addressed conflicts

Author: tangg555

README.md

@@ -43,7 +43,7 @@
 
 ---
 
-<img src="https://statics.memtensor.com.cn/memos/sota_score.jpg" alt="SOTA SCORE">
+<img src="https://cdn.memtensor.com.cn/img/1762436050812_3tgird_compressed.png" alt="SOTA SCORE">
 
 **MemOS** is an operating system for Large Language Models (LLMs) that enhances them with long-term memory capabilities. It allows LLMs to store, retrieve, and manage information, enabling more context-aware, consistent, and personalized interactions.
 
@@ -52,6 +52,28 @@
 - **API Reference**: https://memos-docs.openmem.net/docs/api/info/
 - **Source Code**: https://github.com/MemTensor/MemOS
 
+## 📰 News
+
+Stay up to date with the latest MemOS announcements, releases, and community highlights.
+
+
+- **2025-11-06** - 🎉 MemOS v1.1.3 (Async Memory & Preference):
+  Millisecond-level async memory add (support plain-text-memory and
+  preference memory); enhanced BM25, graph recall, and mixture search; full
+  results & code for LoCoMo, LongMemEval, PersonaMem, and PrefEval released.
+- **2025-10-30** - 🎉 MemOS v1.1.2 (API & MCP Update):
+API architecture overhaul and full MCP (Model Context Protocol) support — enabling models, IDEs, and agents to read/write external memory directly.
+- **2025-09-10** - 🎉 *MemOS v1.0.1 (Group Q&A Bot)*: Group Q&A bot based on MemOS Cube, updated KV-Cache performance comparison data across different GPU deployment schemes, optimized test benchmarks and statistics, added plaintext memory Reranker sorting, optimized plaintext memory hallucination issues, and Playground version updates. [Try PlayGround](https://memos-playground.openmem.net/login/)
+- **2025-08-07** - 🎉 *MemOS v1.0.0 (MemCube Release)*: First MemCube with word game demo, LongMemEval evaluation, BochaAISearchRetriever integration, NebulaGraph support, enhanced search capabilities, and official Playground launch.
+- **2025-07-29** – 🎉 *MemOS v0.2.2 (Nebula Update)*: Internet search+Nebula DB integration, refactored memory scheduler, KV Cache stress tests, MemCube Cookbook release (CN/EN), and 4b/1.7b/0.6b memory ops models.
+- **2025-07-21** – 🎉 *MemOS v0.2.1 (Neo Release)*: Lightweight Neo version with plaintext+KV Cache functionality, Docker/multi-tenant support, MCP expansion, and new Cookbook/Mud game examples.
+- **2025-07-11** – 🎉 *MemOS v0.2.0 (Cross-Platform)*: Added doc search/bilingual UI, MemReader-4B (local deploy), full Win/Mac/Linux support, and playground end-to-end connection.
+- **2025-07-07** – 🎉 *MemOS 1.0 (Stellar) Preview Release*: A SOTA Memory OS for LLMs is now open-sourced.
+- **2025-07-04** – 🎉 *MemOS Paper Released*: [MemOS: A Memory OS for AI System](https://arxiv.org/abs/2507.03724) was published on arXiv.
+- **2025-05-28** – 🎉 *Short Paper Uploaded*: [MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models](https://arxiv.org/abs/2505.22101) was published on arXiv.
+- **2024-07-04** – 🎉 *Memory3 Model Released at WAIC 2024*: The new memory-layered architecture model was unveiled at the 2024 World Artificial Intelligence Conference.
+- **2024-07-01** – 🎉 *Memory3 Paper Released*: [Memory3: Language Modeling with Explicit Memory](https://arxiv.org/abs/2407.01178) introduces the new approach to structured memory in LLMs.
+
 ## 📈 Performance Benchmark
 
 MemOS demonstrates significant improvements over baseline memory solutions in multiple memory tasks,
@@ -81,6 +103,27 @@ showcasing its capabilities in **information extraction**, **temporal and cross-
 
 ## 🚀 Getting Started
 
+### ⭐️ MemOS online API
+The easiest way to use MemOS. Equip your agent with memory **in minutes**!
+
+Sign up and get started on[`MemOS dashboard`](https://memos-dashboard.openmem.net/cn/quickstart/?source=landing).
+
+
+### Self-Hosted Server
+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`
+3. Start the service.
+```bash
+uvicorn memos.api.server_api:app --host 0.0.0.0 --port 8001 --workers 8
+```
+
+### Local SDK
 Here's a quick example of how to create a **`MemCube`**, load it from a directory, access its memories, and save it.
 
 ```python
@@ -102,7 +145,7 @@ for item in mem_cube.act_mem.get_all():
 mem_cube.dump("tmp/mem_cube")
 ```
 
-What about **`MOS`** (Memory Operating System)? It's a higher-level orchestration layer that manages multiple MemCubes and provides a unified API for memory operations. Here's a quick example of how to use MOS:
+**`MOS`** (Memory Operating System) is a higher-level orchestration layer that manages multiple MemCubes and provides a unified API for memory operations. Here's a quick example of how to use MOS:
 
 ```python
 from memos.configs.mem_os import MOSConfig
@@ -244,19 +287,3 @@ We welcome contributions from the community! Please read our [contribution guide
 ## 📄 License
 
 MemOS is licensed under the [Apache 2.0 License](./LICENSE).
-
-## 📰 News
-
-Stay up to date with the latest MemOS announcements, releases, and community highlights.
-
-
-- **2025-09-10** - 🎉 *MemOS v1.0.1 (Group Q&A Bot)*: Group Q&A bot based on MemOS Cube, updated KV-Cache performance comparison data across different GPU deployment schemes, optimized test benchmarks and statistics, added plaintext memory Reranker sorting, optimized plaintext memory hallucination issues, and Playground version updates. [Try PlayGround](https://memos-playground.openmem.net/login/)
-- **2025-08-07** - 🎉 *MemOS v1.0.0 (MemCube Release)*: First MemCube with word game demo, LongMemEval evaluation, BochaAISearchRetriever integration, NebulaGraph support, enhanced search capabilities, and official Playground launch.
-- **2025-07-29** – 🎉 *MemOS v0.2.2 (Nebula Update)*: Internet search+Nebula DB integration, refactored memory scheduler, KV Cache stress tests, MemCube Cookbook release (CN/EN), and 4b/1.7b/0.6b memory ops models.
-- **2025-07-21** – 🎉 *MemOS v0.2.1 (Neo Release)*: Lightweight Neo version with plaintext+KV Cache functionality, Docker/multi-tenant support, MCP expansion, and new Cookbook/Mud game examples.
-- **2025-07-11** – 🎉 *MemOS v0.2.0 (Cross-Platform)*: Added doc search/bilingual UI, MemReader-4B (local deploy), full Win/Mac/Linux support, and playground end-to-end connection.
-- **2025-07-07** – 🎉 *MemOS 1.0 (Stellar) Preview Release*: A SOTA Memory OS for LLMs is now open-sourced.
-- **2025-07-04** – 🎉 *MemOS Paper Released*: [MemOS: A Memory OS for AI System](https://arxiv.org/abs/2507.03724) was published on arXiv.
-- **2025-05-28** – 🎉 *Short Paper Uploaded*: [MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models](https://arxiv.org/abs/2505.22101) was published on arXiv.
-- **2024-07-04** – 🎉 *Memory3 Model Released at WAIC 2024*: The new memory-layered architecture model was unveiled at the 2024 World Artificial Intelligence Conference.
-- **2024-07-01** – 🎉 *Memory3 Paper Released*: [Memory3: Language Modeling with Explicit Memory](https://arxiv.org/abs/2407.01178) introduces the new approach to structured memory in LLMs.

docker/.env.example

@@ -1,29 +1,60 @@
 # MemOS Environment Variables Configuration
+TZ=Asia/Shanghai
 
-# Path to memory storage (e.g. /tmp/data_test)
-MOS_CUBE_PATH=
+MOS_CUBE_PATH="/tmp/data_test"            # Path to memory storage (e.g. /tmp/data_test)
+MOS_ENABLE_DEFAULT_CUBE_CONFIG="true"     # Enable default cube config (true/false)
 
 # OpenAI Configuration
-OPENAI_API_KEY=            # Your OpenAI API key
-OPENAI_API_BASE=           # OpenAI API base URL (default: https://api.openai.com/v1)
+OPENAI_API_KEY="sk-xxx"                   # Your OpenAI API key
+OPENAI_API_BASE="http://xxx"              # OpenAI API base URL (default: https://api.openai.com/v1)
 
-# MemOS Feature Toggles
-MOS_ENABLE_DEFAULT_CUBE_CONFIG=   # Enable default cube config (true/false)
-MOS_ENABLE_SCHEDULER=             # Enable background scheduler (true/false)
+# MemOS Chat Model Configuration
+MOS_CHAT_MODEL=gpt-4o-mini
+MOS_CHAT_TEMPERATURE=0.8
+MOS_MAX_TOKENS=8000
+MOS_TOP_P=0.9
+MOS_TOP_K=50
+MOS_CHAT_MODEL_PROVIDER=openai
 
-# Neo4j Configuration
-NEO4J_URI=               # Neo4j connection URI (e.g. bolt://localhost:7687)
-NEO4J_USER=              # Neo4j username
-NEO4J_PASSWORD=          # Neo4j password
-MOS_NEO4J_SHARED_DB=     # Shared Neo4j database name (if using multi-db)
+# graph db
+# neo4j
+NEO4J_BACKEND=xxx
+NEO4J_URI=bolt://xxx
+NEO4J_USER=xxx
+NEO4J_PASSWORD=xxx
+MOS_NEO4J_SHARED_DB=xxx
+NEO4J_DB_NAME=xxx
+
+# tetxmem reog
+MOS_ENABLE_REORGANIZE=false
 
 # MemOS User Configuration
-MOS_USER_ID=             # Unique user ID
-MOS_SESSION_ID=          # Session ID for current chat
-MOS_MAX_TURNS_WINDOW=    # Max number of turns to keep in memory
+MOS_USER_ID=root
+MOS_SESSION_ID=default_session
+MOS_MAX_TURNS_WINDOW=20
+
+# MemRader Configuration
+MEMRADER_MODEL=gpt-4o-mini
+MEMRADER_API_KEY=sk-xxx
+MEMRADER_API_BASE=http://xxx:3000/v1
+MEMRADER_MAX_TOKENS=5000
+
+#embedding & rerank
+EMBEDDING_DIMENSION=1024
+MOS_EMBEDDER_BACKEND=universal_api
+MOS_EMBEDDER_MODEL=bge-m3
+MOS_EMBEDDER_API_BASE=http://xxx
+MOS_EMBEDDER_API_KEY=EMPTY
+MOS_RERANKER_BACKEND=http_bge
+MOS_RERANKER_URL=http://xxx
+# Ollama Configuration (for embeddings)
+#OLLAMA_API_BASE=http://xxx
 
-# Ollama Configuration (for local embedding models)
-OLLAMA_API_BASE=         # Ollama API base URL (e.g. http://localhost:11434)
+# milvus for pref mem
+MILVUS_URI=http://xxx
+MILVUS_USER_NAME=xxx
+MILVUS_PASSWORD=xxx
 
-# Embedding Configuration
-MOS_EMBEDDER_BACKEND=    # Embedding backend: openai, ollama, etc.
+# pref mem
+ENABLE_PREFERENCE_MEMORY=true
+RETURN_ORIGINAL_PREF_MEM=true

evaluation/.env-example

@@ -22,26 +22,3 @@ SUPERMEMORY_API_KEY="sm_xxx"
 MEMOBASE_API_KEY="xxx"
 MEMOBASE_PROJECT_URL="http://***.***.***.***:8019"
 
-# eval settings
-PRE_SPLIT_CHUNK=false
-
-# Configuration Only For Scheduler
-# RabbitMQ Configuration
-MEMSCHEDULER_RABBITMQ_HOST_NAME=rabbitmq-cn-***.cn-***.amqp-32.net.mq.amqp.aliyuncs.com
-MEMSCHEDULER_RABBITMQ_USER_NAME=***
-MEMSCHEDULER_RABBITMQ_PASSWORD=***
-MEMSCHEDULER_RABBITMQ_VIRTUAL_HOST=memos
-MEMSCHEDULER_RABBITMQ_ERASE_ON_CONNECT=true
-MEMSCHEDULER_RABBITMQ_PORT=5672
-
-# OpenAI Configuration
-MEMSCHEDULER_OPENAI_API_KEY=sk-***
-MEMSCHEDULER_OPENAI_BASE_URL=http://***.***.***.***:3000/v1
-MEMSCHEDULER_OPENAI_DEFAULT_MODEL=gpt-4o-mini
-
-# Graph DB Configuration
-MEMSCHEDULER_GRAPHDBAUTH_URI=bolt://localhost:7687
-MEMSCHEDULER_GRAPHDBAUTH_USER=neo4j
-MEMSCHEDULER_GRAPHDBAUTH_PASSWORD=***
-MEMSCHEDULER_GRAPHDBAUTH_DB_NAME=neo4j
-MEMSCHEDULER_GRAPHDBAUTH_AUTO_CREATE=true

evaluation/README.md

@@ -16,10 +16,7 @@ This repository provides tools and scripts for evaluating the `LoCoMo`, `LongMem
    ```
 
 ## Configuration
-
-1. Copy the `.env-example` file to `.env`, and fill in the required environment variables according to your environment and API keys.
-
-2. Copy the `configs-example/` directory to a new directory named `configs/`, and modify the configuration files inside it as needed. This directory contains model and API-specific settings.
+Copy the `.env-example` file to `.env`, and fill in the required environment variables according to your environment and API keys.
 
 ## Setup MemOS
 ### local server

evaluation/configs-example/mem_cube_config.json

@@ -250,33 +250,23 @@ def search(self, query, user_id, top_k):
                 preference_note = json.loads(response.text)["data"]["preference_note"]
                 for i in text_mem_res:
                     i.update({"memory": i.pop("memory_value")})
+                explicit_pref_string = "Explicit Preference:"
+                implicit_pref_string = "\n\nImplicit Preference:"
+                explicit_idx = 0
+                implicit_idx = 0
+                for pref in pref_mem_res:
+                    if pref["preference_type"] == "explicit_preference":
+                        explicit_pref_string += f"\n{explicit_idx + 1}. {pref['preference']}"
+                        explicit_idx += 1
+                    if pref["preference_type"] == "implicit_preference":
+                        implicit_pref_string += f"\n{implicit_idx + 1}. {pref['preference']}"
+                        implicit_idx += 1
+
+                return {
+                    "text_mem": [{"memories": text_mem_res}],
+                    "pref_string": explicit_pref_string + implicit_pref_string + preference_note,
+                }
 
-                explicit_prefs = [
-                    p["preference"]
-                    for p in pref_mem_res
-                    if p.get("preference_type", "") == "explicit_preference"
-                ]
-                implicit_prefs = [
-                    p["preference"]
-                    for p in pref_mem_res
-                    if p.get("preference_type", "") == "implicit_preference"
-                ]
-
-                pref_parts = []
-                if explicit_prefs:
-                    pref_parts.append(
-                        "Explicit Preference:\n"
-                        + "\n".join(f"{i + 1}. {p}" for i, p in enumerate(explicit_prefs))
-                    )
-                if implicit_prefs:
-                    pref_parts.append(
-                        "Implicit Preference:\n"
-                        + "\n".join(f"{i + 1}. {p}" for i, p in enumerate(implicit_prefs))
-                    )
-
-                pref_string = "\n".join(pref_parts) + preference_note
-
-                return {"text_mem": [{"memories": text_mem_res}], "pref_string": pref_string}
             except Exception as e:
                 if attempt < max_retries - 1:
                     time.sleep(2**attempt)