正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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

15,253 subscribers

18,606 次观看 • 5 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing Cognee v1.0: a major breakthrough in agentic intelligence. It is 145% better than Opus 4.8 and GPT 5.5 at long context memory retrieval. Cognee allows a 100 BILLION token context window 100,000x more than Claude. It's: - 6.9x cheaper than GPT 5.5 and Opus 4.8 - Cold starts in 350ms & searches in 260ms Why this matters: Today agents forget important context, redo tasks, waste tokens, and slow down as workflows get more complex. Cognee solves this. It’s not a place to build agents. It connects to the agents you’ve already built, across any platform, and makes them significantly cheaper, faster, and more accurate. Here's how it works:

Introducing Cognee v1.0: a major breakthrough in agentic intelligence. It is 145% better than Opus 4.8 and GPT 5.5 at long context memory retrieval. Cognee allows a 100 BILLION token context window 100,000x more than Claude. It's: - 6.9x cheaper than GPT 5.5 and Opus 4.8 - Cold starts in 350ms & searches in 260ms Why this matters: Today agents forget important context, redo tasks, waste tokens, and slow down as workflows get more complex. Cognee solves this. It’s not a place to build agents. It connects to the agents you’ve already built, across any platform, and makes them significantly cheaper, faster, and more accurate. Here's how it works:

Vasilije

837,618 次观看 • 15 天前

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

11,210 次观看 • 4 个月前

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 次观看 • 4 个月前

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

11,070 次观看 • 1 个月前

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

305,165 次观看 • 5 个月前

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 次观看 • 1 年前

I built the clipboard I always wanted for working with AI agents. It’s called Bluey and It’s 100% local-first. It lives under your mouse cursor. You can draw on your screen, speak to it, or type what you mean, and Bluey turns all of that into rich context for Claude Code or Codex. I’ve been using it to design websites and debug UI because I can finally say things like “move this here” or “make this section feel cleaner” while pointing at the actual screen. No more writing long explanations. No more manually describing screenshots. No more agents getting lost because they don’t know what “this” or "that" means. You can just point to it, speak or type and it will curate the best possible context for your agents Bluey captures the screenshot, annotation, transcript, app/window context, and the details your agent needs, then sends it directly into your coding session. I am giving it out for free for a while! Im building it with my buddy Omkar Satpute and we would love to hear what you think about it on Discord what context do you wish your agent could understand better?

I built the clipboard I always wanted for working with AI agents. It’s called Bluey and It’s 100% local-first. It lives under your mouse cursor. You can draw on your screen, speak to it, or type what you mean, and Bluey turns all of that into rich context for Claude Code or Codex. I’ve been using it to design websites and debug UI because I can finally say things like “move this here” or “make this section feel cleaner” while pointing at the actual screen. No more writing long explanations. No more manually describing screenshots. No more agents getting lost because they don’t know what “this” or "that" means. You can just point to it, speak or type and it will curate the best possible context for your agents Bluey captures the screenshot, annotation, transcript, app/window context, and the details your agent needs, then sends it directly into your coding session. I am giving it out for free for a while! Im building it with my buddy Omkar Satpute and we would love to hear what you think about it on Discord what context do you wish your agent could understand better?

Milind S

13,302 次观看 • 1 个月前

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 次观看 • 4 个月前

We gave Pi Code persistent memory with Mem0 Launching the Mem0 plugin for Pi Code: persistent, scoped, semantic memory across sessions and projects. It captures what matters, searches by meaning, and brings the right context back when your agent needs it. Try it out: pi install npm:@ mem0/pi-agent-plugin

We gave Pi Code persistent memory with Mem0 Launching the Mem0 plugin for Pi Code: persistent, scoped, semantic memory across sessions and projects. It captures what matters, searches by meaning, and brings the right context back when your agent needs it. Try it out: pi install npm:@ mem0/pi-agent-plugin

mem0

23,321 次观看 • 18 天前

I built something I believe is useful for agentic coding today. I’ve been too worried it’s not the best it can be, but my wife encouraged me to fail fast if I was worried about failure, so here we are. Introducing Kontinuo by Pull Base, the continuity layer for your AI coding agents. You’re mid-task, you hit a rate limit on Claude, and you want to keep going on Codex or Cursor. But the next agent has no idea what just happened. Kontinuo fixes that, it leaves a verifiable context log the next agent can actually use and it’s really token efficient. Check it out: Use it, break it. I hope it’s useful to at least one person.

I built something I believe is useful for agentic coding today. I’ve been too worried it’s not the best it can be, but my wife encouraged me to fail fast if I was worried about failure, so here we are. Introducing Kontinuo by Pull Base, the continuity layer for your AI coding agents. You’re mid-task, you hit a rate limit on Claude, and you want to keep going on Codex or Cursor. But the next agent has no idea what just happened. Kontinuo fixes that, it leaves a verifiable context log the next agent can actually use and it’s really token efficient. Check it out: Use it, break it. I hope it’s useful to at least one person.

Big Sheddy 🦅

47,645 次观看 • 17 天前

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 🪷

16,534 次观看 • 5 个月前

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

1,105,520 次观看 • 9 个月前

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

158,947 次观看 • 3 个月前

$Microsoft just dropped a 17-page paper - "Less Context, Better Agents" - proving the thing nobody building agents wants to admit: Your agent isn't failing because it needs more context. It's drowning in the context it already has. They ran GPT-5 four ways on one 50-task benchmark (via MCP): Full history → bloated, pricey, more errors Trim to the last 5 tool calls → 79% done Add light summarization → 91.6%, on a fraction of the tokens Less context. Fewer tokens. Higher completion. Everyone's racing to cram MORE into the window. Microsoft just published the receipt that the opposite wins for long-running agents. Rewired how I build agents this week. Paper ↓$

Microsoft just dropped a 17-page paper - "Less Context, Better Agents" - proving the thing nobody building agents wants to admit: Your agent isn't failing because it needs more context. It's drowning in the context it already has. They ran GPT-5 four ways on one 50-task benchmark (via MCP): Full history → bloated, pricey, more errors Trim to the last 5 tool calls → 79% done Add light summarization → 91.6%, on a fraction of the tokens Less context. Fewer tokens. Higher completion. Everyone's racing to cram MORE into the window. Microsoft just published the receipt that the opposite wins for long-running agents. Rewired how I build agents this week. Paper ↓

Archive

18,242 次观看 • 17 天前

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

59,064 次观看 • 2 个月前

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 次观看 • 4 个月前

We've built 40+ AI agents and internal tools. The hardest part is Context Creation. AI runs playbooks and makes judgment calls for you. But without your company's context, you get slop. Context Creation means extracting the subject matter expertise and playbooks that live in people's heads, not in LLM training data, or even your tools. As forward deployed engineers (FDEs), we create context and turn it into code. We evaluate the business impact, how it aligns with the dev roadmap, and come up with creative solutions. We built The FDE Factory to replace ourselves. It drives AI adoption inside our clients' companies by running discovery sessions using prototypes to create context. Here's how it works: We put a prototype in front of a stakeholder. The stakeholder gives feedback via voice while they're using or reviewing it. Then our FDE Factory Agents builds in their expertise in minutes: > Context Agent reviews the codebase and feedback, extracts the requirements, and creates a spec > Scope Agent checks the spec against the development roadmap, validates it, and hands it off > Engineering Agent builds a new feature and wires the integration > QA Agent runs tests to prove to itself it works > PR merges, feature goes live, product updates itself in real time It's like the nontechnical stakeholder wrote the code without even knowing it. Coding agents are great at turning good development plans into code, and they're getting better at turning context into good development plans in collaboration with professional engineers. But nontechnical people are capped on what they can build without product people and engineers. The bridge that takes nontechnical people from vibe coding basic apps to building production AI tools that run on first party context is FDEs. Our new FDE Factory gives you the system to go from idea to production. Context Creation is the first and most important step in our FDE lifecycle, and we just automated it. Now clients get the right agents and tools built for them, customized to their unique business and encoded with their expertise. PS: If you're building AI agents within your company, reply "Playbook" and I'll DM you the entire FDE playbook we've run with 30+ companies. It covers finding high-impact AI use cases, building them, and deploying them across the org.

We've built 40+ AI agents and internal tools. The hardest part is Context Creation. AI runs playbooks and makes judgment calls for you. But without your company's context, you get slop. Context Creation means extracting the subject matter expertise and playbooks that live in people's heads, not in LLM training data, or even your tools. As forward deployed engineers (FDEs), we create context and turn it into code. We evaluate the business impact, how it aligns with the dev roadmap, and come up with creative solutions. We built The FDE Factory to replace ourselves. It drives AI adoption inside our clients' companies by running discovery sessions using prototypes to create context. Here's how it works: We put a prototype in front of a stakeholder. The stakeholder gives feedback via voice while they're using or reviewing it. Then our FDE Factory Agents builds in their expertise in minutes: > Context Agent reviews the codebase and feedback, extracts the requirements, and creates a spec > Scope Agent checks the spec against the development roadmap, validates it, and hands it off > Engineering Agent builds a new feature and wires the integration > QA Agent runs tests to prove to itself it works > PR merges, feature goes live, product updates itself in real time It's like the nontechnical stakeholder wrote the code without even knowing it. Coding agents are great at turning good development plans into code, and they're getting better at turning context into good development plans in collaboration with professional engineers. But nontechnical people are capped on what they can build without product people and engineers. The bridge that takes nontechnical people from vibe coding basic apps to building production AI tools that run on first party context is FDEs. Our new FDE Factory gives you the system to go from idea to production. Context Creation is the first and most important step in our FDE lifecycle, and we just automated it. Now clients get the right agents and tools built for them, customized to their unique business and encoded with their expertise. PS: If you're building AI agents within your company, reply "Playbook" and I'll DM you the entire FDE playbook we've run with 30+ companies. It covers finding high-impact AI use cases, building them, and deploying them across the org.

Mike Fishbein

10,101 次观看 • 1 个月前

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 次观看 • 2 年前

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 次观看 • 5 个月前

Even Suppoman ❇️🔺 is using our agent Orion to generate better video titles. 🎥 The real question is: why aren’t you using it yet? Try our 3 powerful agents today:

Even Suppoman ❇️🔺 is using our agent Orion to generate better video titles. 🎥 The real question is: why aren’t you using it yet? Try our 3 powerful agents today:

OrbitAI

19,612 次观看 • 1 年前