Dev 20260109 v2.0.1

README.md

@@ -3,8 +3,6 @@
 MemOS is an open-source **Agent Memory framework** that empowers AI agents with **long-term memory, personality consistency, and contextual recall**. It enables agents to **remember past interactions**, **learn over time**, and **build evolving identities** across sessions.
 
 Designed for **AI companions, role-playing NPCs, and multi-agent systems**, MemOS provides a unified API for **memory representation, retrieval, and update** — making it the foundation for next-generation **memory-augmented AI agents**.
-
-🆕 **MemOS 2.0** introduces **knowledge base system**, **multi-modal memory** (images & documents), **tool memory** for Agent optimization, **memory feedback mechanism** for precise control, and **enterprise-grade architecture** with Redis Streams scheduler and advanced DB optimizations.
 <div align="center">
   <a href="https://memos.openmem.net/">
     <img src="https://statics.memtensor.com.cn/memos/memos-banner.gif" alt="MemOS Banner">
@@ -117,17 +115,6 @@ showcasing its capabilities in **information extraction**, **temporal and cross-
     - **Textual Memory**: For storing and retrieving unstructured or structured text knowledge.
     - **Activation Memory**: Caches key-value pairs (`KVCacheMemory`) to accelerate LLM inference and context reuse.
     - **Parametric Memory**: Stores model adaptation parameters (e.g., LoRA weights).
-    - **Tool Memory** 🆕: Records Agent tool call trajectories and experiences to improve planning capabilities.
-- **📚 Knowledge Base System** 🆕: Build multi-dimensional knowledge bases with automatic document/URL parsing, splitting, and cross-project sharing capabilities.
-- **🔧 Memory Controllability** 🆕:
-    - **Feedback Mechanism**: Use `add_feedback` API to correct, supplement, or replace existing memories with natural language.
-    - **Precise Deletion**: Delete specific memories by User ID or Memory ID via API or MCP tools.
-- **👁️ Multi-Modal Support** 🆕: Support for image understanding and memory, including chart parsing in documents.
-- **⚡ Advanced Architecture**:
-    - **DB Optimization**: Enhanced connection management and batch insertion for high-concurrency scenarios.
-    - **Advanced Retrieval**: Custom tag and info field filtering with complex logical operations.
-    - **Redis Streams Scheduler**: Multi-level queue architecture with intelligent orchestration for fair multi-tenant scheduling.
-    - **Stream & Non-Stream Chat**: Ready-to-use streaming and non-streaming chat interfaces.
 - **🔌 Extensible**: Easily extend and customize memory modules, data sources, and LLM integrations.
 - **🏂 Lightweight Deployment** 🆕: Support for quick mode and complete mode deployment options.
 
@@ -181,6 +168,7 @@ res = client.search_memory(query=query, user_id=user_id, conversation_id=convers
 print(f"result: {res}")
 ```
 
+
 ### Self-Hosted Server
 1. Get the repository.
     ```bash
@@ -215,7 +203,7 @@ Example
     ```python
     import requests
     import json
-    
+
     data = {
         "user_id": "8736b16e-1d20-4163-980b-a5063c3facdc",
         "mem_cube_id": "b32d0977-435d-4828-a86f-4f47f8b55bca",
@@ -231,15 +219,15 @@ Example
         "Content-Type": "application/json"
     }
     url = "http://localhost:8000/product/add"
-    
+
     res = requests.post(url=url, headers=headers, data=json.dumps(data))
     print(f"result: {res.json()}")
     ```
   - Search User Memory
     ```python
     import requests
     import json
-    
+
     data = {
         "query": "What do I like",
         "user_id": "8736b16e-1d20-4163-980b-a5063c3facdc",
@@ -249,7 +237,7 @@ Example
         "Content-Type": "application/json"
     }
     url = "http://localhost:8000/product/search"
-    
+
     res = requests.post(url=url, headers=headers, data=json.dumps(data))
     print(f"result: {res.json()}")
     ```

docker/.env.example

@@ -76,6 +76,7 @@ MODEL=gpt-4o-mini
 # embedding model for evaluation
 EMBEDDING_MODEL=nomic-embed-text:latest
 
+
 ## Internet search & preference memory
 # Enable web search
 ENABLE_INTERNET=false
@@ -211,4 +212,4 @@ MEMSCHEDULER_RABBITMQ_VIRTUAL_HOST=memos
 # Erase connection state on connect for message-log pipeline
 MEMSCHEDULER_RABBITMQ_ERASE_ON_CONNECT=true
 # RabbitMQ port for message-log pipeline
-MEMSCHEDULER_RABBITMQ_PORT=5672
+MEMSCHEDULER_RABBITMQ_PORT=5672

docker/requirements-full.txt

@@ -183,4 +183,4 @@ psycopg2-binary==2.9.11
 py-key-value-aio==0.2.8
 py-key-value-shared==0.2.8
 PyJWT==2.10.1
-pytest==9.0.2
+pytest==9.0.2

docker/requirements.txt

@@ -1,6 +1,3 @@
-# Docker optimized requirements - Core dependencies only
-# Excludes Windows-specific and heavy GPU packages for faster builds
-
 annotated-types==0.7.0
 anyio==4.11.0
 attrs==25.4.0
@@ -125,4 +122,4 @@ urllib3==2.5.0
 uvicorn==0.38.0
 uvloop==0.22.1; sys_platform != 'win32'
 watchfiles==1.1.1
-websockets==15.0.1
+websockets==15.0.1

docs/README.md

@@ -1,3 +1,3 @@
 All documentation has been moved to a separate repository: https://github.com/MemTensor/MemOS-Docs. Please edit documentation there.
 
-所有文档已迁移至独立仓库：https://github.com/MemTensor/MemOS-Docs。请在该仓库中编辑文档。
+所有文档已迁移至独立仓库 https://github.com/MemTensor/MemOS-Docs 。请在该仓库中编辑文档。

evaluation/scripts/run_prefeval_eval.sh

@@ -108,7 +108,9 @@ python $LIB_SCRIPT search \
     --input $IDS_FILE \
     --output $SEARCH_FILE \
     --top-k $TOP_K \
-    --max-workers $WORKERS
+    --max-workers $WORKERS \
+    --lib $LIB \
+    --version $VERSION
 
 if [ $? -ne 0 ]; then
     echo "Error: $LIB_SCRIPT 'search' mode failed."
@@ -121,7 +123,9 @@ echo "Running $LIB_SCRIPT in 'response' mode..."
 python $LIB_SCRIPT response \
     --input $SEARCH_FILE \
     --output $RESPONSE_FILE \
-    --max-workers $WORKERS
+    --max-workers $WORKERS \
+    --lib $LIB \
+    --version $VERSION
 
 if [ $? -ne 0 ]; then
     echo "Error: $LIB_SCRIPT 'response' mode failed."

examples/data/config/mem_scheduler/mem_cube_config.yaml

@@ -0,0 +1,21 @@
+user_id: "user_test"
+cube_id: "user_test/mem_cube_naive"
+text_mem:
+  backend: "naive_text"
+  config:
+    extractor_llm:
+      backend: "huggingface_singleton"
+      config:
+        model_name_or_path: "Qwen/Qwen3-0.6B"
+        temperature: 0.1
+        max_tokens: 1024
+act_mem:
+  backend: "kv_cache"
+  config:
+    memory_filename: "activation_memory.pickle"
+    extractor_llm:
+      backend: "huggingface_singleton"
+      config:
+        model_name_or_path: "Qwen/Qwen3-0.6B"
+        temperature: 0.8
+        max_tokens: 1024

examples/data/config/mem_scheduler/memos_config_w_scheduler.yaml

@@ -10,16 +10,12 @@ mem_reader:
   backend: "simple_struct"
   config:
     llm:
-      backend: "openai"
+      backend: "huggingface_singleton"
       config:
-        model_name_or_path: "gpt-4o-mini"
-        temperature: 0.8
-        max_tokens: 4096
-        top_p: 0.9
-        top_k: 50
+        model_name_or_path: "Qwen/Qwen3-1.7B"
+        temperature: 0.1
         remove_think_prefix: true
-        api_key: "sk-xxxxxx"
-        api_base: "https://api.openai.com/v1"
+        max_tokens: 4096
     embedder:
       backend: "ollama"
       config: