MemOS

<div align="center">
  <a href="https://memos.openmem.net/">
    <img src="https://statics.memtensor.com.cn/memos/memos-banner.gif" alt="MemOS Banner">
  </a>

  <h1 align="center">
    <img src="https://statics.memtensor.com.cn/logo/memos_color_m.png" alt="MemOS Logo" width="48"/>&nbsp;
    MemOS 2.0&ensp;Stardust（星尘）

  </h1>

<p align="center">
  <br>
  <a href="https://memos-docs.openmem.net/home/overview/"><img src="https://img.shields.io/badge/Docs-Get--Start-002FA7?labelColor=gray&style=for-the-badge&logo=googledocs&logoColor=white" alt="Docs"></a>
  <a href="https://arxiv.org/abs/2507.03724"><img src="https://img.shields.io/badge/ArXiv-2507.03724-B31B1B?labelColor=gray&style=for-the-badge&logo=arxiv&logoColor=white" alt="ArXiv"></a>
  <a href="https://x.com/MemOS_dev"><img src="https://img.shields.io/badge/Follow-MemOS-000000?labelColor=gray&style=for-the-badge&logo=x&logoColor=white" alt="X"></a>
  <a href="https://discord.gg/Txbx3gebZR"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Fv10%2Finvites%2FTxbx3gebZR%3Fwith_counts%3Dtrue&query=%24.approximate_presence_count&suffix=%20online&label=Discord&color=404EED&labelColor=gray&style=for-the-badge&logo=discord&logoColor=white" alt="Discord"></a>
  <a href="https://github.com/IAAR-Shanghai/Awesome-AI-Memory"><img src="https://img.shields.io/badge/Resources-Awesome--AI--Memory-8A2BE2?labelColor=gray&style=for-the-badge&logo=awesomelists&logoColor=white" alt="Resources"></a>
</p>

<p align="center">
  <strong>🎯 +43.70% Accuracy vs. OpenAI Memory</strong><br/>
  <strong>🏆 Top-tier Long-term Memory + Personalization</strong><br/>
  <strong>💰 Saves 35.24% Memory Tokens</strong><br/>
  <sub>LoCoMo 75.80 • LongMemEval +40.43% • PrefEval-10 +2568% • PersonaMem +40.75%</sub>
  <!-- <a href="https://memos.openmem.net/">
    <img src="https://statics.memtensor.com.cn/memos/github_api_free_banner.gif" alt="MemOS Free API Banner">
  </a> -->

</p>

</div>

<!-- Get Free API: [Try API](https://memos-dashboard.openmem.net/quickstart/?source=github) -->

<!-- --- -->

<!-- <br> -->

## 🧠 MemOS Plugin: Persistent Memory for Your AI Agents ✨

<div align="center">
  
<img width="1660" height="664" alt="MemOS Plugin Banner" src="https://github.com/user-attachments/assets/9d15dde2-196e-4f71-a364-dd5a33062117" />

Your lobsters and Hermes Agents now have **the best** memory system — choose ***Cloud Service*** or ***Self-hosted*** to get started 🏃🏻

| 🔌 Plugin | <div align="center"> 💡 Core Features </div> | 🧩 Resources |
| :----: | :--- | :---: |
| 👧🏻 [**Hermes Agent Local Plugin**](https://x.com/MemOS_dev/status/2043400241232458204) | <ul><li>Visual Management via Web UI.</li><li>100% local, Hybrid retrieval, Smart dedup,<br>Skill evolution, Multi-Agent knowledge hub. </li></ul> | 📑 [Docs](https://memos-docs.openmem.net/cn/openclaw/hermes_local_plugin) · 🐙 [GitHub](https://github.com/MemTensor/MemOS/tree/main/apps/memos-local-plugin) |
| ☁️ [**OpenClaw Cloud Plugin**](https://x.com/MemOS_dev/status/2019254160919769171?s=20) | <ul><li>[Reduces token usage by 72%.](https://x.com/MemOS_dev/status/2020854044583924111)</li><li>[Multi-agent memory sharing by `user_id`.](https://x.com/MemOS_dev/status/2020538135487062094)</li></ul> | 🖥️ [MemOS Dashboard](https://memos-dashboard.openmem.net/login/) · 📖 [Full Tutorial](https://memos-docs.openmem.net/openclaw/guide#_4-update-plugin) |
| 🦐 [**OpenClaw Local Plugin**](https://x.com/MemOS_dev/status/2031342078480019505) | <ul><li>0 cloud dependency by local SQLite.</li><li>FTS5 + vector search, Task auto-summarization,<br>Multi-Agent memory isolation & skill sharing.</li></ul> | 🌐 [Homepage](https://memos-claw.openmem.net) · 📑 [Docs](https://memos-claw.openmem.net/docs) · 📦 [NPM](https://www.npmjs.com/package/@memtensor/memos-local-openclaw-plugin) |

</div>
<br>

## 👾 MemOS: Memory Operating System for LLM & AI Agents

**MemOS** is a Memory Operating System for LLMs and AI agents that unifies **store / retrieve / manage** for long-term memory, enabling **context-aware and personalized** interactions with **KB**, **multi-modal**, **tool memory**, and **enterprise-grade** optimizations built in.


### Key Features

- **Unified Memory API**: A single API to add, retrieve, edit, and delete memory—structured as a graph, inspectable and editable by design, not a black-box embedding store.
- **Multi-Modal Memory**: Natively supports text, images, tool traces, and personas, retrieved and reasoned together in one memory system.
- **Multi-Cube Knowledge Base Management**: Manage multiple knowledge bases as composable memory cubes, enabling isolation, controlled sharing, and dynamic composition across users, projects, and agents.
- **Asynchronous Ingestion via MemScheduler**: Run memory operations asynchronously with millisecond-level latency for production stability under high concurrency.
- **Memory Feedback & Correction**: Refine memory with natural-language feedback—correcting, supplementing, or replacing existing memories over time.


### News

- **2026-04-10** · 👧🏻 **MemOS Hermes Agent Local Plugin**
  Official Hermes Agent memory plugins launched: Hybrid retrieval (FTS5 + vector), smart dedup, tiered skill evolution, multi-agent collaboration. 100% local, zero cloud dependency.

- **2026-03-08** · 🦞 **MemOS OpenClaw Plugin — Cloud & Local**
  Official OpenClaw memory plugins launched. **Cloud Plugin**: hosted memory service with 72% lower token usage and multi-agent memory sharing ([MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/MemOS-Cloud-OpenClaw-Plugin)). **Local Plugin** (`v1.0.0`): 100% on-device memory with persistent SQLite, hybrid search (FTS5 + vector), task summarization & skill evolution, multi-agent collaboration, and a full Memory Viewer dashboard.

- **2025-12-24** · 🎉 **MemOS v2.0: Stardust (星尘) Release**
  Comprehensive KB (doc/URL parsing + cross-project sharing), memory feedback & precise deletion, multi-modal memory (images/charts), tool memory for agent planning, Redis Streams scheduling + DB optimizations, streaming/non-streaming chat, MCP upgrade, and lightweight quick/full deployment.
  <details>
    <summary>✨ <b>New Features</b></summary>

  **Knowledge Base & Memory**
  - Added knowledge base support for long-term memory from documents and URLs

  **Feedback & Memory Management**
  - Added natural language feedback and correction for memories
  - Added memory deletion API by memory ID
  - Added MCP support for memory deletion and feedback

  **Conversation & Retrieval**
  - Added chat API with memory-aware retrieval
  - Added memory filtering with custom tags (Cloud & Open Source)

  **Multimodal & Tool Memory**
  - Added tool memory for tool usage history
  - Added image memory support for conversations and documents

  </details>

  <details>
    <summary>📈 <b>Improvements</b></summary>

  **Data & Infrastructure**
  - Upgraded database for better stability and performance

  **Scheduler**
  - Rebuilt task scheduler with Redis Streams and queue isolation
  - Added task priority, auto-recovery, and quota-based scheduling

  **Deployment & Engineering**
  - Added lightweight deployment with quick and full modes

  </details>

  <details>
    <summary>🐞 <b>Bug Fixes</b></summary>

  **Memory Scheduling & Updates**
  - Fixed legacy scheduling API to ensure correct memory isolation
  - Fixed memory update logging to show new memories correctly

  </details>

- **2025-08-07** · 🎉 **MemOS v1.0.0 (MemCube) Release**
  First MemCube release with a word-game demo, LongMemEval evaluation, BochaAISearchRetriever integration, improved search capabilities, and the official Playground launch.

  <details>
    <summary>✨ <b>New Features</b></summary>

  **Playground**
  - Expanded Playground features and algorithm performance.

  **MemCube Construction**
  - Added a text game demo based on the MemCube novel.

  **Extended Evaluation Set**
  - Added LongMemEval evaluation results and scripts.

  </details>

  <details>
    <summary>📈 <b>Improvements</b></summary>

  **Plaintext Memory**
  - Integrated internet search with Bocha.
  - Expanded graph database support.
  - Added contextual understanding for the tree-structured plaintext memory search interface.

  </details>

  <details>
    <summary>🐞 <b>Bug Fixes</b></summary>

  **KV Cache Concatenation**
  - Fixed the concat_cache method.

  **Plaintext Memory**
  - Fixed graph search-related issues.

  </details>

- **2025-07-07** · 🎉 **MemOS v1.0: Stellar (星河) Preview Release**
  A SOTA Memory OS for LLMs is now open-sourced.
- **2025-07-04** · 🎉 **MemOS Paper Release**
  [MemOS: A Memory OS for AI System](https://arxiv.org/abs/2507.03724) is available on arXiv.
- **2024-07-04** · 🎉 **Memory3 Model Release at WAIC 2024**
  The Memory3 model, featuring a memory-layered architecture, was unveiled at the 2024 World Artificial Intelligence Conference.

<br>

## 🚀 Quick-start Guide

### ☁️ 1、Cloud API (Hosted)
#### Get API Key
- Sign up on the [MemOS dashboard](https://memos-dashboard.openmem.net/cn/quickstart/?source=landing)
- Go to **API Keys** and copy your key

#### Next Steps
- [MemOS Cloud Getting Started](https://memos-docs.openmem.net/memos_cloud/quick_start/)
  Connect to MemOS Cloud and enable memory in minutes.
- [MemOS Cloud Platform](https://memos.openmem.net/?from=/quickstart/)
  Explore the Cloud dashboard, features, and workflows.

### 🖥️ 2、Self-Hosted (Local/Private)
1. Get the repository.
    ```bash
    git clone https://github.com/MemTensor/MemOS.git
    cd MemOS
    pip install -r ./docker/requirements.txt
    ```
2. Configure `docker/.env.example` and copy to `MemOS/.env`
 - The `OPENAI_API_KEY`,`MOS_EMBEDDER_API_KEY`,`MEMRADER_API_KEY` and others can be applied for through [`BaiLian`](https://bailian.console.aliyun.com/?spm=a2c4g.11186623.0.0.2f2165b08fRk4l&tab=api#/api).
 - Fill in the corresponding configuration in the `MemOS/.env` file.
 - Supported LLM providers: **Op