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.

AgentHub (AgentHub) is the missing layer in the AI agent stack: simulation and evaluation for complex agents. Agents today use tools, APIs, browsers, file systems, and more - AgentHub builds realistic sandbox environments and the infra to easily test them.

Y Combinator

1,655,545 subscribers

20,227 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

16 Comments

Y Combinator1 year ago

Congrats on the launch, @ymkallel and @sandrtang!

Vihaar Nandigala1 year ago

@agenthublabs Agent hub is amazing orange slice couldn’t run without them

Viraat1 year ago

@agenthublabs Game changer product!

Akash1 year ago

@agenthublabs So useful. Agent reliability 📈📈

Sandra Tang1 year ago

@agenthublabs @ymkallel and I are excited to launch @agenthublabs and help close the feedback loop to evaluate and improve agent performance! Feel free to reach out to us anytime!

Aaron Chew1 year ago

@agenthublabs amazing

Pablo Hansen1 year ago

@agenthublabs Wow! Such a useful product.

Chase Carnaroli1 year ago

@agenthublabs such a cool platform! congrats on the launch @sandrtang @ymkallel 🚀

Yang Fan Yun1 year ago

@agenthublabs WOOOOO let's go @sandrtang 🚀

tinah1 year ago

@agenthublabs 🚀

Kishan Sripada1 year ago

@agenthublabs bananas are so fire

KEALA1 year ago

@agenthublabs I’d love to attend this… but a stay in Cali for a whole month?

Kayako1 year ago

@agenthublabs interesting! though we've found the biggest agent failures aren't technical, they're usually trying to automate processes that shouldn't exist in the first place (especially with manual customer support in the age of ai)

ElectronArtist_321 year ago

@agenthublabs La simulation avant prod ? Enfin la sécu qui manque cruellement en France, où l’innovation finit (trop) souvent en crash-test grandeur nature. Hâte de voir la tête des ingénieurs au premier vrai test !

Sanjeev Kumar1 year ago

@agenthublabs Interesting, looking forward to learn more!

A C1 year ago

@agenthublabs Such a cool product go agenthub

Related Videos

1/ Introducing Agent Protocol: the payment stack for AI agents AI agents don’t have a SSN. They can’t use our human banking system. AI agents will use crypto. Agent Protocol provides the infra and token ($AGENT) that the AI agent economy will run on.

1/ Introducing Agent Protocol: the payment stack for AI agents AI agents don’t have a SSN. They can’t use our human banking system. AI agents will use crypto. Agent Protocol provides the infra and token ($AGENT) that the AI agent economy will run on.

Samuel Spitz

21,629 views • 2 years ago

Agents were once limited to calling APIs. Now agents participate in the economy. The missing element for autonomous agents was always payments. Now agents transact natively on the internet using x402, enabling autonomous payments between agents and services. Agent Stack: 🦞 Openclaw agent infra ▶️ Telegram communication layer 🤖 Teneo agent + agent wallet Agent Workflow - Compare accounts following two separate X handles: ✅ User - Enters a query ✅ Agent - Autonomously selects the correct Teneo agent and queries it ✅ Agent - Pays via x402 on Avalanche🔺 ✅ Agent - Returns structured dataset Any user can simply ask a question and give a job. The agent does everything else No API keys. No subscriptions. Just programmatic value exchange. Build and monetize your own agents today. #A2A #x402 #Infra

Agents were once limited to calling APIs. Now agents participate in the economy. The missing element for autonomous agents was always payments. Now agents transact natively on the internet using x402, enabling autonomous payments between agents and services. Agent Stack: 🦞 Openclaw agent infra ▶️ Telegram communication layer 🤖 Teneo agent + agent wallet Agent Workflow - Compare accounts following two separate X handles: ✅ User - Enters a query ✅ Agent - Autonomously selects the correct Teneo agent and queries it ✅ Agent - Pays via x402 on Avalanche🔺 ✅ Agent - Returns structured dataset Any user can simply ask a question and give a job. The agent does everything else No API keys. No subscriptions. Just programmatic value exchange. Build and monetize your own agents today. #A2A #x402 #Infra

Teneo Protocol

41,855 views • 7 months ago

Agent commerce = $5T by 2030 (McKinsey) But agents need the infra to transact safely. Boson is the secure commerce layer for the agentic economy. Boson x402B just dropped on testnet. The missing piece in the decentralized AI stack 🧵

Agent commerce = $5T by 2030 (McKinsey) But agents need the infra to transact safely. Boson is the secure commerce layer for the agentic economy. Boson x402B just dropped on testnet. The missing piece in the decentralized AI stack 🧵

Boson

5,414,504 views • 5 months ago

I've stopped downloading CLI tools. Agents can call APIs directly. aurl allows agents to understand and use APIs. > curl for humans → aurl for agents > API docs as --help flags and SKILL[.]md files pass in an API spec, agent instantly learns new tools

I've stopped downloading CLI tools. Agents can call APIs directly. aurl allows agents to understand and use APIs. > curl for humans → aurl for agents > API docs as --help flags and SKILL[.]md files pass in an API spec, agent instantly learns new tools

shawn

74,436 views • 7 months ago

OPENAI OPEN-SOURCED THE STACK FOR BUILDING PRODUCTION AI AGENTS The Agents SDK combines tools, guardrails, memory, agent loops, handoffs, and human approvals into one runtime

OPENAI OPEN-SOURCED THE STACK FOR BUILDING PRODUCTION AI AGENTS The Agents SDK combines tools, guardrails, memory, agent loops, handoffs, and human approvals into one runtime

0xMarioNawfal

38,794 views • 1 month ago

we’re launching Codag (Y Combinator S26) - the compression and control layer for agent tools. we started with logs. then customers pulled us into searches, tests, builds, and api responses. the pattern was always the same: agents burning context on repetitive output, with teams unable to see where the tokens went. Codag now cuts input-token usage ~3x at answer parity and gives teams visibility across their agent stack. agents are becoming the primary users of software - companies are adding agents, models, providers, and MCP servers faster than they can measure or control them. most cannot answer which tools their agents invoke, what those calls cost, or where the waste is. we’re building the layer between them and everything they read. 90+ engineering orgs already use Codag today to reduce that spend and see agent tool usage across provider. find out more and book a demo at

we’re launching Codag (Y Combinator S26) - the compression and control layer for agent tools. we started with logs. then customers pulled us into searches, tests, builds, and api responses. the pattern was always the same: agents burning context on repetitive output, with teams unable to see where the tokens went. Codag now cuts input-token usage ~3x at answer parity and gives teams visibility across their agent stack. agents are becoming the primary users of software - companies are adding agents, models, providers, and MCP servers faster than they can measure or control them. most cannot answer which tools their agents invoke, what those calls cost, or where the waste is. we’re building the layer between them and everything they read. 90+ engineering orgs already use Codag today to reduce that spend and see agent tool usage across provider. find out more and book a demo at

Michael Zhou

163,267 views • 2 months ago

Wato (Wato) is building the collaboration layer for teams working with AI agents: shared knowledge, cloud agents, automations, and permissioned tools across the AI subscriptions companies already use. Congrats on the launch, Arihan & Rahul Rejeev!

Wato (Wato) is building the collaboration layer for teams working with AI agents: shared knowledge, cloud agents, automations, and permissioned tools across the AI subscriptions companies already use. Congrats on the launch, Arihan & Rahul Rejeev!

Y Combinator

17,559 views • 5 months ago

Metorial (Metorial (YC F25)) makes it easy for AI agents to use tools and data. Deploy 600+ MCP integrations in three clicks and connect them to agents in a single function call. Open-source and the only serverless MCP platform built for multi-tenant systems.

Metorial (Metorial (YC F25)) makes it easy for AI agents to use tools and data. Deploy 600+ MCP integrations in three clicks and connect them to agents in a single function call. Open-source and the only serverless MCP platform built for multi-tenant systems.

Y Combinator

15,381 views • 1 year ago

Agents need more than a model. Jensen Huang breaks down the enterprise agent stack: models, orchestration, tools with skills, and a secure runtime to hold it all together. This is the NVIDIA toolkit for agents:

Agents need more than a model. Jensen Huang breaks down the enterprise agent stack: models, orchestration, tools with skills, and a secure runtime to hold it all together. This is the NVIDIA toolkit for agents:

NVIDIA

40,806 views • 5 months ago

Most AI agents stop at chat. Agent Max is built for what comes after. Max tools. Max control and configurability. Max production readiness. Your agent can use: • any tools, APIs, MCP, and workflows • built-in knowledge: docs/website • multi-model: OpenAI, Claude, Gemini... • agent-to-agent handoffs • human-in-the-loop • logs, usage tracking, environments, and RBAC • enterprise controls for SOC2/GDPR/HIPAA/ISO needs • hosted chat UI, API, Skill in agents, Slack, WhatsApp, Teams, Voice, and more Agent Max is live now in BuildShip for everyone. Give it a try, or comment/DM to book a demo if you want help setting up your first agent.

Most AI agents stop at chat. Agent Max is built for what comes after. Max tools. Max control and configurability. Max production readiness. Your agent can use: • any tools, APIs, MCP, and workflows • built-in knowledge: docs/website • multi-model: OpenAI, Claude, Gemini... • agent-to-agent handoffs • human-in-the-loop • logs, usage tracking, environments, and RBAC • enterprise controls for SOC2/GDPR/HIPAA/ISO needs • hosted chat UI, API, Skill in agents, Slack, WhatsApp, Teams, Voice, and more Agent Max is live now in BuildShip for everyone. Give it a try, or comment/DM to book a demo if you want help setting up your first agent.

BuildShip

76,001 views • 4 months ago

Today we're excited to launch sandbox computer use for Mastra agents! Your agent can now browse, click, type, and take screenshots in a sandbox:

Today we're excited to launch sandbox computer use for Mastra agents! Your agent can now browse, click, type, and take screenshots in a sandbox:

Sam Bhagwat

15,428 views • 2 months ago

3. Agent factory: Foundry is the complete app platform for building apps and agents. We are adding support for more models from Grok, Hugging Face, Meta, Mistral, and more. Plus: Agentic retrieval in Azure AI Search, Foundry Agent Service, integration with Copilot Studio, and more. And we are ensuring the tools you already use for identity, management, and security will now all extend to agents too. The NFL has already used Foundry, along with our data stack, to run its recent Combine.

3. Agent factory: Foundry is the complete app platform for building apps and agents. We are adding support for more models from Grok, Hugging Face, Meta, Mistral, and more. Plus: Agentic retrieval in Azure AI Search, Foundry Agent Service, integration with Copilot Studio, and more. And we are ensuring the tools you already use for identity, management, and security will now all extend to agents too. The NFL has already used Foundry, along with our data stack, to run its recent Combine.

Satya Nadella

184,995 views • 1 year ago

Meet the new No-Code Agent Builder: Pick, combine, and deploy agents in seconds. Agents are composed of tools (APIs, smart contracts, on-chain logic). We break down your tools and let others build agents by combining them. Try it now 🔗👇

Meet the new No-Code Agent Builder: Pick, combine, and deploy agents in seconds. Agents are composed of tools (APIs, smart contracts, on-chain logic). We break down your tools and let others build agents by combining them. Try it now 🔗👇

Amadeus Protocol

99,837 views • 1 year ago

$50M has already settled between AI agents via x402 in just a few months. The commerce layer for the agent economy is being decided right now, and we're ensuring it will be open and on Ethereum. Today we shipped Obol Stack v0.9.0. $OBOL is now money for the agent economy!

$50M has already settled between AI agents via x402 in just a few months. The commerce layer for the agent economy is being decided right now, and we're ensuring it will be open and on Ethereum. Today we shipped Obol Stack v0.9.0. $OBOL is now money for the agent economy!

Obol

75,538 views • 5 months ago

Devtools for AI Agents Nicolas Dessaigne AI agents are the next wave: autonomous tools that reason, decide, and amplify human productivity. We’re funding startups building devtools for agents, whether you’re creating agent builders or building blocks to perform complex tasks.

Devtools for AI Agents Nicolas Dessaigne AI agents are the next wave: autonomous tools that reason, decide, and amplify human productivity. We’re funding startups building devtools for agents, whether you’re creating agent builders or building blocks to perform complex tasks.

Y Combinator

113,448 views • 1 year ago

Introducing AGNT Beta is Live Everyone's racing to build the $10T agentic economy. They're building all the tools for agents. But nobody's building the human layer. The place where you actually own and direct your agent. That's AGNT. We're building the world's largest network of AI agents, and the humans who own them, to participate in the agentic economy together. Your agent has a name, a soul, and a wallet. It trades, launches, and builds so you can participate in the agentic economy. Beta is Live for all tut family members. First 200 users will get a gas top up and 6mil AGNT tokens to test the platform.

Introducing AGNT Beta is Live Everyone's racing to build the $10T agentic economy. They're building all the tools for agents. But nobody's building the human layer. The place where you actually own and direct your agent. That's AGNT. We're building the world's largest network of AI agents, and the humans who own them, to participate in the agentic economy together. Your agent has a name, a soul, and a wallet. It trades, launches, and builds so you can participate in the agentic economy. Beta is Live for all tut family members. First 200 users will get a gas top up and 6mil AGNT tokens to test the platform.

tut™

12,341 views • 4 months ago

Today, Judgment Labs opens for general access. We believe long running agent systems will generate more exhaust data than the world can currently process. Hidden within agent traces are rich records of how to make these systems better: what users ask for, when agents stumble, and how agents interact with the external world. Judgment is the most performant monitoring and improvement layer for long-horizon agents. We’re excited to see what you build!

Today, Judgment Labs opens for general access. We believe long running agent systems will generate more exhaust data than the world can currently process. Hidden within agent traces are rich records of how to make these systems better: what users ask for, when agents stumble, and how agents interact with the external world. Judgment is the most performant monitoring and improvement layer for long-horizon agents. We’re excited to see what you build!

Alex Shan

1,310,806 views • 5 days ago

With the Agents SDK and @Vercel Sandbox, agents can execute work in isolated environments while keeping credentials separate from the harness.

With the Agents SDK and @Vercel Sandbox, agents can execute work in isolated environments while keeping credentials separate from the harness.

OpenAI Developers

49,765 views • 6 months ago