正在加载视频...

视频加载失败

返回首页

We analyzed Anthropic’s memory architecture and built something better: a persistent, human-inspectable, and token-efficient memory layer that scales with your projects. Today, it’s OPEN-SOURCE. ByteRover CLI gives agents (like OpenClaw, Claude Code, and Hermes) persistent, structured memory. Built on the exact architecture that became the #1 memory system for...

kevinnguyendn's profile picture

andy nguyen

3,446 subscribers

28,980 次观看 • 5 个月前 •via X (Twitter)

教育新闻政治科学技术
LIVE

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

Memory for OpenClaw is now Native! Our first OpenClaw Memory Skill was a massive success: 30k+ downloads in a week and 500k+ organic impressions overnight for launch post. But we knew memory needed to be native. On March 21, OpenClaw merged PR #50848, allowing us to go beyond the skill layer and integrate directly into the agent’s context assembly flow. We try to make OpenClaw a truly 24/7 employee capable of complex workflows. The technical setup isn’t the hardest part but the real challenge is giving it a "brain" that remembers exact project details, past decisions, and team changes over time. The Native Memory Plugin is now live on NPM & ClawHub. Here is what it brings to your OpenClaw agents: 👉 Native Integration: Automatically manages a Three-Layer Memory architecture (Context Tree, Workspace Memory, Daily Memory). 👉 Git-like Stateful Memory: Organizes memory into a semantic hierarchy of human-readable, diffable Markdown files. You always get updated knowledge and can actually see and fix what your agent learns. 👉 Top Market Accuracy: Achieves an industry-leading 92.2% retrieval accuracy (LoCoMo & LongMemEval benchmarks), maintaining 90% accuracy even with cheap, lightweight models. 👉 Local-first & Portable: Local-by-default, fully portable for multi-agent teams. 👉 Super Easy Setup
1:46

Memory for OpenClaw is now Native! Our first OpenClaw Memory Skill was a massive success: 30k+ downloads in a week and 500k+ organic impressions overnight for launch post. But we knew memory needed to be native. On March 21, OpenClaw merged PR #50848, allowing us to go beyond the skill layer and integrate directly into the agent’s context assembly flow. We try to make OpenClaw a truly 24/7 employee capable of complex workflows. The technical setup isn’t the hardest part but the real challenge is giving it a "brain" that remembers exact project details, past decisions, and team changes over time. The Native Memory Plugin is now live on NPM & ClawHub. Here is what it brings to your OpenClaw agents: 👉 Native Integration: Automatically manages a Three-Layer Memory architecture (Context Tree, Workspace Memory, Daily Memory). 👉 Git-like Stateful Memory: Organizes memory into a semantic hierarchy of human-readable, diffable Markdown files. You always get updated knowledge and can actually see and fix what your agent learns. 👉 Top Market Accuracy: Achieves an industry-leading 92.2% retrieval accuracy (LoCoMo & LongMemEval benchmarks), maintaining 90% accuracy even with cheap, lightweight models. 👉 Local-first & Portable: Local-by-default, fully portable for multi-agent teams. 👉 Super Easy Setup

andy nguyen

169,442 次观看 • 5 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!
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 次观看 • 5 个月前

Memory Skill for OpenClaw with 26k+ users in 1 week🚀 OpenClaw's memory system is broken by default. It requires curating massive MEMORY.md files or relying on duplicate-heavy generation. Hours are wasted tuning, and massive amounts of tokens are burned. It's time to stop. So we built the memory skill to solve that prob Here is our superpower ⚔️ 🎯 Top #1 market accuracy (92.19%) after 8+ months of intense architecture iteration 🧠 The ultimate solution to keep the timeline, facts, and meaning perfectly in place ☁️ Local & Cloud + Version control ⚡ Super easy setup
2:26

Memory Skill for OpenClaw with 26k+ users in 1 week🚀 OpenClaw's memory system is broken by default. It requires curating massive MEMORY.md files or relying on duplicate-heavy generation. Hours are wasted tuning, and massive amounts of tokens are burned. It's time to stop. So we built the memory skill to solve that prob Here is our superpower ⚔️ 🎯 Top #1 market accuracy (92.19%) after 8+ months of intense architecture iteration 🧠 The ultimate solution to keep the timeline, facts, and meaning perfectly in place ☁️ Local & Cloud + Version control ⚡ Super easy setup

andy nguyen

589,959 次观看 • 6 个月前

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.
0:50

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.

NO1ennn

13,359 次观看 • 1 个月前

Clude is now available as a custom connector on Anthropic Claude. Giving it persistent memory across every conversation. It remembers your projects, your preferences, and the decisions you make, so you never start from zero again. Use Clude across Chat / Co-Work and Claude Code. Add it in 30 seconds, no API key: 1. In Claude: Customize, Add custom connector URL: Enter your email. That's it. Recap for people unfamiliar: Clude deviates from the traditional vector database that many others bolt onto Claude. We are a cognitive memory system modeled on how human memory works. Think traditional memory systems: Calculator > It computes. Fullstop. Excel > Dynamic, formula run, able to share and manipulate Clude scored 86% on LongMemEval, one of the toughest long-term memory benchmarks. This means less hallucinations to traditional platforms. It scores memories by relevance, recency, and importance, links them into a knowledge graph, and consolidates them over time. Tell Claude something, open a new chat, and watch it remember.
0:39

Clude is now available as a custom connector on Anthropic Claude. Giving it persistent memory across every conversation. It remembers your projects, your preferences, and the decisions you make, so you never start from zero again. Use Clude across Chat / Co-Work and Claude Code. Add it in 30 seconds, no API key: 1. In Claude: Customize, Add custom connector URL: Enter your email. That's it. Recap for people unfamiliar: Clude deviates from the traditional vector database that many others bolt onto Claude. We are a cognitive memory system modeled on how human memory works. Think traditional memory systems: Calculator > It computes. Fullstop. Excel > Dynamic, formula run, able to share and manipulate Clude scored 86% on LongMemEval, one of the toughest long-term memory benchmarks. This means less hallucinations to traditional platforms. It scores memories by relevance, recency, and importance, links them into a knowledge graph, and consolidates them over time. Tell Claude something, open a new chat, and watch it remember.

seb

20,611 次观看 • 2 个月前

We’re excited to launch OpenMemory MCP, a private memory for MCP-compatible clients powered by mem0 Today, most AI assistants and dev tools operate without memory. You plan your roadmap in Claude, implement tasks in Cursor, but none of them know what the other did. Each tool operates in isolation, and your context disappears as soon as the session ends. OpenMemory MCP solves this. Built on the open Model Context Protocol (MCP), OpenMemory MCP runs 100% locally and provides a persistent, portable memory layer for all your AI tools. It enables agents and assistants to read from and write to a shared memory, securely and privately. Key capabilities: ✅Works across MCP clients like Cursor, Claude Desktop, Windsurf, Cline and more ✅Provides standardized memory operations (add_memories, search_memory, list_memories, delete_all_memories) ✅Stores data on your machine, fully private ✅Offers a centralized dashboard for visibility and control ✅Simple Docker-based setup with no vendor lock-in If you're building on MCP, OpenMemory MCP is the easiest way to add persistent, private memory to your clients with zero cloud dependencies and full local control. We’ve put together a short demo to show how it works Check it out in the links below 👇
2:24

We’re excited to launch OpenMemory MCP, a private memory for MCP-compatible clients powered by mem0 Today, most AI assistants and dev tools operate without memory. You plan your roadmap in Claude, implement tasks in Cursor, but none of them know what the other did. Each tool operates in isolation, and your context disappears as soon as the session ends. OpenMemory MCP solves this. Built on the open Model Context Protocol (MCP), OpenMemory MCP runs 100% locally and provides a persistent, portable memory layer for all your AI tools. It enables agents and assistants to read from and write to a shared memory, securely and privately. Key capabilities: ✅Works across MCP clients like Cursor, Claude Desktop, Windsurf, Cline and more ✅Provides standardized memory operations (add_memories, search_memory, list_memories, delete_all_memories) ✅Stores data on your machine, fully private ✅Offers a centralized dashboard for visibility and control ✅Simple Docker-based setup with no vendor lock-in If you're building on MCP, OpenMemory MCP is the easiest way to add persistent, private memory to your clients with zero cloud dependencies and full local control. We’ve put together a short demo to show how it works Check it out in the links below 👇

Taranjeet

472,126 次观看 • 1 年前

Google just showed how AI engineers are moving from simple "RAG" to "graphs", memory and multimodal agents • 15:32 - setting up the production agent stack • 28:00 - turning disconnected data into a knowledge graph • 41:00 - Graph RAG with semantic + hybrid search • 58:00 - extracting graph context from images, text and video • 1:09:00 - orchestrating specialized agents with ADK • 1:20:00 - giving agents persistent memory across sessions 94-minute Google Cloud workshop, and it’s one of the clearest hands-on examples of the shift from -> RAG → Graph RAG → Memory → Multimodal Agent Graphs. The workshop uses Spanner Graph, Gemini, ADK and Memory Bank to build that stack. Watch it today, then read the full “From RAG to Context Graphs” roadmap below.
1:30:26

Google just showed how AI engineers are moving from simple "RAG" to "graphs", memory and multimodal agents • 15:32 - setting up the production agent stack • 28:00 - turning disconnected data into a knowledge graph • 41:00 - Graph RAG with semantic + hybrid search • 58:00 - extracting graph context from images, text and video • 1:09:00 - orchestrating specialized agents with ADK • 1:20:00 - giving agents persistent memory across sessions 94-minute Google Cloud workshop, and it’s one of the clearest hands-on examples of the shift from -> RAG → Graph RAG → Memory → Multimodal Agent Graphs. The workshop uses Spanner Graph, Gemini, ADK and Memory Bank to build that stack. Watch it today, then read the full “From RAG to Context Graphs” roadmap below.

Morlex

74,134 次观看 • 1 个月前

New course on serving LLMs efficiently -- how do you serve models to many concurrent users at low latency and reasonable cost? This short course is built with Red Hat and taught by Cedric Clyburn. Efficient LLM serving requires efficient memory management. A 70B-parameter model takes ~140 GB just to load the weights. On top of that, every active request needs its own chunk of GPU memory, the KV cache, to store the token context it has built up so far. In this course, you'll learn to reduce a model's memory footprint with quantization and serve it using vLLM, which handles many concurrent requests efficiently through smart memory management. Skills you'll gain: - Quantize a model and measure the accuracy tradeoff - Serve a model with vLLM and watch it handle concurrent requests efficiently - Benchmark your deployment and make informed tradeoffs between speed, cost, and accuracy Join and learn to serve LLMs efficiently:
2:11

New course on serving LLMs efficiently -- how do you serve models to many concurrent users at low latency and reasonable cost? This short course is built with Red Hat and taught by Cedric Clyburn. Efficient LLM serving requires efficient memory management. A 70B-parameter model takes ~140 GB just to load the weights. On top of that, every active request needs its own chunk of GPU memory, the KV cache, to store the token context it has built up so far. In this course, you'll learn to reduce a model's memory footprint with quantization and serve it using vLLM, which handles many concurrent requests efficiently through smart memory management. Skills you'll gain: - Quantize a model and measure the accuracy tradeoff - Serve a model with vLLM and watch it handle concurrent requests efficiently - Benchmark your deployment and make informed tradeoffs between speed, cost, and accuracy Join and learn to serve LLMs efficiently:

Andrew Ng

135,137 次观看 • 3 个月前

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.
0:34

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

SIBYL

85,997 次观看 • 3 个月前

Introducing Merge’s Universal Context Layer. It substantially decreases token cost while increasing accuracy. Every company uses AI wrong: Say your designer makes a deck using Claude. They teach Claude your design systems and typography. Now a Marketing hire makes a deck. None of the information your designer taught Claude gets passed over… why? Merge fixes this: All knowledge and memory across your entire company gets stored inside our context layer. When someone on the org teaches Al, that skill lives across the entire organization instead of staying locked in their session. Your AI runs faster, cheaper, and with more accuracy. You don’t have to switch systems, incur more costs, or retrain anyone on your team, Merge runs invisibly in the background. Book a demo here:
1:23

Introducing Merge’s Universal Context Layer. It substantially decreases token cost while increasing accuracy. Every company uses AI wrong: Say your designer makes a deck using Claude. They teach Claude your design systems and typography. Now a Marketing hire makes a deck. None of the information your designer taught Claude gets passed over… why? Merge fixes this: All knowledge and memory across your entire company gets stored inside our context layer. When someone on the org teaches Al, that skill lives across the entire organization instead of staying locked in their session. Your AI runs faster, cheaper, and with more accuracy. You don’t have to switch systems, incur more costs, or retrain anyone on your team, Merge runs invisibly in the background. Book a demo here:

Shensi Ding

564,286 次观看 • 2 天前

I gave my local AI agents persistent memory without sending a single byte to a cloud API. It’s called Hindsight. Instead of your agent forgetting everything the moment a session ends, it extracts facts, builds a knowledge graph, and recalls exactly what matters, next time you ask. → Three core operations: retain (store a fact), recall (search memories), reflect (reason across everything it knows), not just a vector database bolted onto a chatbot → Runs fully local when paired with Ollama, no API keys, no cloud costs, and no user data transiting through a third-party provider → Ships as an MCP server out of the box, so Claude, Cursor, or any MCP-compatible client gets persistent memory in one Docker command → Builds “mental models,” living summaries that auto-update as memories accumulate, instead of you re-reading a growing pile of raw logs → Per-user memory isolation lets you run one instance for multiple people or agents without their memories bleeding into each other → Reports top results on the LongMemEval long-term memory benchmark, per the project’s own published numbers Every AI agent today is stateless by default, it knows nothing about yesterday’s conversation unless you re-paste it. Hindsight’s answer: real structured memory, running on your own hardware if you want it there. MIT License. Built by
1:12

I gave my local AI agents persistent memory without sending a single byte to a cloud API. It’s called Hindsight. Instead of your agent forgetting everything the moment a session ends, it extracts facts, builds a knowledge graph, and recalls exactly what matters, next time you ask. → Three core operations: retain (store a fact), recall (search memories), reflect (reason across everything it knows), not just a vector database bolted onto a chatbot → Runs fully local when paired with Ollama, no API keys, no cloud costs, and no user data transiting through a third-party provider → Ships as an MCP server out of the box, so Claude, Cursor, or any MCP-compatible client gets persistent memory in one Docker command → Builds “mental models,” living summaries that auto-update as memories accumulate, instead of you re-reading a growing pile of raw logs → Per-user memory isolation lets you run one instance for multiple people or agents without their memories bleeding into each other → Reports top results on the LongMemEval long-term memory benchmark, per the project’s own published numbers Every AI agent today is stateless by default, it knows nothing about yesterday’s conversation unless you re-paste it. Hindsight’s answer: real structured memory, running on your own hardware if you want it there. MIT License. Built by

Harman

11,032 次观看 • 1 个月前

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇
20:54

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇

YanXbt

22,720 次观看 • 2 个月前

HERMES AGENT CAN SHARE MEMORY WITH CODEX AND CLAUDE CODE THROUGH HINDSIGHT. ONE MEMORY BANK. ONE AGENT REMEMBERS, EVERY OTHER AGENT KNOWS. the problem: you use Hermes for orchestration. Codex for coding. Claude Code for debugging. each has its own memory. switch between them and you explain the same project three times. Hindsight fixes this. one shared memory bank that every agent reads and writes to. tell Codex: "the test color for this project is purple." switch to Hermes. ask: "what test color did I pick?" Hermes answers: "purple." no copy-paste. no re-explaining. instant recall. HOW IT WORKS: Hindsight runs as a Docker container on your machine. self-hosted. your data stays local. an LLM powers the memory processing (retain, recall, reflect). RETAIN: extracts facts from your conversations. entities, decisions, preferences, project context. saved to the memory bank automatically. RECALL: when you ask a question, Hindsight pulls from semantic search, keywords, graph connections, and temporal data. fused into one answer. REFLECT: deeper reasoning layer. connects memories across sessions. identifies patterns in your work. produces observations that get smarter over time. CONNECT TO HERMES: Desktop app: Settings → Memory and Context → switch provider from Namosin to Hindsight. set API URL to your local Docker container. set bank ID. done. CLI: hermes memory setup → select Hindsight. verify: hermes memory status should show: provider: hindsight, installed, available. CONNECT TO CODEX: npx hindsight-coding-agents install codex \ --self-hosted --server this installs lifecycle hooks: initialize memory on session start. recall context during work. retain the session when done. enable hooks in Codex: Settings → Hooks → trust all three. CONNECT TO CLAUDE CODE (same command): npx hindsight-coding-agents install all "all" connects every detected agent on your machine. Claude Code, Codex, Cursor, and others. one command. every agent shares the same bank. TAGS FOR FILTERING: every memory gets tagged by harness (Hermes, Codex, Claude Code) and optionally by project name. in the Hindsight control plane: filter by harness. see only Hermes memories. or only Codex memories. or search across everything. soft partitions inside one bank. not hard walls. cross-reference when you need to. ONE BANK OR MANY: one global bank: solo dev, related projects. all agents share everything. patterns emerge across projects. per-project banks: unrelated codebases. each project gets its own memory. no cross-contamination. your call. start with one. split when projects diverge. KNOWLEDGE PAGES (v0.9.0): Hindsight auto-generates living summaries from your accumulated memories. components, concepts, conventions, decisions. not static docs. projected from real agent conversations. auto-refresh as new memories land. WHAT TO KNOW: self-hosted via Docker. your data never leaves your machine. backup system built in (admin CLI + scheduled exports). works with any LLM (local Ollama, OpenAI, Codex subscription). memory defense: redact or block sensitive content automatically. 33,000+ memories accumulated in ~10 days of normal use.
34:12

HERMES AGENT CAN SHARE MEMORY WITH CODEX AND CLAUDE CODE THROUGH HINDSIGHT. ONE MEMORY BANK. ONE AGENT REMEMBERS, EVERY OTHER AGENT KNOWS. the problem: you use Hermes for orchestration. Codex for coding. Claude Code for debugging. each has its own memory. switch between them and you explain the same project three times. Hindsight fixes this. one shared memory bank that every agent reads and writes to. tell Codex: "the test color for this project is purple." switch to Hermes. ask: "what test color did I pick?" Hermes answers: "purple." no copy-paste. no re-explaining. instant recall. HOW IT WORKS: Hindsight runs as a Docker container on your machine. self-hosted. your data stays local. an LLM powers the memory processing (retain, recall, reflect). RETAIN: extracts facts from your conversations. entities, decisions, preferences, project context. saved to the memory bank automatically. RECALL: when you ask a question, Hindsight pulls from semantic search, keywords, graph connections, and temporal data. fused into one answer. REFLECT: deeper reasoning layer. connects memories across sessions. identifies patterns in your work. produces observations that get smarter over time. CONNECT TO HERMES: Desktop app: Settings → Memory and Context → switch provider from Namosin to Hindsight. set API URL to your local Docker container. set bank ID. done. CLI: hermes memory setup → select Hindsight. verify: hermes memory status should show: provider: hindsight, installed, available. CONNECT TO CODEX: npx hindsight-coding-agents install codex \ --self-hosted --server this installs lifecycle hooks: initialize memory on session start. recall context during work. retain the session when done. enable hooks in Codex: Settings → Hooks → trust all three. CONNECT TO CLAUDE CODE (same command): npx hindsight-coding-agents install all "all" connects every detected agent on your machine. Claude Code, Codex, Cursor, and others. one command. every agent shares the same bank. TAGS FOR FILTERING: every memory gets tagged by harness (Hermes, Codex, Claude Code) and optionally by project name. in the Hindsight control plane: filter by harness. see only Hermes memories. or only Codex memories. or search across everything. soft partitions inside one bank. not hard walls. cross-reference when you need to. ONE BANK OR MANY: one global bank: solo dev, related projects. all agents share everything. patterns emerge across projects. per-project banks: unrelated codebases. each project gets its own memory. no cross-contamination. your call. start with one. split when projects diverge. KNOWLEDGE PAGES (v0.9.0): Hindsight auto-generates living summaries from your accumulated memories. components, concepts, conventions, decisions. not static docs. projected from real agent conversations. auto-refresh as new memories land. WHAT TO KNOW: self-hosted via Docker. your data never leaves your machine. backup system built in (admin CLI + scheduled exports). works with any LLM (local Ollama, OpenAI, Codex subscription). memory defense: redact or block sensitive content automatically. 33,000+ memories accumulated in ~10 days of normal use.

YanXbt

29,200 次观看 • 24 天前

Sharing a super simple, user-owned memory module we've been playing around: nanomem The basic idea is to treat memory as a pure intelligence problem: ingestion, structuring, and (selective) retrieval are all just LLM calls & agent loops on a on-device markdown file tree. Each file lists a set of facts w/ metadata (timestamp, confidence, source, etc.); no embeddings/RAG/training of any kind. For example: - `nanomem add ` starts an agent loop to walk the tree, read relevant files, and edit. - `nanomem retrieve ` walks the tree and returns a single summary string (possibly assembled from many subtrees) related to the query. What’s nice about this approach is that the memory system is, by construction: 1. partitionable (human/agents can easily separate `hobbies/snowboard.md` from `tax/residency.md` for data minimization + relevance) 2. portable and user-owned (it’s just text files) 3. interpretable (you know exactly what’s written and you can manually edit) 4. forward-compatible (future models can read memory files just the same, and memory quality/speed improves as models get better) 5. modularized (you can optimize ingestion/retrieval/compaction prompts separately) Privacy & utility. I'm most excited about the ability to partition + selectively disclose memory at inference-time. Selective disclosure helps with both privacy (principle of least privilege & “need-to-know”) and utility (as too much context for a query can harm answer quality). Composability. An inference-time memory module means: (1) you can run such a module with confidential inference (LLMs on TEEs) for provable privacy, and (2) you can selectively disclose context over unlinkable inference of remote models (demo below). We built nanomem as part of the Open Anonymity project ( but it’s meant to be a standalone module for humans and agents (e.g., you can write a SKILL for using the CLI tool). Still polishing the rough edges! - GitHub (MIT): - Blog: - Beta implementation in chat client soon: Work done with amazing project co-leads Amelia Kuang Coco Xu Erik Chi !!
0:29

Sharing a super simple, user-owned memory module we've been playing around: nanomem The basic idea is to treat memory as a pure intelligence problem: ingestion, structuring, and (selective) retrieval are all just LLM calls & agent loops on a on-device markdown file tree. Each file lists a set of facts w/ metadata (timestamp, confidence, source, etc.); no embeddings/RAG/training of any kind. For example: - `nanomem add ` starts an agent loop to walk the tree, read relevant files, and edit. - `nanomem retrieve ` walks the tree and returns a single summary string (possibly assembled from many subtrees) related to the query. What’s nice about this approach is that the memory system is, by construction: 1. partitionable (human/agents can easily separate `hobbies/snowboard.md` from `tax/residency.md` for data minimization + relevance) 2. portable and user-owned (it’s just text files) 3. interpretable (you know exactly what’s written and you can manually edit) 4. forward-compatible (future models can read memory files just the same, and memory quality/speed improves as models get better) 5. modularized (you can optimize ingestion/retrieval/compaction prompts separately) Privacy & utility. I'm most excited about the ability to partition + selectively disclose memory at inference-time. Selective disclosure helps with both privacy (principle of least privilege & “need-to-know”) and utility (as too much context for a query can harm answer quality). Composability. An inference-time memory module means: (1) you can run such a module with confidential inference (LLMs on TEEs) for provable privacy, and (2) you can selectively disclose context over unlinkable inference of remote models (demo below). We built nanomem as part of the Open Anonymity project ( but it’s meant to be a standalone module for humans and agents (e.g., you can write a SKILL for using the CLI tool). Still polishing the rough edges! - GitHub (MIT): - Blog: - Beta implementation in chat client soon: Work done with amazing project co-leads Amelia Kuang Coco Xu Erik Chi !!

Ken Liu

74,970 次观看 • 5 个月前

If you use Cursor for coding, Claude Code for debugging, and local agents for automation, you almost certainly have a context problem. Every tool acts like an isolated employee. One assistant forgets what the other just learned. The biggest bottleneck in multi-agent workflows right now isn’t reasoning. It’s collective amnesia, combined with zero communication between agents. Memmy just launched a smart fix for this: a local, cross-agent memory layer. Instead of re-pasting your context everywhere, Memmy gives your stack a shared memory hub: → accumulate knowledge once, then use it across Cursor, Codex, and OpenClaw → automatically scan and import your existing agent history, so you don’t have to start from zero → keep your memory local, while model usage depends on your chosen provider or BYOK setup And it isn’t just a memory plugin. It’s a complete personal AI runtime with both MCP and a CLI. Memmy officially launched on Product Hunt, and the team is giving early users experiencing context fragmentation a free trial with 2M GPT tokens. Check it out and support the team with an upvote: → Best part? It’s also open-source for devs who want to build their own agents 🔥 Repo in 🧵↓
3:29

If you use Cursor for coding, Claude Code for debugging, and local agents for automation, you almost certainly have a context problem. Every tool acts like an isolated employee. One assistant forgets what the other just learned. The biggest bottleneck in multi-agent workflows right now isn’t reasoning. It’s collective amnesia, combined with zero communication between agents. Memmy just launched a smart fix for this: a local, cross-agent memory layer. Instead of re-pasting your context everywhere, Memmy gives your stack a shared memory hub: → accumulate knowledge once, then use it across Cursor, Codex, and OpenClaw → automatically scan and import your existing agent history, so you don’t have to start from zero → keep your memory local, while model usage depends on your chosen provider or BYOK setup And it isn’t just a memory plugin. It’s a complete personal AI runtime with both MCP and a CLI. Memmy officially launched on Product Hunt, and the team is giving early users experiencing context fragmentation a free trial with 2M GPT tokens. Check it out and support the team with an upvote: → Best part? It’s also open-source for devs who want to build their own agents 🔥 Repo in 🧵↓

Charly Wargnier

203,456 次观看 • 1 个月前

researchers gave a tiny local model human-style memory and its context limit basically stopped existing a team from MBZUAI, Princeton and Weizmann took a 1B model and rebuilt how it reads. instead of attending to everything at once, the model reads in 1,024 token chunks and passes the important stuff forward through an associative memory, the same way you carry the plot of a book between chapters without rereading them. the design mirrors human memory on purpose. full attention inside a chunk works as short-term memory. the module that carries information between chunks works as long-term memory. they even trained it like a person, starting with short easy texts and raising the difficulty gradually, because memory thrown into the deep end learns nothing. the numbers back it up. the normal model burns 40GB of GPU memory on a long document and collapses hard past its limit, dropping from 0.86 to 0.32 accuracy. the memory version holds 0.71 at double that length while using a flat 12GB no matter how long the input gets. it also needs about 30% fewer FLOPs. the part i keep thinking about is that nobody scaled anything here. they didn't build a bigger model, didn't stretch the window, didn't add compute. they looked at how a brain handles a long day and copied the architecture. a model small enough to run on a consumer gpu now survives documents its own architecture used to choke on. we keep treating intelligence as a compute problem. sometimes it's a memory problem.
0:43

researchers gave a tiny local model human-style memory and its context limit basically stopped existing a team from MBZUAI, Princeton and Weizmann took a 1B model and rebuilt how it reads. instead of attending to everything at once, the model reads in 1,024 token chunks and passes the important stuff forward through an associative memory, the same way you carry the plot of a book between chapters without rereading them. the design mirrors human memory on purpose. full attention inside a chunk works as short-term memory. the module that carries information between chunks works as long-term memory. they even trained it like a person, starting with short easy texts and raising the difficulty gradually, because memory thrown into the deep end learns nothing. the numbers back it up. the normal model burns 40GB of GPU memory on a long document and collapses hard past its limit, dropping from 0.86 to 0.32 accuracy. the memory version holds 0.71 at double that length while using a flat 12GB no matter how long the input gets. it also needs about 30% fewer FLOPs. the part i keep thinking about is that nobody scaled anything here. they didn't build a bigger model, didn't stretch the window, didn't add compute. they looked at how a brain handles a long day and copied the architecture. a model small enough to run on a consumer gpu now survives documents its own architecture used to choke on. we keep treating intelligence as a compute problem. sometimes it's a memory problem.

Alex Veremeyenko

16,147 次观看 • 1 个月前

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code
0:50

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code

monokern

64,312 次观看 • 3 个月前

AMD JUST KILLED THE $200 - A - MONTH AI SUBSCRIPTION - A 65-WATT BOX WITH 128GB OF UNIFIED MEMORY THAT RUNS 70B MODELS LOCALLY. that clip is amd's ryzen ai max+ 395 mini box, held up on stage. the whole pitch is one spec: 128gb of high-speed unified memory. why it matters: cpu, gpu and npu share the same 128gb pool, so a model that used to need a rack of vram just fits. what it actually runs: llama 70b in full precision on the built-in gpu open models up to ~100b parameters, locally, no cloud all of it in a mini pc pulling around 65 watts that's the part that ends the subscription: your prompts, your data, your model, on a box on your desk, not metered by the token. honest line: this runs open models, not gpt-5 or claude opus. for chat, coding help and agents on your own data it's more than enough. for the absolute frontier, the cloud still wins. and it isn't free: the box runs ~$1,500 and up. but that's a few months of a $200 sub, then it's yours forever. no monthly ai bill, no tokens metered, no prompt leaving the room. the uncomfortable part isn't that amd made a fast box. it's that "you need the cloud for ai" was a pricing choice, and unified memory just made it optional. follow RetroChainer for the hardware that turns rent into ownership, and bookmark this before your next ai renewal.
0:41

AMD JUST KILLED THE $200 - A - MONTH AI SUBSCRIPTION - A 65-WATT BOX WITH 128GB OF UNIFIED MEMORY THAT RUNS 70B MODELS LOCALLY. that clip is amd's ryzen ai max+ 395 mini box, held up on stage. the whole pitch is one spec: 128gb of high-speed unified memory. why it matters: cpu, gpu and npu share the same 128gb pool, so a model that used to need a rack of vram just fits. what it actually runs: llama 70b in full precision on the built-in gpu open models up to ~100b parameters, locally, no cloud all of it in a mini pc pulling around 65 watts that's the part that ends the subscription: your prompts, your data, your model, on a box on your desk, not metered by the token. honest line: this runs open models, not gpt-5 or claude opus. for chat, coding help and agents on your own data it's more than enough. for the absolute frontier, the cloud still wins. and it isn't free: the box runs ~$1,500 and up. but that's a few months of a $200 sub, then it's yours forever. no monthly ai bill, no tokens metered, no prompt leaving the room. the uncomfortable part isn't that amd made a fast box. it's that "you need the cloud for ai" was a pricing choice, and unified memory just made it optional. follow RetroChainer for the hardware that turns rent into ownership, and bookmark this before your next ai renewal.

RetroChainer

16,995 次观看 • 1 个月前

AI Agent Teams, DeFi Builders & Enterprises; this is the infrastructure you’ve been waiting for. Menese Protocol delivers entirely on-chain execution that is 100% trustless, non-custodial, and sovereign across 50+ blockchains with full composability into every DeFi protocol. No bridges. No custodians. No off-chain components. No single point of failure. Your autonomous AI agents gain native superpowers with $MENES $ICP $BTC $SOL $ETH $SUI and 50+ others: • Instant token swaps, liquidity provision, and 0% fixed-interest borrowing — executed directly on-chain • OpenClaw native plugin or lightweight SDK for fast integration • Smart contract brain for persistent state, memory, and autonomy (state survives even if the agent is replaced) • Built on Internet Computer threshold cryptography for true 24/7 sovereign operation Build with us. #AIAgents #DeFi #Multichain #OnChain #Trustless #NonCustodial #EnterpriseDeFi #BuiltOnICP #ICP #MeneseProtocol
0:37

AI Agent Teams, DeFi Builders & Enterprises; this is the infrastructure you’ve been waiting for. Menese Protocol delivers entirely on-chain execution that is 100% trustless, non-custodial, and sovereign across 50+ blockchains with full composability into every DeFi protocol. No bridges. No custodians. No off-chain components. No single point of failure. Your autonomous AI agents gain native superpowers with $MENES $ICP $BTC $SOL $ETH $SUI and 50+ others: • Instant token swaps, liquidity provision, and 0% fixed-interest borrowing — executed directly on-chain • OpenClaw native plugin or lightweight SDK for fast integration • Smart contract brain for persistent state, memory, and autonomy (state survives even if the agent is replaced) • Built on Internet Computer threshold cryptography for true 24/7 sovereign operation Build with us. #AIAgents #DeFi #Multichain #OnChain #Trustless #NonCustodial #EnterpriseDeFi #BuiltOnICP #ICP #MeneseProtocol

Menese Protocol

17,749 次观看 • 4 个月前

AutoGPT might be the next big step in AI. Here's why Karpathy recently said "AutoGPT is the next frontier of prompt engineering" AutoGPT is the equivalent of giving GPT-based models a memory and a body. You can now give a task to an AI agent and have it autonomously come up with a plan, execute on it, browse the web, and use new data to revise the strategy until the task is completed. It can analyze the market and come up with a trading strategy, customer service, marketing, finance, or other tasks that requires continuous updates. There are three components to it: 1. Architecture: It leverages GPT-4 and GPT-3.5 via API. 2. Autonomous Iterations: AutoGPT can refine its outputs by self-critical review, building on its previous work and integrating prompt history for more accurate results. 3. Memory Management: Integration with Pinecone allows for long-term memory storage, enabling context preservation and improved decision-making. 4. Multi-functionality: Capabilities include file manipulation, web browsing, and data retrieval, distinguishing AutoGPT from previous AI advancements by broadening its application scope.
0:29

AutoGPT might be the next big step in AI. Here's why Karpathy recently said "AutoGPT is the next frontier of prompt engineering" AutoGPT is the equivalent of giving GPT-based models a memory and a body. You can now give a task to an AI agent and have it autonomously come up with a plan, execute on it, browse the web, and use new data to revise the strategy until the task is completed. It can analyze the market and come up with a trading strategy, customer service, marketing, finance, or other tasks that requires continuous updates. There are three components to it: 1. Architecture: It leverages GPT-4 and GPT-3.5 via API. 2. Autonomous Iterations: AutoGPT can refine its outputs by self-critical review, building on its previous work and integrating prompt history for more accurate results. 3. Memory Management: Integration with Pinecone allows for long-term memory storage, enabling context preservation and improved decision-making. 4. Multi-functionality: Capabilities include file manipulation, web browsing, and data retrieval, distinguishing AutoGPT from previous AI advancements by broadening its application scope.

Lior Alexander

808,154 次观看 • 3 年前