6 months of YouTube tutorials made by people who've never deployed an agent past localhost. People who watch this understand production AI agents at the architect level. People who skip it keep hacking together frameworks that break every time an API updates. Save the video. Watch it tonight. Build a real agent this weekend. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.

Anthropic's Claude Ai Agents Team just Educated how to build production AI agents in under 30 mins. For Free. From the engineers who built the stack. CANCEL Your Weekend Plans, and Learn to Build AI Agents Today. Bookmark it. Watch it. Build your first production agent this weekend. $5,000/month. $7,000/month. $12,000/month. People are building agents for clients and charging $$$ as Beginners. You're still stuck in the thinking about AI phase. This video fixes that tonight. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward. ↓ Ivan Nardini runs Developer Relations for AI at Google Cloud. He just gave away the entire production agent stack in 30 minutes. This is the talk that separates people deploying AI agents that actually scale from people whose agents break the moment they leave localhost. Here's everything inside. I break down a production AI video like this every week. Follow Himanshu Kumar. ↓ The 4-part agent stack that actually scales. Most devs are duct-taping frameworks together and calling it an "AI agent." Ivan lays out the real stack: Agent Development Kit (ADK): open-source, code-first framework for building, evaluating, and deploying agents. Supports Claude models through Vertex AI directly. Model Context Protocol (MCP): lets your agent talk to any tool or data source with one standard. Vertex AI Agent Engine: managed platform for deploying, monitoring, and scaling agents in production. No DevOps headaches. Agent-to-Agent Protocol: open protocol so agents built on different frameworks can actually work together. This is the stack replacing every hacky agent setup in production right now. Full MCP + Claude breakdowns drop weekly on Himanshu Kumar. ↓ Building your first real agent. Ivan builds a birthday planner agent live. LLM Agent class. Name it. Define instructions. Pick the model. He uses Claude 3.7 Sonnet. You could use Opus 4.7 for better reasoning. Full agent built in minutes. Not weeks. Watch the build once and you'll never structure an agent the wrong way again. I post agent architectures people pay $500 courses to learn. Himanshu Kumar. ↓ Multi-agent systems without the chaos. Single agents are easy. Multi-agent systems are where 99% of builders fail. Ivan extends the birthday planner by: Adding a calendar service through MCP tools Creating an orchestrator agent to route requests between agents Handling state and context across agent handoffs This is production multi-agent architecture. Clean. Scalable. Debuggable. Most tutorials hand-wave this part. This one shows you every step. Multi-agent orchestration content drops weekly on Himanshu Kumar. ↓ Deployment without the DevOps nightmare. This is where most AI projects die. You build a cool agent locally. It works. You try to deploy it. Everything breaks. Vertex AI Agent Engine fixes this: Minimal code deployment Automatic monitoring of latency, CPU, and memory Built-in observability and logging No infrastructure setup needed You provide config and requirements. The platform handles the rest. This is how agents actually get to production. Deployment guides for Claude agents post every week. Himanshu Kumar. ↓ Agent-to-Agent Protocol: the future nobody's talking about. Most people don't know this exists yet. The A2A Protocol lets agents built in different frameworks communicate seamlessly. Your Claude agent. My LangChain agent. Someone else's CrewAI agent. All talking to each other. All solving parts of the same problem. All without custom integration code. This is the infrastructure layer of the coming AI economy. Getting in early on A2A Protocol is like getting in early on HTTP in 1995. A2A deep dive coming soon. Himanshu Kumar. ↓ 30 minutes from the team shipping this in production. You'll learn more from this than from 6 months of YouTube tutorials made by people who've never deployed an agent past localhost. People who watch this understand production AI agents at the architect level. People who skip it keep hacking together frameworks that break every time an API updates. Save the video. Watch it tonight. Build a real agent this weekend. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.

Himanshu Kumar

227,802 views • 2 months ago

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Roberta Raileanu

105,030 views • 1 year ago

Andrej Karpathy: "90% of what AI twitter tells you to learn will be dead in 6 months" Here are 10 things senior AI engineers stopped wasting time on: 1. AutoGen / AG2: moved to community maintenance, releases stalled. dead for production 2. CrewAI: demos well, breaks in production. engineers building real systems already moved off it 3. Autonomous agent pitches: the AutoGPT / BabyAGI wave is dead in product form. the industry settled on supervised, bounded, evaluated agents 4. Agent app stores / marketplaces: promised since 2023, zero enterprise traction 5. SWE-bench leaderboard chasing: researchers proved nearly every public benchmark can be gamed without solving the underlying task 6. Microsoft Semantic Kernel: unless you're locked into Microsoft enterprise stack, it's not where the ecosystem is heading 7. DSPy: philosophical merit, niche audience. not a general agent framework 8. Horizontal "build any agent" platforms: Google Agentspace, AWS Bedrock Agents, Copilot Studio. confusing, slow-shipping, the math still favors building yourself 9. Per-seat SaaS pricing for agent products: market moved to outcome-based. per-seat is already dead 10. The framework that went viral on HN this week: wait 6 months. if it still matters, it'll be obvious what actually compounds instead: - context engineering - tool design - orchestrator-subagent pattern - eval discipline - the harness mindset (harness > model, always) - MCP as the protocol layer be few steps ahead than your competitors and outperform this market till it became mass-opinion study this.

Andrej Karpathy: "90% of what AI twitter tells you to learn will be dead in 6 months" Here are 10 things senior AI engineers stopped wasting time on: 1. AutoGen / AG2: moved to community maintenance, releases stalled. dead for production 2. CrewAI: demos well, breaks in production. engineers building real systems already moved off it 3. Autonomous agent pitches: the AutoGPT / BabyAGI wave is dead in product form. the industry settled on supervised, bounded, evaluated agents 4. Agent app stores / marketplaces: promised since 2023, zero enterprise traction 5. SWE-bench leaderboard chasing: researchers proved nearly every public benchmark can be gamed without solving the underlying task 6. Microsoft Semantic Kernel: unless you're locked into Microsoft enterprise stack, it's not where the ecosystem is heading 7. DSPy: philosophical merit, niche audience. not a general agent framework 8. Horizontal "build any agent" platforms: Google Agentspace, AWS Bedrock Agents, Copilot Studio. confusing, slow-shipping, the math still favors building yourself 9. Per-seat SaaS pricing for agent products: market moved to outcome-based. per-seat is already dead 10. The framework that went viral on HN this week: wait 6 months. if it still matters, it'll be obvious what actually compounds instead: - context engineering - tool design - orchestrator-subagent pattern - eval discipline - the harness mindset (harness > model, always) - MCP as the protocol layer be few steps ahead than your competitors and outperform this market till it became mass-opinion study this.

Ronin

415,734 views • 2 months ago

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

Andrew Ng

131,779 views • 1 year ago

We built an open-source research platform for agents utilizing Andrej Karpathy's autoresearch agent. agentipedia Crowd-sourced research will be the single biggest impact point for AI in the next 5 years and agentipedia will be a platform to drive it. Our vision: > There are potentially millions of niche use cases of research agents building strategies, better models, operating procedures and more. PHD level science is possible through agent collaboration. > Right now, very few entities control the vast majority of resources that can power this research; we believe in the future where any curious soul can harness the same energy. > Agentipedia was created to let curious souls (ML Engineers, Executives/CEOs, Founders, Builders, or literally anyone) think of a hypothesis for any application and be met with a swarm of agents experimenting to see if its true. Collaboration will yield magnitudes of impact on our society that we have not yet seen. The simulators for several use cases like (drug discovery, autonomous driving) and more already exist today.

We built an open-source research platform for agents utilizing Andrej Karpathy's autoresearch agent. agentipedia Crowd-sourced research will be the single biggest impact point for AI in the next 5 years and agentipedia will be a platform to drive it. Our vision: > There are potentially millions of niche use cases of research agents building strategies, better models, operating procedures and more. PHD level science is possible through agent collaboration. > Right now, very few entities control the vast majority of resources that can power this research; we believe in the future where any curious soul can harness the same energy. > Agentipedia was created to let curious souls (ML Engineers, Executives/CEOs, Founders, Builders, or literally anyone) think of a hypothesis for any application and be met with a swarm of agents experimenting to see if its true. Collaboration will yield magnitudes of impact on our society that we have not yet seen. The simulators for several use cases like (drug discovery, autonomous driving) and more already exist today.

invisible

30,345 views • 4 months ago

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

fxnction

27,570 views • 1 month ago

We are excited to announce a powerful step for the future of FOMO! Taking a page out of Virtuals book on BASE, FOMO will be releasing the ability for future projects to be paired in $FOMO in the coming weeks. This is the biggest release we have ever announced. Launch your AI Agent Token + $FOMO trading pair Every individual agent token is paired with the $FOMO token in its liquidity pool. When launching an agent on you will need $FOMO tokens, which are used to create the liquidity pool. This process creates deflationary pressure for FOMO and the entire agent ecosystem. When creating your agent and token, you will have the option to pair your launch with FOMO or SOL, as our goal is not to alienate any project, but rather invite the best communities, CTO’s and builders to launch with us. If you decide to pair your project with FOMO you in turn get full marketing and dev support, once your project graduates the bonding curve and reaches Raydium. Further, as an added incentive, as our revenue grows we will be using part of the funds to support projects that have paired in FOMO. And Devs who launch tokens paired in FOMO will earn fees from their AI Agent token launch. Building the most robust agents using our framework will catapult us as one of the most prominent standards of the Solana ecosystem. Not only have we developed our own core infrastructure, but we also pull from some of the best repo’s and developer talent in all of AI, not just blockchain. Our team is comprised of 9 world class artificial intelligence engineers, PHDs in mathematics and engineering from the top companies on the cutting edge of AI. The future of AI Agents will be on Solana and we will help lead the way.

We are excited to announce a powerful step for the future of FOMO! Taking a page out of Virtuals book on BASE, FOMO will be releasing the ability for future projects to be paired in $FOMO in the coming weeks. This is the biggest release we have ever announced. Launch your AI Agent Token + $FOMO trading pair Every individual agent token is paired with the $FOMO token in its liquidity pool. When launching an agent on you will need $FOMO tokens, which are used to create the liquidity pool. This process creates deflationary pressure for FOMO and the entire agent ecosystem. When creating your agent and token, you will have the option to pair your launch with FOMO or SOL, as our goal is not to alienate any project, but rather invite the best communities, CTO’s and builders to launch with us. If you decide to pair your project with FOMO you in turn get full marketing and dev support, once your project graduates the bonding curve and reaches Raydium. Further, as an added incentive, as our revenue grows we will be using part of the funds to support projects that have paired in FOMO. And Devs who launch tokens paired in FOMO will earn fees from their AI Agent token launch. Building the most robust agents using our framework will catapult us as one of the most prominent standards of the Solana ecosystem. Not only have we developed our own core infrastructure, but we also pull from some of the best repo’s and developer talent in all of AI, not just blockchain. Our team is comprised of 9 world class artificial intelligence engineers, PHDs in mathematics and engineering from the top companies on the cutting edge of AI. The future of AI Agents will be on Solana and we will help lead the way.

FOMO

129,867 views • 1 year ago

Every software company just got a second life and Jensen just explained why (Save this). The conventional fear was straightforward, AI agents replace human workers, human workers use software tools, therefore agents destroy SaaS. Jensen Huang stood on stage at Computex 2026 and walked through exactly why that logic is backwards. Agents don't replace software, they consume it at machine speed, around the clock, without weekends. Here's the actual architecture Jensen laid out. An agent isn't just a large language model but rather an LLM sitting inside a harness that manages memory, orchestrates tool use, routes context, and plans iterative actions. That harness has to constantly call tools, spreadsheets, databases, browsers, and code engines, with every reasoning loop triggering another tool call. A human might use Salesforce 40 hours a week, an agent running inside a company uses it 168 hours a week and never misses a context window. The GitHub data Jensen showed on stage makes it tangible, 90 million pull requests merged, 1.4 billion commits, and 20 million new repositories created every month. As of April 2026, GitHub is processing 275 million commits per week on pace for roughly 14 billion by year end, a 14x explosion in a single year and AI agents are the source. Pull requests opened by AI agents went from 4 million in September 2025 to 17 million in March 2026 more than 4x in six months. That's AI becoming the largest software user on earth. Goldman Sachs quantified the downstream effect last month, token consumption is expected to multiply 24x by 2030, reaching 120 quadrillion tokens per month globally. A traditional chatbot consumes roughly 1,000 tokens per session, an embedded copilot burns 5,000 tokens per day while a continuously running enterprise agent? Over 100,000 tokens per day. The software companies that figured this out first are already printing money, Salesforce Agentforce hit $800 million ARR growing 169% year over year, with 29,000 deals closed. ServiceNow's Now Assist crossed $600 million in ACV, just raised its full year target to $1.5 billion, and told investors that when its agents replace a 20-person support team, total ServiceNow spend by that customer grows more than 5x even after accounting for reduced seat licenses. Workday delivered 1.7 billion AI actions across its platform in fiscal 2026. The key unlock Jensen pointed to and what investors need to understand is MCP, the model context protocol is the interface layer that makes software agent-readable. Software that supports MCP can be called by any agent, from any model, through any harness. Anthropic created it, OpenAI, Microsoft, and Google all adopted it and it was donated to the Linux Foundation. It is effectively becoming the HTTP of agentic computing. Software companies with native MCP support are plugged into the agent economy. Software companies still waiting are one product cycle away from becoming invisible to the fastest-growing category of software users in history.

Every software company just got a second life and Jensen just explained why (Save this). The conventional fear was straightforward, AI agents replace human workers, human workers use software tools, therefore agents destroy SaaS. Jensen Huang stood on stage at Computex 2026 and walked through exactly why that logic is backwards. Agents don't replace software, they consume it at machine speed, around the clock, without weekends. Here's the actual architecture Jensen laid out. An agent isn't just a large language model but rather an LLM sitting inside a harness that manages memory, orchestrates tool use, routes context, and plans iterative actions. That harness has to constantly call tools, spreadsheets, databases, browsers, and code engines, with every reasoning loop triggering another tool call. A human might use Salesforce 40 hours a week, an agent running inside a company uses it 168 hours a week and never misses a context window. The GitHub data Jensen showed on stage makes it tangible, 90 million pull requests merged, 1.4 billion commits, and 20 million new repositories created every month. As of April 2026, GitHub is processing 275 million commits per week on pace for roughly 14 billion by year end, a 14x explosion in a single year and AI agents are the source. Pull requests opened by AI agents went from 4 million in September 2025 to 17 million in March 2026 more than 4x in six months. That's AI becoming the largest software user on earth. Goldman Sachs quantified the downstream effect last month, token consumption is expected to multiply 24x by 2030, reaching 120 quadrillion tokens per month globally. A traditional chatbot consumes roughly 1,000 tokens per session, an embedded copilot burns 5,000 tokens per day while a continuously running enterprise agent? Over 100,000 tokens per day. The software companies that figured this out first are already printing money, Salesforce Agentforce hit $800 million ARR growing 169% year over year, with 29,000 deals closed. ServiceNow's Now Assist crossed $600 million in ACV, just raised its full year target to $1.5 billion, and told investors that when its agents replace a 20-person support team, total ServiceNow spend by that customer grows more than 5x even after accounting for reduced seat licenses. Workday delivered 1.7 billion AI actions across its platform in fiscal 2026. The key unlock Jensen pointed to and what investors need to understand is MCP, the model context protocol is the interface layer that makes software agent-readable. Software that supports MCP can be called by any agent, from any model, through any harness. Anthropic created it, OpenAI, Microsoft, and Google all adopted it and it was donated to the Linux Foundation. It is effectively becoming the HTTP of agentic computing. Software companies with native MCP support are plugged into the agent economy. Software companies still waiting are one product cycle away from becoming invisible to the fastest-growing category of software users in history.

Milk Road AI

33,878 views • 1 month ago

RLM is the most import foundation of my Pi Harness (other than Pi of course). It's seeded with late interaction retrieval results (thanks to @lightonai for pylate). The Agent initiates it with query then.. 𝐒𝐞𝐭𝐮𝐩 A python REPL is created and seeded with: 1. Late interaction search to pre-filter. Instead of doing top 3/5/10, it's top hundreds of documents. This is set into a `context` variable. 2. Python functions are loaded in to do more searches if `context` variable isn't enough. And to make llm calls with cheaper models in parallel batches. 𝐈𝐭𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐋𝐨𝐨𝐩 From there, an LLM iterates in the REPL based on the query. It's just like exploring in a jupyter notebook. The LLM writes prose (like a markdown cell) and code to be run in the REPL each turn. This allows the LLM to sort, filter, and synthesize information. It can fan out and ask smaller models to summarize, combine, contrast, or do anything else to documents to help it understand the data. After several turns the LLM reponds with the final answer. Either because it found the answer, or hit the budget limit. Context as a Python variable, LLM as the programmer, REPL as the runtime. 𝐖𝐡𝐲 𝐃𝐨𝐞𝐬 𝐓𝐡𝐢𝐬 𝐖𝐨𝐫𝐤 1. Richer Shell. Agents (and subagents) work by intermixing code and prose/thinking. But they use static scripts or bash that run and exit and start over each tool call. That's not ideal for exploration and synthesis of data. For that, state is useful to continue building and exploring the data as you learn more. There's a reason jupyter notebooks have been popular with data scientists. 2. Keeps main agent context clean. The better context you have the better the agent will perform (duh!). This means three thing: better human input, less missing search results, and less incorrect search results. Letting the agent iterate allows it to synthesize just what is needed and nothing else. All bad paths or peeks at something that turns out to be irrelevant stays out of main agent context. 3. Stack the good ideas! People often compare late interaction search vs RLM. Or static vs dynamic languages. Or agentic search vs semantic search. But...You can just use them all together for what they're each good at. Use them all for the area they're really great for. Read the full post which has more detail about how and why.

RLM is the most import foundation of my Pi Harness (other than Pi of course). It's seeded with late interaction retrieval results (thanks to @lightonai for pylate). The Agent initiates it with query then.. 𝐒𝐞𝐭𝐮𝐩 A python REPL is created and seeded with: 1. Late interaction search to pre-filter. Instead of doing top 3/5/10, it's top hundreds of documents. This is set into a `context` variable. 2. Python functions are loaded in to do more searches if `context` variable isn't enough. And to make llm calls with cheaper models in parallel batches. 𝐈𝐭𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐋𝐨𝐨𝐩 From there, an LLM iterates in the REPL based on the query. It's just like exploring in a jupyter notebook. The LLM writes prose (like a markdown cell) and code to be run in the REPL each turn. This allows the LLM to sort, filter, and synthesize information. It can fan out and ask smaller models to summarize, combine, contrast, or do anything else to documents to help it understand the data. After several turns the LLM reponds with the final answer. Either because it found the answer, or hit the budget limit. Context as a Python variable, LLM as the programmer, REPL as the runtime. 𝐖𝐡𝐲 𝐃𝐨𝐞𝐬 𝐓𝐡𝐢𝐬 𝐖𝐨𝐫𝐤 1. Richer Shell. Agents (and subagents) work by intermixing code and prose/thinking. But they use static scripts or bash that run and exit and start over each tool call. That's not ideal for exploration and synthesis of data. For that, state is useful to continue building and exploring the data as you learn more. There's a reason jupyter notebooks have been popular with data scientists. 2. Keeps main agent context clean. The better context you have the better the agent will perform (duh!). This means three thing: better human input, less missing search results, and less incorrect search results. Letting the agent iterate allows it to synthesize just what is needed and nothing else. All bad paths or peeks at something that turns out to be irrelevant stays out of main agent context. 3. Stack the good ideas! People often compare late interaction search vs RLM. Or static vs dynamic languages. Or agentic search vs semantic search. But...You can just use them all together for what they're each good at. Use them all for the area they're really great for. Read the full post which has more detail about how and why.

Isaac Flath

40,212 views • 2 months ago

What a year. 🚀 2025 was the year ChainOpera AI turned vision into real momentum: building a community-co-created, community-co-owned AI agent network and pushing the boundaries of what decentralized, collaborative intelligence can look like. 🚀 Biggest highlights from 2025 ✅- AI Terminal officially launched: We unveiled the ChainOpera AI Terminal as a unified gateway to decentralized AI, making it possible for anyone to interact with powerful, decentralized LLMs without technical friction. Positioned as the “browser for the DeAI era,” the AI Terminal marked a major step toward making decentralized intelligence accessible, usable, and mainstream. ✅- AI Terminal adoption at massive scale: Momentum followed quickly. The AI Terminal surpassed 2M registered users and consistently ranked top 3 among all apps on the BNB AI DappBay, validating strong product–market fit and real, sustained usage at scale. ✅- Announcing Coco: the world’s first community-owned Super Agent: We introduced Coco, the intelligence layer that sits between users and the agent network. Coco dynamically routes each request to the most efficient, community-built agent—optimizing for quality and speed while rewarding the creators behind the best-performing agents. This was a defining moment in realizing a truly community-owned intelligence layer. ✅- From agents to a living agent network: With the launch of the Agent Social Network and Super Agent architecture, ChainOpera AI moved beyond isolated agents toward a collaborative system where humans and specialized agents coordinate, share context, and solve complex, multi-step tasks together. ✅- $COAI breakout year: The listing of $COAI across major exchanges shocked the market, and throughout the year COAI consistently remained among the top AI-native crypto tokens by visibility, activity, and community engagement – reflecting growing confidence in the long-term vision of collaborative intelligence. ✅- Global presence: ChainOpera AI around-the-world tour: ChainOpera AI went global in 2025, sponsoring and participating in major AI and Web3 events across North America, Europe, and Asia, including ETHDenver, Consensus Toronto, Token2049 Singapore, ETHCC, SBC, and Devcon. These global touchpoints helped us engage directly with developers, builders, investors, and partners worldwide, accelerating adoption and positioning ChainOpera AI at the center of the emerging AIxBlockchain movement. ✅- Community momentum at scale: Community remained the heart of ChainOpera AI’s growth. We successfully completed three seasons of structured community engagement, executed a widely participated community airdrop, and ran multiple ecosystem-shaping campaigns to incentivize builders, creators, and early adopters. These efforts strengthened alignment between users, developers, and the protocol, laying the foundation for a durable, community-owned AI ecosystem. ✅- “AI for Markets” taking shape: We laid critical groundwork for AI-native market intelligence, including the launch of PrediMarket Agent and multiple trading and analysis agents—early building blocks toward an AI-driven ecosystem for crypto and DeFi markets. ✅- Building in public, with the community: Across product launches, research milestones, ecosystem discussions, and global events, we continued to build openly to bring developers, users, and partners directly into the evolution of ChainOpera AI. This year also marked the launch of the ChainOpera AI Foundation website, formally kicking off a bold Ecosystem Fund designed to empower builders, incubate high-impact projects, and accelerate the growth of a truly community-owned, collaborative AI ecosystem. To every builder, user, and supporter who helped make this year possible: THANK YOU! 🧭 What we’re excited about in the coming year 🔹- A Stronger, Denser Agent Economy (everyday adoption + cross-chain reach): In 2026, we are scaling the Agent Economy from growth to daily usage, with more agents, richer workflows, deeper multi-agent collaboration, and higher-impact use cases that users rely on every day. In parallel, we are expanding the agent network beyond a single ecosystem with cross-chain execution and interoperability, allowing agents to access the best liquidity, data, and opportunities wherever they exist. 🔹- AI Market Infrastructure Evolution: Building on PrediMarket Agent and our growing suite of trading and market-intelligence agents, we are advancing toward a mature AI market infrastructure, where agents continuously monitor, reason, simulate, optimize, and act across crypto, DeFi, and beyond. The goal is to make complex markets more accessible, more transparent, and more intelligence-driven, turning research, decision-making, and execution into a fast and reliable loop for everyday users. 🔹- Ecosystem Acceleration through the Foundation: With the ChainOpera AI Foundation and our Ecosystem Fund and Co-Creation Grants, we are doubling down on empowering independent builders to expand the protocol, the agent network, and the underlying infrastructure, so the community can co-create, co-own, and scale the ecosystem together. 🔹- Business Expansion and Market Penetration: In 2026, we will focus on expanding ChainOpera’s reach through strategic partnerships, product-led growth, and new paths to monetization, bringing AI agents to a broader global user base and driving sustained adoption, engagement, and revenue, while staying aligned with community ownership and an open ecosystem. 2025 was the proof. 2026 is where it compounds. 🔥 Co-Create. Co-Own. COAI.

What a year. 🚀 2025 was the year ChainOpera AI turned vision into real momentum: building a community-co-created, community-co-owned AI agent network and pushing the boundaries of what decentralized, collaborative intelligence can look like. 🚀 Biggest highlights from 2025 ✅- AI Terminal officially launched: We unveiled the ChainOpera AI Terminal as a unified gateway to decentralized AI, making it possible for anyone to interact with powerful, decentralized LLMs without technical friction. Positioned as the “browser for the DeAI era,” the AI Terminal marked a major step toward making decentralized intelligence accessible, usable, and mainstream. ✅- AI Terminal adoption at massive scale: Momentum followed quickly. The AI Terminal surpassed 2M registered users and consistently ranked top 3 among all apps on the BNB AI DappBay, validating strong product–market fit and real, sustained usage at scale. ✅- Announcing Coco: the world’s first community-owned Super Agent: We introduced Coco, the intelligence layer that sits between users and the agent network. Coco dynamically routes each request to the most efficient, community-built agent—optimizing for quality and speed while rewarding the creators behind the best-performing agents. This was a defining moment in realizing a truly community-owned intelligence layer. ✅- From agents to a living agent network: With the launch of the Agent Social Network and Super Agent architecture, ChainOpera AI moved beyond isolated agents toward a collaborative system where humans and specialized agents coordinate, share context, and solve complex, multi-step tasks together. ✅- $COAI breakout year: The listing of $COAI across major exchanges shocked the market, and throughout the year COAI consistently remained among the top AI-native crypto tokens by visibility, activity, and community engagement – reflecting growing confidence in the long-term vision of collaborative intelligence. ✅- Global presence: ChainOpera AI around-the-world tour: ChainOpera AI went global in 2025, sponsoring and participating in major AI and Web3 events across North America, Europe, and Asia, including ETHDenver, Consensus Toronto, Token2049 Singapore, ETHCC, SBC, and Devcon. These global touchpoints helped us engage directly with developers, builders, investors, and partners worldwide, accelerating adoption and positioning ChainOpera AI at the center of the emerging AIxBlockchain movement. ✅- Community momentum at scale: Community remained the heart of ChainOpera AI’s growth. We successfully completed three seasons of structured community engagement, executed a widely participated community airdrop, and ran multiple ecosystem-shaping campaigns to incentivize builders, creators, and early adopters. These efforts strengthened alignment between users, developers, and the protocol, laying the foundation for a durable, community-owned AI ecosystem. ✅- “AI for Markets” taking shape: We laid critical groundwork for AI-native market intelligence, including the launch of PrediMarket Agent and multiple trading and analysis agents—early building blocks toward an AI-driven ecosystem for crypto and DeFi markets. ✅- Building in public, with the community: Across product launches, research milestones, ecosystem discussions, and global events, we continued to build openly to bring developers, users, and partners directly into the evolution of ChainOpera AI. This year also marked the launch of the ChainOpera AI Foundation website, formally kicking off a bold Ecosystem Fund designed to empower builders, incubate high-impact projects, and accelerate the growth of a truly community-owned, collaborative AI ecosystem. To every builder, user, and supporter who helped make this year possible: THANK YOU! 🧭 What we’re excited about in the coming year 🔹- A Stronger, Denser Agent Economy (everyday adoption + cross-chain reach): In 2026, we are scaling the Agent Economy from growth to daily usage, with more agents, richer workflows, deeper multi-agent collaboration, and higher-impact use cases that users rely on every day. In parallel, we are expanding the agent network beyond a single ecosystem with cross-chain execution and interoperability, allowing agents to access the best liquidity, data, and opportunities wherever they exist. 🔹- AI Market Infrastructure Evolution: Building on PrediMarket Agent and our growing suite of trading and market-intelligence agents, we are advancing toward a mature AI market infrastructure, where agents continuously monitor, reason, simulate, optimize, and act across crypto, DeFi, and beyond. The goal is to make complex markets more accessible, more transparent, and more intelligence-driven, turning research, decision-making, and execution into a fast and reliable loop for everyday users. 🔹- Ecosystem Acceleration through the Foundation: With the ChainOpera AI Foundation and our Ecosystem Fund and Co-Creation Grants, we are doubling down on empowering independent builders to expand the protocol, the agent network, and the underlying infrastructure, so the community can co-create, co-own, and scale the ecosystem together. 🔹- Business Expansion and Market Penetration: In 2026, we will focus on expanding ChainOpera’s reach through strategic partnerships, product-led growth, and new paths to monetization, bringing AI agents to a broader global user base and driving sustained adoption, engagement, and revenue, while staying aligned with community ownership and an open ecosystem. 2025 was the proof. 2026 is where it compounds. 🔥 Co-Create. Co-Own. COAI.

ChainOpera AI

17,016 views • 6 months ago

NEAR AI Ecosystem – “What Did You Ship This Week?” Ep. 7 A big week across the NEAR AI ecosystem with updates on personalized data agents, TypeScript tooling, crowdsourced AI data, and non-custodial flows for token coordination + much more. Timestamps & Highlights: 00:00 – Intro by Cameron.near🇺🇸 from NEAR AI 01:00 – 𝕵𝖔𝖗𝖉𝖆𝖓✨🐾ヤᵇᵃ ͥ ꜝ9d from PublicAI explains how their platform lets users earn stablecoins and points by uploading and verifying native language audio clips. Data builders can now claim earnings directly to a NEAR Protocol wallet. Public beta is live. 09:35 – Matt Hamilton from ASIMOV Protocol demos their CLI tools for uploading structured datasets to NEAR, plus new knowledge graph visualizations and early experiments transcribing voice into semantic graphs. 15:55 – @tahpot_au from Verida 💜 shows how developers can access private user data for AI agents using the Verida Vault. Users retain full control over their data, with API keys gated by permission. 25:25 – Zahidul Islam from Jutsu | Work Smarter with AI Agents drops updates on the NEAR AI TypeScript SDK. One-command agent deployment, fully local dev support, and matching features with the Python SDK. Also demoed new AI-generated video tooling with Postt. 34:20 – Matt Lockyer from Proximity Labs shares the launch of their Base naming agent Basednames. Users post on X to mint names, pay with Bankr, and finalize with verified chain signatures powered by NEAR. All non-custodial. All live on Base. 50:35 – Charles previews Divvy Agent. Users can set portfolio growth and swap thresholds with natural language. Latest update adds persistent memory, improved LLM matching, and MPC integration for safe, automated execution. 59:36 – Cameron.near🇺🇸 closes out with updates from the NEAR AI core team. Hiring in progress, governance agents coming soon, and progress on privacy tooling and agent infra powering the NEAR AI Hub. The future is NEAR - the blockchain for AI. Catch the full replay:

NEAR AI Ecosystem – “What Did You Ship This Week?” Ep. 7 A big week across the NEAR AI ecosystem with updates on personalized data agents, TypeScript tooling, crowdsourced AI data, and non-custodial flows for token coordination + much more. Timestamps & Highlights: 00:00 – Intro by Cameron.near🇺🇸 from NEAR AI 01:00 – 𝕵𝖔𝖗𝖉𝖆𝖓✨🐾ヤᵇᵃ ͥ ꜝ9d from PublicAI explains how their platform lets users earn stablecoins and points by uploading and verifying native language audio clips. Data builders can now claim earnings directly to a NEAR Protocol wallet. Public beta is live. 09:35 – Matt Hamilton from ASIMOV Protocol demos their CLI tools for uploading structured datasets to NEAR, plus new knowledge graph visualizations and early experiments transcribing voice into semantic graphs. 15:55 – @tahpot_au from Verida 💜 shows how developers can access private user data for AI agents using the Verida Vault. Users retain full control over their data, with API keys gated by permission. 25:25 – Zahidul Islam from Jutsu | Work Smarter with AI Agents drops updates on the NEAR AI TypeScript SDK. One-command agent deployment, fully local dev support, and matching features with the Python SDK. Also demoed new AI-generated video tooling with Postt. 34:20 – Matt Lockyer from Proximity Labs shares the launch of their Base naming agent Basednames. Users post on X to mint names, pay with Bankr, and finalize with verified chain signatures powered by NEAR. All non-custodial. All live on Base. 50:35 – Charles previews Divvy Agent. Users can set portfolio growth and swap thresholds with natural language. Latest update adds persistent memory, improved LLM matching, and MPC integration for safe, automated execution. 59:36 – Cameron.near🇺🇸 closes out with updates from the NEAR AI core team. Hiring in progress, governance agents coming soon, and progress on privacy tooling and agent infra powering the NEAR AI Hub. The future is NEAR - the blockchain for AI. Catch the full replay:

NEARWEEK

35,143 views • 1 year ago

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

GREG ISENBERG

375,365 views • 4 months ago

🤯 Building computer-vision applications is never going to be the same again. As Andrej Karpathy says, "English is going to be the new programming-language", and we just made that happen for programming visual AI. 👨‍💻 This past month, the VLM Run team cooked up something magical that I'm especially proud of - a natural-language interface to build and run computer vision workflows (object-detection, OCR, parsing, and so much more) – all via our new VLM Run MCP server. 🔌 It works with any MCP-compatible AI agent (Claude, OpenAI, Cursor, etc.) and abstracts complex visual workflows into simple English commands. No need to write Python or fiddle with bespoke computer-vision code – just say what you want your agent to do, and it does it. Here’s a glimpse into what you can build today ( ☑️ Image AI agents – run detection, tagging, blurring, cropping, and more traditional CV tasks with English ☑️ Document AI agents – extract totals from invoices, search visual content, or act on what’s found ☑️ Video AI agents – understand scene content, trim clips, add subtitles, and create ready-to-share edits ☑️ And best-of-all, it's fully programmable with English. 🧑‍🍳 MCP Showcase: 📚 MCP Cookbooks: 📚 MCP Docs: #computervision #ai #agents #llm #vlm #mcp #vibecoding #genai

🤯 Building computer-vision applications is never going to be the same again. As Andrej Karpathy says, "English is going to be the new programming-language", and we just made that happen for programming visual AI. 👨‍💻 This past month, the VLM Run team cooked up something magical that I'm especially proud of - a natural-language interface to build and run computer vision workflows (object-detection, OCR, parsing, and so much more) – all via our new VLM Run MCP server. 🔌 It works with any MCP-compatible AI agent (Claude, OpenAI, Cursor, etc.) and abstracts complex visual workflows into simple English commands. No need to write Python or fiddle with bespoke computer-vision code – just say what you want your agent to do, and it does it. Here’s a glimpse into what you can build today ( ☑️ Image AI agents – run detection, tagging, blurring, cropping, and more traditional CV tasks with English ☑️ Document AI agents – extract totals from invoices, search visual content, or act on what’s found ☑️ Video AI agents – understand scene content, trim clips, add subtitles, and create ready-to-share edits ☑️ And best-of-all, it's fully programmable with English. 🧑‍🍳 MCP Showcase: 📚 MCP Cookbooks: 📚 MCP Docs: #computervision #ai #agents #llm #vlm #mcp #vibecoding #genai

Sudeep Pillai

17,789 views • 1 year ago