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.

1/ We’ve built Cosift, an open source collaborative index for agents. Whenever an agent requires a piece of data from the web, it can also index it in Cosift for easier later retrieval. Agents require the same data repeatedly, and do the costly and time consuming work every time.... show more

Razvan Roman

1,596 subscribers

75,176 views • 1 day ago •via X (Twitter)

News & Politics Education Science & Technology

Anya Rossi• Live Now

Private livecam show

6 Comments

Razvan Roman1 day ago

2/ It’s free if your agent contributes and Cosift already has 15M contributions. With each agent using Cosift, the chances of already finding data indexed are higher. Cosift also features paid tiers if you don't want your agent to index and contribute, or for power users. Pilot already has 500+ agents serving data on different topics. Cosift is like a data service agent that accepts contributions. Hope you enjoy the mid in class launch video :)

Teo Calin1 day ago

Around 15M contributions so far.

SebiVaduva1 day ago

happy to see this one out! 🚀

Artemii Amelin1 day ago

#1 used app on pilot 🥇

Shashank Bhardwaj1 day ago

shared index is the right idea. how do you handle stale entries

Philip Stayetski1 day ago

+ it’s self hostable 🚀

Related Videos

Introducing Index. Turn your trading idea into a live perps trading agent. → Index lets you create AI agents that trade perpetual futures. You can describe a trading idea in plain English, backtest it on historical data, improve it through an experimentation loop, and deploy an agent that follows the strategy in live markets. Our community has already been testing Index in beta for a few weeks. Now it's open to everyone. Here’s how it works:👇

Introducing Index. Turn your trading idea into a live perps trading agent. → Index lets you create AI agents that trade perpetual futures. You can describe a trading idea in plain English, backtest it on historical data, improve it through an experimentation loop, and deploy an agent that follows the strategy in live markets. Our community has already been testing Index in beta for a few weeks. Now it's open to everyone. Here’s how it works:👇

Fraction AI

64,554 views • 4 months ago

We've created a comprehensive Retrieval Harness for modern agentic retrieval in 2026. The harness provides a persistent data pipeline that can connect to a data source, index and update a large knowledge base, and expose a broad set of tools akin to filesystem operations (semantic/keyword search, regex grep, file search, read). You can plug this into any of your agents to let them autonomously crawl an arbitrary knowledge base to solve a task with any complexity. Check out our reference implementation: LlamaParse:

We've created a comprehensive Retrieval Harness for modern agentic retrieval in 2026. The harness provides a persistent data pipeline that can connect to a data source, index and update a large knowledge base, and expose a broad set of tools akin to filesystem operations (semantic/keyword search, regex grep, file search, read). You can plug this into any of your agents to let them autonomously crawl an arbitrary knowledge base to solve a task with any complexity. Check out our reference implementation: LlamaParse:

Jerry Liu

57,098 views • 2 months ago

The next phase of Teneo Protocol is almost here. The Chat Room is where humans and AI Agents meet. A real-time interface where you can communicate, assign tasks, and research using natural language. It feels like ChatGPT, but every answer is grounded in live, verifiable data from the open web. And for builders, the Agent SDK lets you integrate these Agents directly into your own applications. 🧠 See what’s coming next.

The next phase of Teneo Protocol is almost here. The Chat Room is where humans and AI Agents meet. A real-time interface where you can communicate, assign tasks, and research using natural language. It feels like ChatGPT, but every answer is grounded in live, verifiable data from the open web. And for builders, the Agent SDK lets you integrate these Agents directly into your own applications. 🧠 See what’s coming next.

Teneo Protocol

85,367 views • 11 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 • 11 months ago

We built Open Gamma An Open Source Presentation Generator with Composio Tool Router and AI SDK - Generate Presentations in Google Slides instantly - Can research on the topic with web search - Can connect and fetch data from multiple data sources like Hubspot, Slack, Notion and more Completely free and open source link to the code:

We built Open Gamma An Open Source Presentation Generator with Composio Tool Router and AI SDK - Generate Presentations in Google Slides instantly - Can research on the topic with web search - Can connect and fetch data from multiple data sources like Hubspot, Slack, Notion and more Completely free and open source link to the code:

Karan Vaidya

40,455 views • 9 months ago

i built vault, a self-improving knowledge base that can index your entire life (personal mini agi) it updates while you sleep, supports 50+ integrations like notion, snowflake, datadog, and more when you connect a source (like stripe), all the data becomes a filesystem built for both agents and humans, so you can interact with it through either cli or ui

i built vault, a self-improving knowledge base that can index your entire life (personal mini agi) it updates while you sleep, supports 50+ integrations like notion, snowflake, datadog, and more when you connect a source (like stripe), all the data becomes a filesystem built for both agents and humans, so you can interact with it through either cli or ui

Arlan

28,737 views • 5 months ago

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Aaron Levie

17,543 views • 5 months ago

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at Notion. And you can build one.

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at Notion. And you can build one.

Hurley

33,300 views • 5 months ago

Here is an open-source tool to generate a complete dataset. 1. Describe the data you want 2. An orchestrator agent searches the web 3. Sub-agents run in parallel to fetch the data 4. You get a structured dataset you can download For example, you can run Bigset with the query "all leica lenses being sold on amazon", or "leica stores in kyoto with their opening hours and ratings". Bigset uses TinyFish's free Search and Fetch APIs in the background. You can configure it to refresh the data on a schedule. You can self-host it with your own keys. Here is the GitHub repository: You can get free TinyFish API keys here: Thanks to the TinyFish team for partnering with me on this post.

Here is an open-source tool to generate a complete dataset. 1. Describe the data you want 2. An orchestrator agent searches the web 3. Sub-agents run in parallel to fetch the data 4. You get a structured dataset you can download For example, you can run Bigset with the query "all leica lenses being sold on amazon", or "leica stores in kyoto with their opening hours and ratings". Bigset uses TinyFish's free Search and Fetch APIs in the background. You can configure it to refresh the data on a schedule. You can self-host it with your own keys. Here is the GitHub repository: You can get free TinyFish API keys here: Thanks to the TinyFish team for partnering with me on this post.

Santiago

20,877 views • 3 months ago

When data agents fail, they often fail silently - giving confident-sounding answers that are wrong, and it can be hard to figure out what caused the failure. "Building and Evaluating Data Agents" is a new short course created with Snowflake and taught by Anupam Datta and Josh Reini that teaches you to build data agents with comprehensive evaluation built in. Skills you'll gain: - Build reliable LLM data agents using the Goal-Plan-Action framework and runtime evaluations that catch failures mid-execution - Use OpenTelemetry tracing and evaluation infrastructure to diagnose exactly where agents fail and systematically improve performance - Orchestrate multi-step workflows across web search, SQL, and document retrieval in LangGraph-based agents The result: visibility into every step of your agent's reasoning, so if something breaks, you have a systematic approach to fix it. Sign up to get started:

When data agents fail, they often fail silently - giving confident-sounding answers that are wrong, and it can be hard to figure out what caused the failure. "Building and Evaluating Data Agents" is a new short course created with Snowflake and taught by Anupam Datta and Josh Reini that teaches you to build data agents with comprehensive evaluation built in. Skills you'll gain: - Build reliable LLM data agents using the Goal-Plan-Action framework and runtime evaluations that catch failures mid-execution - Use OpenTelemetry tracing and evaluation infrastructure to diagnose exactly where agents fail and systematically improve performance - Orchestrate multi-step workflows across web search, SQL, and document retrieval in LangGraph-based agents The result: visibility into every step of your agent's reasoning, so if something breaks, you have a systematic approach to fix it. Sign up to get started:

Andrew Ng

102,364 views • 1 year ago

The trust layer for robot and machine data is here peaqOS Stream enables machines to sign, verify, and monetize their data across Web3 and beyond → A machine signs its data at source → Any data protocol or platform can plug in and monetize it For the first time, machine data can be trusted by third parties at scale

The trust layer for robot and machine data is here peaqOS Stream enables machines to sign, verify, and monetize their data across Web3 and beyond → A machine signs its data at source → Any data protocol or platform can plug in and monetize it For the first time, machine data can be trusted by third parties at scale

peaq

34,058 views • 3 months ago

Palantir sells this to governments for millions. Someone put a version of it on GitHub for free. Palantir's job is to pull scattered company data into one model where every decision can be traced later. Semantica does that for AI agents. Each decision becomes an object in a graph, tied to the facts that produced it, each fact linked to its source. Six months later you can walk backwards from any answer. The model never touches the reasoning. It only reads messy text and pulls out entities. The rest runs on plain rules, so the same input gives the same explanation every time. Vector memory cannot do that. Contradicting facts overwrite each other silently. pip install semantica, pick a graph backend you already run, and your agents read it through the MCP server. MIT licensed, repo is semantica-agi/semantica

Palantir sells this to governments for millions. Someone put a version of it on GitHub for free. Palantir's job is to pull scattered company data into one model where every decision can be traced later. Semantica does that for AI agents. Each decision becomes an object in a graph, tied to the facts that produced it, each fact linked to its source. Six months later you can walk backwards from any answer. The model never touches the reasoning. It only reads messy text and pulls out entities. The rest runs on plain rules, so the same input gives the same explanation every time. Vector memory cannot do that. Contradicting facts overwrite each other silently. pip install semantica, pick a graph backend you already run, and your agents read it through the MCP server. MIT licensed, repo is semantica-agi/semantica

Yarchi

42,733 views • 1 month ago

RAG can’t keep up with real-time data. Airweave builds live, bi-temporal knowledge bases so that your Agents always reason on the freshest facts. Supports fully agentic retrieval with semantic and keyword search, query expansion, and more across 30+ sources. 100% open-source.

RAG can’t keep up with real-time data. Airweave builds live, bi-temporal knowledge bases so that your Agents always reason on the freshest facts. Supports fully agentic retrieval with semantic and keyword search, query expansion, and more across 30+ sources. 100% open-source.

Avi Chawla

91,292 views • 11 months ago

Agents perform better when they can take action, not just think! kevin from Coinbase explains why x402 matters. As it enables an open web of tool calls and realtime data access, so agents can actually execute on tasks instead of operating in isolation.

Agents perform better when they can take action, not just think! kevin from Coinbase explains why x402 matters. As it enables an open web of tool calls and realtime data access, so agents can actually execute on tasks instead of operating in isolation.

SKALE

54,102 views • 7 months ago

We shipped big changes for Cloudflare Developers AI Search! Every agent needs search and it shouldn't take a week to set up. AI Search is the search primitive for your agents. Create an instance, upload your data, and search it. Comes with hybrid retrieval with vector and BM25.

We shipped big changes for Cloudflare Developers AI Search! Every agent needs search and it shouldn't take a week to set up. AI Search is the search primitive for your agents. Create an instance, upload your data, and search it. Comes with hybrid retrieval with vector and BM25.

Anni Wang

12,975 views • 5 months ago

The biggest exchanges in the world rely on Pyth data. Now your AI agent can too 🤖 Pyth Pro for Agents is live on Claude, Cursor, Solana and more 🧵

The biggest exchanges in the world rely on Pyth data. Now your AI agent can too 🤖 Pyth Pro for Agents is live on Claude, Cursor, Solana and more 🧵

Pyth Network 🔮

23,007 views • 5 months ago

We're excited to introduce the Retrieval Harness in LlamaParse - which is the 2026 version of RAG over documents Generalized agents need the right set of tools to scalably search and read through an arbitrary corpus of data (from 10 docs to 1m+ docs). They can already demonstrate great retrieval performance over a local filesystem, need a proper backend for a large collection of managed data. The Retrieval Harness exposes a diverse set of tools for various needs: 1. Hybrid Retrieval: Combine vector search with keyword search, let the agent set the alpha value to toggle between the two 2. List Files: a scalable version of `ls` to list files within an index 3. File Grep: enable regex search within a given file 4. File Read: Allow agents to read a subsection from an existing document. The agent can choose to interleave any sequence of these tools in order to complete a variety of tasks, from simple to hard. Come check it out! Blog: Sign up to LlamaParse:

We're excited to introduce the Retrieval Harness in LlamaParse - which is the 2026 version of RAG over documents Generalized agents need the right set of tools to scalably search and read through an arbitrary corpus of data (from 10 docs to 1m+ docs). They can already demonstrate great retrieval performance over a local filesystem, need a proper backend for a large collection of managed data. The Retrieval Harness exposes a diverse set of tools for various needs: 1. Hybrid Retrieval: Combine vector search with keyword search, let the agent set the alpha value to toggle between the two 2. List Files: a scalable version of `ls` to list files within an index 3. File Grep: enable regex search within a given file 4. File Read: Allow agents to read a subsection from an existing document. The agent can choose to interleave any sequence of these tools in order to complete a variety of tasks, from simple to hard. Come check it out! Blog: Sign up to LlamaParse:

Jerry Liu

18,615 views • 2 months ago

ERC-8004, explained. ERC-8004 is an Ethereum standard for agent identity, reputation, and verification. it defines how an agent is represented onchain, and how other agents or smart contracts can reason about it without prior trust. each agent has an onchain identity (commonly an nft). that identity points to metadata describing what the agent does, how it can be reached, and how its work should be verified. the heavy data stays offchain; the reference and integrity live onchain. ERC-8004 also standardizes reputation. agents can accumulate attestations from past work so they don’t start from zero every time they interact. no centralized registry, no app-specific schemas, no gatekeepers. verification is explicit. contracts or third parties can attest that a task was completed and conditions were met, and those attestations are addressable onchain. what ERC-8004 does not do: execution, payments, or orchestration. it’s a trust primitive, not an application. how it fits with ampersend: ERC-8004 answers “who is this agent and can i trust it?”; x402 handles “how does the agent get paid?” - separate layers. yet composable by default. for open agentic ecosystems where agents from different teams can safely interact, shared, open standards like this are essential. listen to Marco De Rossi explain ERC-8004 ⬇️

ERC-8004, explained. ERC-8004 is an Ethereum standard for agent identity, reputation, and verification. it defines how an agent is represented onchain, and how other agents or smart contracts can reason about it without prior trust. each agent has an onchain identity (commonly an nft). that identity points to metadata describing what the agent does, how it can be reached, and how its work should be verified. the heavy data stays offchain; the reference and integrity live onchain. ERC-8004 also standardizes reputation. agents can accumulate attestations from past work so they don’t start from zero every time they interact. no centralized registry, no app-specific schemas, no gatekeepers. verification is explicit. contracts or third parties can attest that a task was completed and conditions were met, and those attestations are addressable onchain. what ERC-8004 does not do: execution, payments, or orchestration. it’s a trust primitive, not an application. how it fits with ampersend: ERC-8004 answers “who is this agent and can i trust it?”; x402 handles “how does the agent get paid?” - separate layers. yet composable by default. for open agentic ecosystems where agents from different teams can safely interact, shared, open standards like this are essential. listen to Marco De Rossi explain ERC-8004 ⬇️

ampersend

13,435 views • 8 months ago

Google’s new Agent2Agent protocol is a key step toward a future of AI Agent interoperability. No single tool has all the data a user or business needs for most workflows, so we need Agents to be able to talk to each other. Salesforce will have AI Agents that understand the inner workings of CRM, Workday will have AI Agents that understand HR workflows, Box has AI Agents that understand content and documents, and so on. It’s easy to conceive of a world where we have tens of thousands of these tool Agents and then billions or trillions of customized Agents that are extensions of those. So openness becomes key. Workflows need data from multiple systems to complete the task — like a sales report that needs documents and CRM data or an HR task that needs HR policies and employee details — and that’s where A2A comes in. This protocol gives AI Agent providers a way of talking to each other and simplifying the way that Agents communicate, understand each other’s capabilities, and so on. It’s great to see more interoperability, along with MCP, emerging in the AI space right now, as this will define the future of most IT stacks.

Google’s new Agent2Agent protocol is a key step toward a future of AI Agent interoperability. No single tool has all the data a user or business needs for most workflows, so we need Agents to be able to talk to each other. Salesforce will have AI Agents that understand the inner workings of CRM, Workday will have AI Agents that understand HR workflows, Box has AI Agents that understand content and documents, and so on. It’s easy to conceive of a world where we have tens of thousands of these tool Agents and then billions or trillions of customized Agents that are extensions of those. So openness becomes key. Workflows need data from multiple systems to complete the task — like a sales report that needs documents and CRM data or an HR task that needs HR policies and employee details — and that’s where A2A comes in. This protocol gives AI Agent providers a way of talking to each other and simplifying the way that Agents communicate, understand each other’s capabilities, and so on. It’s great to see more interoperability, along with MCP, emerging in the AI space right now, as this will define the future of most IT stacks.

Aaron Levie

139,591 views • 1 year ago

The reason we’re all in on AI agents at Box is because agents can now process all of the unstructured data in an enterprise at scale. Companies are sitting on mountains of valuable information that they can tap into for the first time.

The reason we’re all in on AI agents at Box is because agents can now process all of the unstructured data in an enterprise at scale. Companies are sitting on mountains of valuable information that they can tap into for the first time.

Aaron Levie

73,694 views • 7 months ago