Dev 20260302 v2.0.8 (#1148)

## Description

Please include a summary of the change, the problem it solves, the
implementation approach, and relevant context. List any dependencies
required for this change.

Related Issue (Required):  Fixes @issue_number

## Type of change

Please delete options that are not relevant.

- [ ] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to not work as expected)
- [ ] Refactor (does not change functionality, e.g. code style
improvements, linting)
- [ ] Documentation update

## How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration

- [ ] Unit Test
- [ ] Test Script Or Test Steps (please provide)
- [ ] Pipeline Automated API Test (please provide)

## Checklist

- [ ] I have performed a self-review of my own code | 我已自行检查了自己的代码
- [ ] I have commented my code in hard-to-understand areas |
我已在难以理解的地方对代码进行了注释
- [ ] I have added tests that prove my fix is effective or that my
feature works | 我已添加测试以证明我的修复有效或功能正常
- [ ] I have created related documentation issue/PR in
[MemOS-Docs](https://github.com/MemTensor/MemOS-Docs) (if applicable) |
我已在 [MemOS-Docs](https://github.com/MemTensor/MemOS-Docs) 中创建了相关的文档
issue/PR（如果适用）
- [ ] I have linked the issue to this PR (if applicable) | 我已将 issue
链接到此 PR（如果适用）
- [ ] I have mentioned the person who will review this PR | 我已提及将审查此 PR
的人

## Reviewer Checklist
- [ ] closes #xxxx (Replace xxxx with the GitHub issue number)
- [ ] Made sure Checks passed
- [ ] Tests have been provided

Author: CaralHsi

.gitignore

@@ -230,3 +230,5 @@ cython_debug/
 outputs
 
 evaluation/data/temporal_locomo
+test_add_pipeline.py
+test_file_pipeline.py

README.md

@@ -42,7 +42,7 @@
     </a>
     <a href="https://github.com/IAAR-Shanghai/Awesome-AI-Memory">
       <img alt="Awesome AI Memory" src="https://img.shields.io/badge/Resources-Awesome--AI--Memory-8A2BE2">
-    </a>  
+    </a>
   </p>
 
 <p align="center">
@@ -55,7 +55,7 @@
   </a> -->
 
 </p>
-  
+
 </div>
 
 <!-- Get Free API: [Try API](https://memos-dashboard.openmem.net/quickstart/?source=github) -->
@@ -154,7 +154,7 @@ Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/Mem
 
   </details>
 
-- **2025-08-07** · 🎉 **MemOS v1.0.0 (MemCube) Release**  
+- **2025-08-07** · 🎉 **MemOS v1.0.0 (MemCube) Release**
   First MemCube release with a word-game demo, LongMemEval evaluation, BochaAISearchRetriever integration, NebulaGraph support, improved search capabilities, and the official Playground launch.
 
   <details>
@@ -192,11 +192,11 @@ Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/Mem
 
   </details>
 
-- **2025-07-07** · 🎉 **MemOS v1.0: Stellar (星河) Preview Release**  
+- **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**  
+- **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**  
+- **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>
@@ -209,9 +209,9 @@ Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/Mem
 - Go to **API Keys** and copy your key
 
 #### Next Steps
-- [MemOS Cloud Getting Started](https://memos-docs.openmem.net/memos_cloud/quick_start/)  
+- [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/)  
+- [MemOS Cloud Platform](https://memos.openmem.net/?from=/quickstart/)
   Explore the Cloud dashboard, features, and workflows.
 
 ### 🖥️ 2、Self-Hosted (Local/Private)
@@ -249,7 +249,7 @@ Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/Mem
     ```python
     import requests
     import json
-    
+
     data = {
         "user_id": "8736b16e-1d20-4163-980b-a5063c3facdc",
         "mem_cube_id": "b32d0977-435d-4828-a86f-4f47f8b55bca",
@@ -265,15 +265,15 @@ Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/Mem
         "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",
@@ -283,7 +283,7 @@ Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/Mem
         "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()}")
     ```
@@ -292,8 +292,8 @@ Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/Mem
 
 ## 📚 Resources
 
-- **Awesome-AI-Memory**   
- This is a curated repository dedicated to resources on memory and memory systems for large language models. It systematically collects relevant research papers, frameworks, tools, and practical insights. The repository aims to organize and present the rapidly evolving research landscape of LLM memory, bridging multiple research directions including natural language processing, information retrieval, agentic systems, and cognitive science.  
+- **Awesome-AI-Memory**
+ This is a curated repository dedicated to resources on memory and memory systems for large language models. It systematically collects relevant research papers, frameworks, tools, and practical insights. The repository aims to organize and present the rapidly evolving research landscape of LLM memory, bridging multiple research directions including natural language processing, information retrieval, agentic systems, and cognitive science.
 - **Get started** 👉 [IAAR-Shanghai/Awesome-AI-Memory](https://github.com/IAAR-Shanghai/Awesome-AI-Memory)
 - **MemOS Cloud OpenClaw Plugin**
   Official OpenClaw lifecycle plugin for MemOS Cloud. It automatically recalls context from MemOS before the agent starts and saves the conversation back to MemOS after the agent finishes.

docker/Dockerfile.krolik

@@ -1,5 +1,5 @@
 # MemOS with Krolik Security Extensions
-# 
+#
 # This Dockerfile builds MemOS with authentication, rate limiting, and admin API.
 # It uses the overlay pattern to keep customizations separate from base code.
 

examples/core_memories/general_textual_memory.py

@@ -68,21 +68,9 @@
 
 example_id = "a19b6caa-5d59-42ad-8c8a-e4f7118435b4"
 
-print("===== Extract memories =====")
-# Extract memories from a conversation
-# The extractor LLM processes the conversation to identify relevant information.
-memories = m.extract(
-    [
-        {"role": "user", "content": "I love tomatoes."},
-        {"role": "assistant", "content": "Great! Tomatoes are delicious."},
-    ]
-)
-pprint.pprint(memories)
-print()
-
 print("==== Add memories ====")
-# Add the extracted memories to the memory store
-m.add(memories)
+# Add example memories to the memory store
+m.add(example_memories)
 # Add a manually created memory item
 m.add(
     [

examples/core_memories/naive_textual_memory.py

@@ -1,20 +1,11 @@
-import json
 import os
+import pprint
 import uuid
 
 from memos.configs.memory import MemoryConfigFactory
 from memos.memories.factory import MemoryFactory
 
 
-def print_result(title, result):
-    """Helper function: Pretty print the result."""
-    print(f"\n{'=' * 10} {title} {'=' * 10}")
-    if isinstance(result, list | dict):
-        print(json.dumps(result, indent=2, ensure_ascii=False, default=str))
-    else:
-        print(result)
-
-
 # Configure memory backend with OpenAI extractor
 config = MemoryConfigFactory(
     backend="naive_text",
@@ -38,39 +29,55 @@ def print_result(title, result):
 # Create memory instance
 m = MemoryFactory.from_config(config)
 
+example_memories = [
+    {
+        "memory": "I'm a RUCer, I'm happy.",
+        "metadata": {
+            "type": "event",
+        },
+    },
+    {
+        "memory": "MemOS is awesome!",
+        "metadata": {
+            "type": "opinion",
+        },
+    },
+]
+
+example_id = str(uuid.uuid4())
 
-# Extract memories from a simulated conversation
-memories = m.extract(
+print("==== Add memories ====")
+# Add example memories to the memory store
+m.add(example_memories)
+# Manually create a memory item and add it
+m.add(
     [
-        {"role": "user", "content": "I love tomatoes."},
-        {"role": "assistant", "content": "Great! Tomatoes are delicious."},
+        {
+            "id": example_id,
+            "memory": "User is Chinese.",
+            "metadata": {"type": "opinion"},
+        }
     ]
 )
-print_result("Extract memories", memories)
-
-
-# Add the extracted memories to storage
-m.add(memories)
-
-# Manually create a memory item and add it
-example_id = str(uuid.uuid4())
-manual_memory = [{"id": example_id, "memory": "User is Chinese.", "metadata": {"type": "opinion"}}]
-m.add(manual_memory)
-
-# Print all current memories
-print_result("Add memories (Check all after adding)", m.get_all())
-
+print("All memories after addition:")
+pprint.pprint(m.get_all())
+print()
 
-# Search for relevant memories based on the query
+print("==== Search memories ====")
+# Search for memories related to a query
 search_results = m.search("Tell me more about the user", top_k=2)
-print_result("Search memories", search_results)
-
+pprint.pprint(search_results)
+print()
 
+print("==== Get memories ====")
 # Get specific memory item by ID
-memory_item = m.get(example_id)
-print_result("Get memory", memory_item)
-
+print(f"Memory with ID {example_id}:")
+pprint.pprint(m.get(example_id))
+print(f"Memories by IDs [{example_id}]:")
+pprint.pprint(m.get_by_ids([example_id]))
+print()
 
+print("==== Update memories ====")
 # Update the memory content for the specified ID
 m.update(
     example_id,
@@ -80,22 +87,26 @@ def print_result(title, result):
         "metadata": {"type": "opinion", "confidence": 85},
     },
 )
-updated_memory = m.get(example_id)
-print_result("Update memory", updated_memory)
-
+print(f"Memory after update (ID {example_id}):")
+pprint.pprint(m.get(example_id))
+print()
 
 print("==== Dump memory ====")
 # Dump the current state of memory to a file
 m.dump("tmp/naive_mem")
 print("Memory dumped to 'tmp/naive_mem'.")
 print()
 
-
+print("==== Delete memories ====")
 # Delete memory with the specified ID
 m.delete([example_id])
-print_result("Delete memory (Check all after deleting)", m.get_all())
-
+print("All memories after deletion:")
+pprint.pprint(m.get_all())
+print()
 
+print("==== Delete all memories ====")
 # Delete all memories in storage
 m.delete_all()
-print_result("Delete all", m.get_all())
+print("All memories after delete_all:")
+pprint.pprint(m.get_all())
+print()

examples/data/mem_cube_tree/textual_memory.json

@@ -4216,4 +4216,4 @@
   "edges": [],
   "total_nodes": 4,
   "total_edges": 0
-}
+}

examples/mem_feedback/example_feedback.py

@@ -144,7 +144,7 @@ def init_components():
         mem_reader=mem_reader,
         searcher=searcher,
         reranker=mem_reranker,
-        pref_mem=None,
+        pref_feedback=True,
     )
 
     return feedback_server, memory_manager, embedder

pyproject.toml

@@ -4,7 +4,7 @@
 ##############################################################################
 
 name = "MemoryOS"
-version = "2.0.7"
+version = "2.0.8"
 description = "Intelligence Begins with Memory"
 license = {text = "Apache-2.0"}
 readme = "README.md"

src/memos/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "2.0.7"
+__version__ = "2.0.8"
 
 from memos.configs.mem_cube import GeneralMemCubeConfig
 from memos.configs.mem_os import MOSConfig

src/memos/api/config.py

@@ -675,7 +675,17 @@ def get_polardb_config(user_id: str | None = None) -> dict[str, Any]:
             "user_name": user_name,
             "use_multi_db": use_multi_db,
             "auto_create": True,
-            "embedding_dimension": int(os.getenv("EMBEDDING_DIMENSION", 1024)),
+            "embedding_dimension": int(os.getenv("EMBEDDING_DIMENSION", "1024")),
+            # .env: CONNECTION_WAIT_TIMEOUT, SKIP_CONNECTION_HEALTH_CHECK, WARM_UP_ON_STARTUP_BY_FULL, WARM_UP_ON_STARTUP_BY_ALL
+            "connection_wait_timeout": int(os.getenv("CONNECTION_WAIT_TIMEOUT", "60")),
+            "skip_connection_health_check": os.getenv(
+                "SKIP_CONNECTION_HEALTH_CHECK", "false"
+            ).lower()
+            == "true",
+            "warm_up_on_startup_by_full": os.getenv("WARM_UP_ON_STARTUP_BY_FULL", "false").lower()
+            == "true",
+            "warm_up_on_startup_by_all": os.getenv("WARM_UP_ON_STARTUP_BY_ALL", "false").lower()
+            == "true",
         }
 
     @staticmethod