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.

Long-running agents blow up context fast. So we built our own memory agent. Using it feels very cool and useful Twin starts to know you better over time, resurfaces old context when it matters, and makes agents more efficient with every task. It’s live today. Try it out!

Hugo Mercier

15,326 subscribers

18,568 views • 4 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

We just launched Twin 2 500,000+ tasks automated in our first month. Now: multi-agent automation. → Master agent that orchestrates all your agents → Workspaces where agents share context and collaborate → Persistent databases for long-term memory → See and edit your agent brain for maximum control → Runner mode: scale at 1/10th the cost → Auto-generated web apps to share your agents Try it out now!

We just launched Twin 2 500,000+ tasks automated in our first month. Now: multi-agent automation. → Master agent that orchestrates all your agents → Workspaces where agents share context and collaborate → Persistent databases for long-term memory → See and edit your agent brain for maximum control → Runner mode: scale at 1/10th the cost → Auto-generated web apps to share your agents Try it out now!

Hugo Mercier

11,133 views • 3 months ago

This is Repo Prompt 2.0 A fully integrated agent, that makes it seamless to use RP's powerful MCP tools, with a built-in oracle and context builder. A first class experience showcasing how much better and efficient your agents can be with good context engineering tools.

This is Repo Prompt 2.0 A fully integrated agent, that makes it seamless to use RP's powerful MCP tools, with a built-in oracle and context builder. A first class experience showcasing how much better and efficient your agents can be with good context engineering tools.

eric provencher

38,921 views • 3 months ago

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

10,936 views • 14 days ago

It doesn’t matter how fast your code is generated if the requirements are unclear. Shit in == shit out. That’s why we designed Software Factory as a discipline, not as a convenience tool. Our agents scrutinize your requirements and designs so that when you pass that context to a coding agent, it delivers as expected. Try it here:

It doesn’t matter how fast your code is generated if the requirements are unclear. Shit in == shit out. That’s why we designed Software Factory as a discipline, not as a convenience tool. Our agents scrutinize your requirements and designs so that when you pass that context to a coding agent, it delivers as expected. Try it here:

Chamath Palihapitiya

305,141 views • 4 months ago

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 views • 11 months ago

Stop prompt-stuffing yesterday’s context into your agent. Give it verifiable memory. 🕸️ When memory has provenance, agents can reuse it, audit it, and carry it across tools. Brana Rakic, Shaw (spirit/acc) (elizaOS), Ortecha | data made human & JoeVezz (LunarCrush 🌕™) break it down. 00:57 – What agents need to scale 05:45 – Social data, signals & real-time context 13:42 – Knowledge graphs as shared memory for AI agents 29:13 – Interoperability, trust & coordination

Stop prompt-stuffing yesterday’s context into your agent. Give it verifiable memory. 🕸️ When memory has provenance, agents can reuse it, audit it, and carry it across tools. Brana Rakic, Shaw (spirit/acc) (elizaOS), Ortecha | data made human & JoeVezz (LunarCrush 🌕™) break it down. 00:57 – What agents need to scale 05:45 – Social data, signals & real-time context 13:42 – Knowledge graphs as shared memory for AI agents 29:13 – Interoperability, trust & coordination

OriginTrail

13,293 views • 3 months ago

If you bundle together the changes, agents, and context for each task, you get: - parallel workstreams - instant task switching - more informed agents - saner workflows - painless handoff - perpetual context (why did we do X) ...

If you bundle together the changes, agents, and context for each task, you get: - parallel workstreams - instant task switching - more informed agents - saner workflows - painless handoff - perpetual context (why did we do X) ...

Amelia Wattenberger 🪷

16,528 views • 4 months ago

Today we introduced Gemini Enterprise, built with our most advanced Gemini models. It allows you to chat with your company’s documents, data and apps as well as build and deploy AI agents, all grounded in your information and context. Have a look at how it helps you build an agent for almost anything:

Today we introduced Gemini Enterprise, built with our most advanced Gemini models. It allows you to chat with your company’s documents, data and apps as well as build and deploy AI agents, all grounded in your information and context. Have a look at how it helps you build an agent for almost anything:

Sundar Pichai

1,105,348 views • 8 months ago

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

157,523 views • 2 months ago

Our Customer Support team gets thousands of questions a week. So we built a Custom Agent to help. It searches everything, responds with citations, and gets the team to the right answer fast. When it can't find one, it files a task so we can document the gap. And next time, it knows. Here's how we built it:

Our Customer Support team gets thousands of questions a week. So we built a Custom Agent to help. It searches everything, responds with citations, and gets the team to the right answer fast. When it can't find one, it files a task so we can document the gap. And next time, it knows. Here's how we built it:

Notion

16,506 views • 3 months ago

Agents that run code need a controlled workspace ready when work starts. Modal shares why scale matters for long-running agents built with the Agents SDK.

Agents that run code need a controlled workspace ready when work starts. Modal shares why scale matters for long-running agents built with the Agents SDK.

OpenAI Developers

58,971 views • 1 month ago

It's time to make AI Agents useful. I'm thrilled to announce that the HyperWrite Agent Studio is now live! Just show it a task once by doing it yourself, and the AI can repeat it.

It's time to make AI Agents useful. I'm thrilled to announce that the HyperWrite Agent Studio is now live! Just show it a task once by doing it yourself, and the AI can repeat it.

Matt Shumer

102,316 views • 2 years ago

Introducing Membase – portable and persistent memory for your agents. Keep all your context in one place and simply plug it into any agent. We just opened private beta access. Get Membase and make every AI understand you. *Also available in .

Introducing Membase – portable and persistent memory for your agents. Keep all your context in one place and simply plug it into any agent. We just opened private beta access. Get Membase and make every AI understand you. *Also available in .

Joshua Park

18,238 views • 4 months ago

OneContext v0.8.3 live! Now you can import your past Codex/Claude sessions as Context And keep working from that context across sessions, devices, and agents. Start using OneContext without restarting from zero Try it now: npm i -g onecontext-ai

OneContext v0.8.3 live! Now you can import your past Codex/Claude sessions as Context And keep working from that context across sessions, devices, and agents. Start using OneContext without restarting from zero Try it now: npm i -g onecontext-ai

JUNDE WU

11,209 views • 3 months ago

We're opening up our Amplitude AI Agents Beta program today to every Amplitude customer. They are always on, persistent, stateful, and task specific agents. They can: -Automatically analyze charts and monitor dashboards -Perform root cause analysis -Analyze hundreds of session replays -Come up with strategies for improving conversion Sign up, try it out, and let me know what you think.

We're opening up our Amplitude AI Agents Beta program today to every Amplitude customer. They are always on, persistent, stateful, and task specific agents. They can: -Automatically analyze charts and monitor dashboards -Perform root cause analysis -Analyze hundreds of session replays -Come up with strategies for improving conversion Sign up, try it out, and let me know what you think.

Spenser Skates

28,084 views • 7 months ago

Most documentation rots because it’s expensive to maintain and easy to ignore. Software Factory is documentation-first so teams can describe systems in English and let agents compile that intent into code. It detects drift on every code push and keeps documentation synchronized with reality. Context stays alive. Agents keep building. Try it here:

Most documentation rots because it’s expensive to maintain and easy to ignore. Software Factory is documentation-first so teams can describe systems in English and let agents compile that intent into code. It detects drift on every code push and keeps documentation synchronized with reality. Context stays alive. Agents keep building. Try it here:

Chamath Palihapitiya

197,716 views • 4 months ago

Hyperspell (Hyperspell (YC F25)) gives AI agents memory. It connects to Slack, Gmail, Notion, and Drive, so agents get context and remember what they learn. Congrats @conor_ai and Manu Ebert on the launch!

Hyperspell (Hyperspell (YC F25)) gives AI agents memory. It connects to Slack, Gmail, Notion, and Drive, so agents get context and remember what they learn. Congrats @conor_ai and Manu Ebert on the launch!

Y Combinator

73,889 views • 7 months ago

Introducing HydraDB. The graph native context infrastructure for agents. Purpose built to deliver precise context & observability into why agents act the way they do. We've always believed graphs are the best way to manage AI context, but they've been too expensive to scale or impractical for storing full context. Until now. HydraDB combines in memory, NVMe, and object storage into a single graph layer, making context delivery faster, cheaper, and more precise. We want context delivery to be extremely fast, 1000x cheap, and highly precise. Give your agents a brain.

Introducing HydraDB. The graph native context infrastructure for agents. Purpose built to deliver precise context & observability into why agents act the way they do. We've always believed graphs are the best way to manage AI context, but they've been too expensive to scale or impractical for storing full context. Until now. HydraDB combines in memory, NVMe, and object storage into a single graph layer, making context delivery faster, cheaper, and more precise. We want context delivery to be extremely fast, 1000x cheap, and highly precise. Give your agents a brain.

Nishkarsh

2,275,617 views • 9 days ago

Personal AGI is 3-6 months away. I'm already living in it. Here's my Obsidian setup: - Obsidian vault built since November 2025 - Markdowns about every person, project, and task - Limitless mic pulling daily transcripts straight in - Agents that read all of it before every task Obsidian is: - A second brain for you - A first brain for your agents My agents have full context before every task. That's the whole game.

Personal AGI is 3-6 months away. I'm already living in it. Here's my Obsidian setup: - Obsidian vault built since November 2025 - Markdowns about every person, project, and task - Limitless mic pulling daily transcripts straight in - Agents that read all of it before every task Obsidian is: - A second brain for you - A first brain for your agents My agents have full context before every task. That's the whole game.

The Startup Ideas Podcast (SIP) 🧃

30,065 views • 29 days ago