@berryxia: Guys, the MemOS 2.0 open-source project has been updated again! It has gained 9.3K Stars on GitHub ~ This time, 'AI memory' has been upgraded from an advanced clipboard to true 'execute and learn'. Previously, many memory solutions simply stored chat logs and added semantic search, making it look like memory, but it was actually just RAG...

X AI KOLs Timeline Tools
ai-memory agent open-source learning memos

Summary

MemOS 2.0 open-source project update introduces the 'execute and learn' mechanism, enabling the AI Agent to automatically deconstruct and distill experience when completing tasks, evolving hierarchically from raw trajectories to muscle memory, resulting in a dedicated assistant that understands you better as you use it.

Guys, the MemOS 2.0 open-source project has been updated again! It has gained 9.3K Stars on GitHub ~ This time, 'AI memory' has been directly upgraded from an advanced clipboard to true 'execute and learn'. Previously, many memory solutions simply stored chat logs and added semantic search, making it look like memory, but it was actually just the same old RAG approach. The most impressive feature of the MemOS Local Plugin 2.0 this time is called 'execute and learn'. It doesn't just remember what you said; when the Agent helps you complete a task, it breaks down the entire execution process into learnable units. Which step found the key clue, which step was just an inefficient attempt, which reflection led to subsequent success. These experiences are automatically layered and refined: The bottom layer is raw trajectories; above that are general patterns; further up is the long-term world model; and the top becomes skills stored as muscle memory. A dual feedback mechanism automatically scores them, reinforcing useful ones and gradually forgetting inefficient ones. Previously, when using OpenClaw to write tools, the coding style, naming conventions, and error handling practices we honed in the first round would be lost when switching conversations or after a couple of days, and I'd have to start over from scratch. Now with 2.0, on the next day's new task, it directly applies the writing style we developed together in the previous round. This is no longer just 'remembering the context'; the Agent, while helping you work, is automatically reviewing, distilling, and evolving. The more you use it, the better it understands you, and the more it becomes your dedicated assistant. This version also supports seamless migration from Hermes and OpenClaw, can be installed with a single command, and the Memory Viewer displays the entire memory chain clearly. It's quite interesting; you can set it up for both Hermes and OpenClaw. See the comments for the link~~~
Original Article
View Cached Full Text

Cached at: 05/21/26, 05:38 PM

Folks, the MemOS 2.0 open-source project has been updated again!
It has already earned 9.3K stars on GitHub ~

This time, it upgrades “AI memory” from an advanced clipboard to a true “execute-to-learn” system.

Previously, most memory solutions simply stored chat history and added semantic search — it looked like memory, but was still just RAG in disguise.

The standout feature of the MemOS Local Plugin 2.0 is called “Execute and Learn.”

It doesn’t just remember what you said — when an Agent helps you complete a task, it breaks down the entire execution process into learnable units.

Which step found a key clue, which step was just inefficient probing, which reflection led to later success.

These experiences are automatically distilled into layers:

The bottom layer is raw traces; above that, general patterns; higher still, long-term world models; and at the top, muscle-memory skills.

A dual-feedback mechanism scores automatically — useful patterns get reinforced, inefficient ones fade over time.

Previously, when writing tools with OpenClaw, the code style, naming conventions, and error-handling approaches you refined in the first round would be lost after switching conversations or a couple of days — you’d have to explain everything from scratch.

Now with 2.0, when you start a new task the next day, it directly uses the style you worked out together in the previous session.

This isn’t just “remembering the context” anymore — the Agent, while helping you work, automatically reviews, distills, and evolves.

The more you use it, the better it understands you; the more it feels like your personal assistant.

This update also supports seamless migration for Hermes and OpenClaw — installable with a single command, and the Memory Viewer shows the entire chain of memory clearly.

Pretty interesting — both Hermes and OpenClaw can get it up and running.

Link in comments ~~~

Ears (@RookieRicardoR):
MemOS has made new progress.

There are quite a few approaches to AI Memory now, but many still stay at the level of storing chat logs — it looks like memory, but it’s essentially just adding semantic retrieval to markdown.

@MemOS_dev has been working on memory systems for a while, from 1.0 to 2.0. Looking back now, a consensus is gradually becoming clear: the next step that truly determines Agent

Similar Articles

@RookieRicardoR: MemOS has made new progress. There are quite a few AI Memory solutions now, but many are still at the level of storing chat history. It looks like memory, but it's essentially adding a semantic search to markdown. @MemOS_dev has been working on a memory system for a while, from 1.0 all the way...

X AI KOLs Timeline

MemOS Local Plugin 2.0 update has been released, introducing the "Learn by Doing" feature, which allows the agent to convert key steps during task execution into reusable, scorable cognitive assets, thereby achieving continuous learning and memory in the local environment.

@berryxia: https://x.com/berryxia/status/2084479289882194402

X AI KOLs Following

Introducing Memmy, an open-source AI memory tool that remembers projects, skills, and business process diagrams across tools. Through real-world tests, it demonstrates the ability to locate local projects, invoke Skills, and connect to business agents, emphasizing its core concept of letting multiple AI tools share a single working memory.

@berryxia: Agent memory is incredibly competitive! I have to say, the more people join this track, the better it gets! The Tencent AI team spent a full 6 months tackling just one problem: AI agents frequently dropping context in long conversations. They ended up building a complete memory system and open-sourced it directly. After reading their sharing, my biggest takeaway is...

X AI KOLs Timeline

Tencent AI has open-sourced an Agent memory system that significantly improves token efficiency and agent consistency in long dialogues through three methods: real-time context compression, Mermaid task maps, and Persona memory. Token consumption is reduced by 61%, and persona consistency jumps from 48% to 76%.