Загрузка видео...

Не удалось загрузить видео

На главную

🧠 Can agent memory scale without losing reasoning? 🔥 We’re excited to share our latest work, SimpleMem, a principled memory framework for LLM agents built around semantic lossless compression. 📉 30× fewer inference tokens 📈 +26.4% avg F1 (vs Mem0) ⚡ 50.2% faster retrieval (vs Mem0) Instead of storing...

HuaxiuYaoML's profile picture

Huaxiu Yao

6,763 subscribers

119,812 просмотров • 8 месяцев назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🚀 SimpleMem MCP is now LIVE & Open Source! Experience SimpleMem as a cloud-hosted memory service with fast retrieval, fewer tokens, and persistent memory - all exposed via MCP. Easily integrate with Cursor, Claude Desktop, LM Studio, Cherry Studio, and more. 👉 Try it now: 🔗 Code: Nice work again @JiaqiLiu835914, Yaofeng Su, Peng (Richard) Xia, Siwei Han, and great collab. w/ Cihang Xie, Zeyu Zheng, Mingyu Ding
0:38

🚀 SimpleMem MCP is now LIVE & Open Source! Experience SimpleMem as a cloud-hosted memory service with fast retrieval, fewer tokens, and persistent memory - all exposed via MCP. Easily integrate with Cursor, Claude Desktop, LM Studio, Cherry Studio, and more. 👉 Try it now: 🔗 Code: Nice work again @JiaqiLiu835914, Yaofeng Su, Peng (Richard) Xia, Siwei Han, and great collab. w/ Cihang Xie, Zeyu Zheng, Mingyu Ding

Huaxiu Yao

16,015 просмотров • 7 месяцев назад

🚀 SimpleMem now supports Claude Skills! Use SimpleMem in to remember long-term information and project history across conversations. Register at 👉 🔗 Detailed Code: Try it out and let us know what you think! @JiaqiLiu835914, Yaofeng Su, Peng (Richard) Xia, Siwei Han, Cihang Xie, Zeyu Zheng, Mingyu Ding
0:37

🚀 SimpleMem now supports Claude Skills! Use SimpleMem in to remember long-term information and project history across conversations. Register at 👉 🔗 Detailed Code: Try it out and let us know what you think! @JiaqiLiu835914, Yaofeng Su, Peng (Richard) Xia, Siwei Han, Cihang Xie, Zeyu Zheng, Mingyu Ding

Huaxiu Yao ✈️ ICML 2026

22,937 просмотров • 7 месяцев назад

Introducing mem0 CLI 🚀 Give your agents memory from the terminal - add, search, and retrieve memory - remember agents + developers's preference - agent-first, JSON schema-driven We built mem0 CLI to help agents remember Get started npm install -g @mem0/cli Open source 👇
0:36

Introducing mem0 CLI 🚀 Give your agents memory from the terminal - add, search, and retrieve memory - remember agents + developers's preference - agent-first, JSON schema-driven We built mem0 CLI to help agents remember Get started npm install -g @mem0/cli Open source 👇

Taranjeet

20,567 просмотров • 5 месяцев назад

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
0:43

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

24,925 просмотров • 2 месяцев назад

Open sourcing Dynamic Graph Memory by mem0. Memory is fundamental to human reasoning, shaping how we approach tasks and make decisions. At Mem0, we believe that AI agents & apps should reflect this principle. Our Dynamic Graph Memory emulates human memory, advancing AI agents toward more intelligent, human-like reasoning. This is a significant step forward in building AI that truly understands and interacts with the world like we do. All credit to Dev Khant Deshraj Yadav Prateek Chhikara for their countless nights spent on bringing this to life. Link:
0:26

Open sourcing Dynamic Graph Memory by mem0. Memory is fundamental to human reasoning, shaping how we approach tasks and make decisions. At Mem0, we believe that AI agents & apps should reflect this principle. Our Dynamic Graph Memory emulates human memory, advancing AI agents toward more intelligent, human-like reasoning. This is a significant step forward in building AI that truly understands and interacts with the world like we do. All credit to Dev Khant Deshraj Yadav Prateek Chhikara for their countless nights spent on bringing this to life. Link:

Taranjeet

51,129 просмотров • 2 лет назад

🚀 Say hello to the new & improved phidata 🚀 Build, ship, and monitor Agents with blazing-fast memory, knowledge, tools & reasoning 🔥 ⚡️ 70% faster memory & knowledge 🛠 100+ tools 🧠 Reasoning Agents 🤝 Multi-agent collaboration 📊 Built-in monitoring and Agent UI
0:34

🚀 Say hello to the new & improved phidata 🚀 Build, ship, and monitor Agents with blazing-fast memory, knowledge, tools & reasoning 🔥 ⚡️ 70% faster memory & knowledge 🛠 100+ tools 🧠 Reasoning Agents 🤝 Multi-agent collaboration 📊 Built-in monitoring and Agent UI

Ashpreet Bedi

114,568 просмотров • 1 год назад

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!
1:37

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

161,260 просмотров • 5 месяцев назад

We’re thrilled to open-source TriAttention! 🚀 🦞 Deploy OpenClaw (32B LLM) on a single 24GB RTX 4090 locally 💻Full code open-source & vLLM-ready for one-click deployment ⚡️ 2.5× faster inference speed & 10.7× less KV cache memory usage TriAttention is a novel KV cache compression method built on rigorous trigonometric analysis in the Pre‑RoPE space for efficient LLM long reasoning. Github Repo: Paper Link: Homepage:
0:28

We’re thrilled to open-source TriAttention! 🚀 🦞 Deploy OpenClaw (32B LLM) on a single 24GB RTX 4090 locally 💻Full code open-source & vLLM-ready for one-click deployment ⚡️ 2.5× faster inference speed & 10.7× less KV cache memory usage TriAttention is a novel KV cache compression method built on rigorous trigonometric analysis in the Pre‑RoPE space for efficient LLM long reasoning. Github Repo: Paper Link: Homepage:

Yukang Chen

199,051 просмотров • 5 месяцев назад

Excited to share our new work: StreamingVLM! 🚀 We tackle a major challenge for Vision-Language Models (VLMs): understanding infinite video streams in real-time without latency blowing up or running out of memory. Paper: Code:
2:26

Excited to share our new work: StreamingVLM! 🚀 We tackle a major challenge for Vision-Language Models (VLMs): understanding infinite video streams in real-time without latency blowing up or running out of memory. Paper: Code:

Guangxuan Xiao

92,141 просмотров • 10 месяцев назад

CNVS went viral for the wrong reason... the Ui is beautiful, but the CNVS cross agent memory system is world class. ultra simple & based on actual research. talking between multiple agents, codex, cursor, claude, starts to feel like one brain that actually understands your project. CNVS memory is just files agents read on demand and on Mem0's own benchmark, that approach beats Mem0 (74% vs 68.5%). Append-only JSONL every agent reads & writes directly. No DB. No embeddings. No service to be down. memory is scoped per canvas (project) increasing the specificity of the context. NO BLOAT, just clean and on demand. the least complex solution always works best.
0:33

CNVS went viral for the wrong reason... the Ui is beautiful, but the CNVS cross agent memory system is world class. ultra simple & based on actual research. talking between multiple agents, codex, cursor, claude, starts to feel like one brain that actually understands your project. CNVS memory is just files agents read on demand and on Mem0's own benchmark, that approach beats Mem0 (74% vs 68.5%). Append-only JSONL every agent reads & writes directly. No DB. No embeddings. No service to be down. memory is scoped per canvas (project) increasing the specificity of the context. NO BLOAT, just clean and on demand. the least complex solution always works best.

Max Blade

21,522 просмотров • 2 месяцев назад

Andrej Karpathy just broke the entire premise of modern AI: "The new computer isn't a chip - It's a language model running agent loops." Agents talking to agents -loops spawning sub-loops The stack being built RIGHT NOW: agent loop + memory + sub-agents + harness In a 20-minute talk, Karpathy explain the full reasoning stack
17:31

Andrej Karpathy just broke the entire premise of modern AI: "The new computer isn't a chip - It's a language model running agent loops." Agents talking to agents -loops spawning sub-loops The stack being built RIGHT NOW: agent loop + memory + sub-agents + harness In a 20-minute talk, Karpathy explain the full reasoning stack

Ricker

31,924 просмотров • 1 месяц назад

Augment Agent is now live. Designed for large-scale codebases — with 200K context tokens, persistent memory, and deep tool integrations, Augment Agent is available in VS Code and JetBrains.
8:21

Augment Agent is now live. Designed for large-scale codebases — with 200K context tokens, persistent memory, and deep tool integrations, Augment Agent is available in VS Code and JetBrains.

Augment Code

147,773 просмотров • 1 год назад

Most active projects carry a few memories that quietly contradict each other. We built something for that! Introducing Dream, the background layer that keeps mem0 memory clean, current, and true. → Merge: facts that repeat get folded into one clear memory → Supersede: the old fact stays as history, the new fact becomes the truth → Synthesis: not one memory — a pattern built from many, traced back to each one Excited to share that we're live today on Pro and Enterprise!
1:00

Most active projects carry a few memories that quietly contradict each other. We built something for that! Introducing Dream, the background layer that keeps mem0 memory clean, current, and true. → Merge: facts that repeat get folded into one clear memory → Supersede: the old fact stays as history, the new fact becomes the truth → Synthesis: not one memory — a pattern built from many, traced back to each one Excited to share that we're live today on Pro and Enterprise!

mem0

10,499 просмотров • 1 месяц назад

Introducing Mem1: Memory framework for AI. It is the blind implementation of the Mem0 research paper which I've been working on and off for last couple of weeks. Completely self-hosted. Also, made a CLI assistant to accompany it. It also performed well with around 70-75% accuracy on a large dataset.
1:11

Introducing Mem1: Memory framework for AI. It is the blind implementation of the Mem0 research paper which I've been working on and off for last couple of weeks. Completely self-hosted. Also, made a CLI assistant to accompany it. It also performed well with around 70-75% accuracy on a large dataset.

water

25,977 просмотров • 9 месяцев назад

Agents, for real work. The latest Visual Studio Code release gives you better agent orchestration, extensibility, and continuity. Here's what's new: 🪝 Hooks support 🎯 Message steering and queueing 🌐 Agentic integrated browser 🧠 Shared memory And more...
0:59

Agents, for real work. The latest Visual Studio Code release gives you better agent orchestration, extensibility, and continuity. Here's what's new: 🪝 Hooks support 🎯 Message steering and queueing 🌐 Agentic integrated browser 🧠 Shared memory And more...

Visual Studio Code

255,429 просмотров • 6 месяцев назад

What if robots could think longer on harder problems without saying a single word?🤔 We introduce RD-VLA (Recurrent-Depth VLA): a latent, iterative reasoning architecture for robot control. ❌No Chain-of-Thought tokens. ❌No extra memory overhead. ✅Just reasoning—directly in latent space. 🧠🤖 Project page: 👇🧵
1:22

What if robots could think longer on harder problems without saying a single word?🤔 We introduce RD-VLA (Recurrent-Depth VLA): a latent, iterative reasoning architecture for robot control. ❌No Chain-of-Thought tokens. ❌No extra memory overhead. ✅Just reasoning—directly in latent space. 🧠🤖 Project page: 👇🧵

Jiafei Duan

13,949 просмотров • 7 месяцев назад

All your Agents, shared Memory. Memory belongs to your work, not the agent.
0:36

All your Agents, shared Memory. Memory belongs to your work, not the agent.

Joe Fernandez

1,182,033 просмотров • 4 месяцев назад

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!
2:57

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

201,127 просмотров • 1 год назад