MemoryOS 2.0.6__tar.gz → 2.0.8__tar.gz

{memoryos-2.0.6 → memoryos-2.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: MemoryOS
-Version: 2.0.6
+Version: 2.0.8
 Summary: Intelligence Begins with Memory
 License: Apache-2.0
 License-File: LICENSE
@@ -123,7 +123,7 @@ Description-Content-Type: text/markdown
     </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">
@@ -131,30 +131,42 @@ Description-Content-Type: text/markdown
   <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/">
+  <!-- <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>
+  </a> -->
 
 </p>
-  
+
 </div>
 
-Get Free API: [Try API](https://memos-dashboard.openmem.net/quickstart/?source=github)
+<!-- Get Free API: [Try API](https://memos-dashboard.openmem.net/quickstart/?source=github) -->
 
----
+<!-- --- -->
 
-<br>
+<!-- <br> -->
 
 ## 🦞 Enhanced OpenClaw with MemOS Plugin
+
 ![](https://cdn.memtensor.com.cn/img/1770612303123_mnaisk_compressed.png)
 
-- [**72% lower token usage**](https://x.com/MemOS_dev/status/2020854044583924111) – intelligent memory retrieval instead of loading full chat history
-- [**Multi-agent memory sharing**](https://x.com/MemOS_dev/status/2020538135487062094) – multi-instance agents share memory via same user_id. Automatic context handoff.  
+🦞 Your lobster now has a working memory system — choose **Cloud** or **Local** to get started.
 
-🦞 Your lobster now has a working memory system.
+### ☁️ Cloud Plugin — Hosted Memory Service
+
+- [**72% lower token usage**](https://x.com/MemOS_dev/status/2020854044583924111) — intelligent memory retrieval instead of loading full chat history
+- [**Multi-agent memory sharing**](https://x.com/MemOS_dev/status/2020538135487062094) — multi-instance agents share memory via same user_id, automatic context handoff
 
 Get your API key: [MemOS Dashboard](https://memos-dashboard.openmem.net/cn/login/)  
-Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/MemOS-Cloud-OpenClaw-Plugin)
+Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/MemOS-Cloud-OpenClaw-Plugin)
+
+### 🧠 Local Plugin — 100% On-Device Memory
+
+- **Zero cloud dependency** — all data stays on your machine, persistent local SQLite storage
+- **Hybrid search + task & skill evolution** — FTS5 + vector search, auto task summarization, reusable skills that self-upgrade
+- **Multi-agent collaboration + Memory Viewer** — memory isolation, skill sharing, full web dashboard with 7 management pages
+
+ 🌐 [Homepage](https://memos-claw.openmem.net) · 
+📖 [Documentation](https://memos-claw.openmem.net/docs/index.html) · 📦 [NPM](https://www.npmjs.com/package/@memtensor/memos-local-openclaw-plugin)
 
 ## 📌 MemOS: Memory Operating System for AI Agents
 
@@ -173,6 +185,9 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
 
 ### News
 
+- **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>
@@ -220,7 +235,7 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
 
   </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>
@@ -258,11 +273,11 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
 
   </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>
@@ -275,9 +290,9 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
 - 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)
@@ -315,7 +330,7 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
     ```python
     import requests
     import json
-    
+
     data = {
         "user_id": "8736b16e-1d20-4163-980b-a5063c3facdc",
         "mem_cube_id": "b32d0977-435d-4828-a86f-4f47f8b55bca",
@@ -331,7 +346,7 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
         "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()}")
     ```
@@ -339,7 +354,7 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
     ```python
     import requests
     import json
-    
+
     data = {
         "query": "What do I like",
         "user_id": "8736b16e-1d20-4163-980b-a5063c3facdc",
@@ -349,7 +364,7 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
         "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()}")
     ```
@@ -358,8 +373,8 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
 
 ## 📚 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.
@@ -426,10 +441,11 @@ url = {https://global-sci.com/article/91443/memory3-language-modeling-with-expli
 
 ## 🙌 Contributing
 
-We welcome contributions from the community! Please read our [contribution guidelines](https://memos-docs.openmem.net/contribution/overview) to get started.
+We welcome contributions from the community! Please read our [contribution guidelines](https://memos-docs.openmem.net/open_source/contribution/overview/) to get started.
 
 <br>
 
 ## 📄 License
 
 MemOS is licensed under the [Apache 2.0 License](./LICENSE).
+

{memoryos-2.0.6 → memoryos-2.0.8}/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">
@@ -50,30 +50,42 @@
   <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/">
+  <!-- <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>
+  </a> -->
 
 </p>
-  
+
 </div>
 
-Get Free API: [Try API](https://memos-dashboard.openmem.net/quickstart/?source=github)
+<!-- Get Free API: [Try API](https://memos-dashboard.openmem.net/quickstart/?source=github) -->
 
----
+<!-- --- -->
 
-<br>
+<!-- <br> -->
 
 ## 🦞 Enhanced OpenClaw with MemOS Plugin
+
 ![](https://cdn.memtensor.com.cn/img/1770612303123_mnaisk_compressed.png)
 
-- [**72% lower token usage**](https://x.com/MemOS_dev/status/2020854044583924111) – intelligent memory retrieval instead of loading full chat history
-- [**Multi-agent memory sharing**](https://x.com/MemOS_dev/status/2020538135487062094) – multi-instance agents share memory via same user_id. Automatic context handoff.  
+🦞 Your lobster now has a working memory system — choose **Cloud** or **Local** to get started.
 
-🦞 Your lobster now has a working memory system.
+### ☁️ Cloud Plugin — Hosted Memory Service
+
+- [**72% lower token usage**](https://x.com/MemOS_dev/status/2020854044583924111) — intelligent memory retrieval instead of loading full chat history
+- [**Multi-agent memory sharing**](https://x.com/MemOS_dev/status/2020538135487062094) — multi-instance agents share memory via same user_id, automatic context handoff
 
 Get your API key: [MemOS Dashboard](https://memos-dashboard.openmem.net/cn/login/)  
-Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/MemOS-Cloud-OpenClaw-Plugin)
+Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/MemOS-Cloud-OpenClaw-Plugin)
+
+### 🧠 Local Plugin — 100% On-Device Memory
+
+- **Zero cloud dependency** — all data stays on your machine, persistent local SQLite storage
+- **Hybrid search + task & skill evolution** — FTS5 + vector search, auto task summarization, reusable skills that self-upgrade
+- **Multi-agent collaboration + Memory Viewer** — memory isolation, skill sharing, full web dashboard with 7 management pages
+
+ 🌐 [Homepage](https://memos-claw.openmem.net) · 
+📖 [Documentation](https://memos-claw.openmem.net/docs/index.html) · 📦 [NPM](https://www.npmjs.com/package/@memtensor/memos-local-openclaw-plugin)
 
 ## 📌 MemOS: Memory Operating System for AI Agents
 
@@ -92,6 +104,9 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
 
 ### News
 
+- **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>
@@ -139,7 +154,7 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
 
   </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>
@@ -177,11 +192,11 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
 
   </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>
@@ -194,9 +209,9 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
 - 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)
@@ -234,7 +249,7 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
     ```python
     import requests
     import json
-    
+
     data = {
         "user_id": "8736b16e-1d20-4163-980b-a5063c3facdc",
         "mem_cube_id": "b32d0977-435d-4828-a86f-4f47f8b55bca",
@@ -250,7 +265,7 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
         "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()}")
     ```
@@ -258,7 +273,7 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
     ```python
     import requests
     import json
-    
+
     data = {
         "query": "What do I like",
         "user_id": "8736b16e-1d20-4163-980b-a5063c3facdc",
@@ -268,7 +283,7 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
         "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()}")
     ```
@@ -277,8 +292,8 @@ Try it: Full tutorial → [MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTe
 
 ## 📚 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.
@@ -345,10 +360,10 @@ url = {https://global-sci.com/article/91443/memory3-language-modeling-with-expli
 
 ## 🙌 Contributing
 
-We welcome contributions from the community! Please read our [contribution guidelines](https://memos-docs.openmem.net/contribution/overview) to get started.
+We welcome contributions from the community! Please read our [contribution guidelines](https://memos-docs.openmem.net/open_source/contribution/overview/) to get started.
 
 <br>
 
 ## 📄 License
 
-MemOS is licensed under the [Apache 2.0 License](./LICENSE).
+MemOS is licensed under the [Apache 2.0 License](./LICENSE).

{memoryos-2.0.6 → memoryos-2.0.8}/pyproject.toml

@@ -4,7 +4,7 @@
 ##############################################################################
 
 name = "MemoryOS"
-version = "2.0.6"
+version = "2.0.8"
 description = "Intelligence Begins with Memory"
 license = {text = "Apache-2.0"}
 readme = "README.md"

{memoryos-2.0.6 → memoryos-2.0.8}/src/memos/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "2.0.6"
+__version__ = "2.0.8"
 
 from memos.configs.mem_cube import GeneralMemCubeConfig
 from memos.configs.mem_os import MOSConfig

{memoryos-2.0.6 → memoryos-2.0.8}/src/memos/api/config.py

@@ -675,7 +675,17 @@ class APIConfig:
             "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
@@ -1014,6 +1024,7 @@ class APIConfig:
                                 "fast_graph": bool(os.getenv("FAST_GRAPH", "false") == "true"),
                                 "bm25": bool(os.getenv("BM25_CALL", "false") == "true"),
                                 "cot": bool(os.getenv("VEC_COT_CALL", "false") == "true"),
+                                "fulltext": bool(os.getenv("FULLTEXT_CALL", "false") == "true"),
                             },
                             "include_embedding": bool(
                                 os.getenv("INCLUDE_EMBEDDING", "false") == "true"
@@ -1096,6 +1107,7 @@ class APIConfig:
                                 "fast_graph": bool(os.getenv("FAST_GRAPH", "false") == "true"),
                                 "bm25": bool(os.getenv("BM25_CALL", "false") == "true"),
                                 "cot": bool(os.getenv("VEC_COT_CALL", "false") == "true"),
+                                "fulltext": bool(os.getenv("FULLTEXT_CALL", "false") == "true"),
                             },
                             "mode": os.getenv("ASYNC_MODE", "sync"),
                             "include_embedding": bool(

{memoryos-2.0.6 → memoryos-2.0.8}/src/memos/api/handlers/__init__.py

@@ -32,7 +32,6 @@ from memos.api.handlers.config_builders import (
 )
 from memos.api.handlers.formatters_handler import (
     format_memory_item,
-    post_process_pref_mem,
     to_iter,
 )
 
@@ -54,7 +53,6 @@ __all__ = [
     "formatters_handler",
     "init_server",
     "memory_handler",
-    "post_process_pref_mem",
     "scheduler_handler",
     "search_handler",
     "suggestion_handler",

{memoryos-2.0.6 → memoryos-2.0.8}/src/memos/api/handlers/add_handler.py

@@ -22,7 +22,7 @@ class AddHandler(BaseHandler):
     """
     Handler for memory addition operations.
 
-    Handles both text and preference memory additions with sync/async support.
+    Handles text memory additions with sync/async support.
     """
 
     def __init__(self, dependencies: HandlerDependencies):
@@ -41,7 +41,7 @@ class AddHandler(BaseHandler):
         """
         Main handler for add memories endpoint.
 
-        Orchestrates the addition of both text and preference memories,
+        Orchestrates the addition of text memories,
         supporting concurrent processing.
 
         Args:

{memoryos-2.0.6 → memoryos-2.0.8}/src/memos/api/handlers/component_init.py

@@ -19,11 +19,7 @@ from memos.api.handlers.config_builders import (
     build_llm_config,
     build_mem_reader_config,
     build_nli_client_config,
-    build_pref_adder_config,
-    build_pref_extractor_config,
-    build_pref_retriever_config,
     build_reranker_config,
-    build_vec_db_config,
 )
 from memos.configs.mem_scheduler import SchedulerConfigFactory
 from memos.embedders.factory import EmbedderFactory
@@ -36,12 +32,6 @@ from memos.mem_os.product_server import MOSServer
 from memos.mem_reader.factory import MemReaderFactory
 from memos.mem_scheduler.orm_modules.base_model import BaseDBManager
 from memos.mem_scheduler.scheduler_factory import SchedulerFactory
-from memos.memories.textual.prefer_text_memory.factory import (
-    AdderFactory,
-    ExtractorFactory,
-    RetrieverFactory,
-)
-from memos.memories.textual.simple_preference import SimplePreferenceTextMemory
 from memos.memories.textual.simple_tree import SimpleTreeTextMemory
 from memos.memories.textual.tree_text_memory.organize.history_manager import MemoryHistoryManager
 from memos.memories.textual.tree_text_memory.organize.manager import MemoryManager
@@ -56,7 +46,6 @@ from memos.memories.textual.tree_text_memory.retrieve.internet_retriever_factory
     InternetRetrieverFactory,
 )
 from memos.reranker.factory import RerankerFactory
-from memos.vec_dbs.factory import VecDBFactory
 
 
 if TYPE_CHECKING:
@@ -125,7 +114,7 @@ def init_server() -> dict[str, Any]:
     required by the MemOS server, including:
     - Database connections (graph DB, vector DB)
     - Language models and embedders
-    - Memory systems (text, preference)
+    - Memory systems (text)
     - Scheduler and related modules
 
     Returns:
@@ -169,20 +158,11 @@ def init_server() -> dict[str, Any]:
     reranker_config = build_reranker_config()
     feedback_reranker_config = build_feedback_reranker_config()
     internet_retriever_config = build_internet_retriever_config()
-    vector_db_config = build_vec_db_config()
-    pref_extractor_config = build_pref_extractor_config()
-    pref_adder_config = build_pref_adder_config()
-    pref_retriever_config = build_pref_retriever_config()
 
     logger.debug("Component configurations built successfully")
 
     # Create component instances
     graph_db = GraphStoreFactory.from_config(graph_db_config)
-    vector_db = (
-        VecDBFactory.from_config(vector_db_config)
-        if os.getenv("ENABLE_PREFERENCE_MEMORY", "false") == "true"
-        else None
-    )
     llm = LLMFactory.from_config(llm_config)
     chat_llms = (
         _init_chat_llms(chat_llm_config)
@@ -231,61 +211,6 @@ def init_server() -> dict[str, Any]:
 
     logger.debug("Text memory initialized")
 
-    # Initialize preference memory components
-    pref_extractor = (
-        ExtractorFactory.from_config(
-            config_factory=pref_extractor_config,
-            llm_provider=llm,
-            embedder=embedder,
-            vector_db=vector_db,
-        )
-        if os.getenv("ENABLE_PREFERENCE_MEMORY", "false") == "true"
-        else None
-    )
-
-    pref_adder = (
-        AdderFactory.from_config(
-            config_factory=pref_adder_config,
-            llm_provider=llm,
-            embedder=embedder,
-            vector_db=vector_db,
-            text_mem=text_mem,
-        )
-        if os.getenv("ENABLE_PREFERENCE_MEMORY", "false") == "true"
-        else None
-    )
-
-    pref_retriever = (
-        RetrieverFactory.from_config(
-            config_factory=pref_retriever_config,
-            llm_provider=llm,
-            embedder=embedder,
-            reranker=feedback_reranker,
-            vector_db=vector_db,
-        )
-        if os.getenv("ENABLE_PREFERENCE_MEMORY", "false") == "true"
-        else None
-    )
-
-    logger.debug("Preference memory components initialized")
-
-    # Initialize preference memory
-    pref_mem = (
-        SimplePreferenceTextMemory(
-            extractor_llm=llm,
-            vector_db=vector_db,
-            embedder=embedder,
-            reranker=feedback_reranker,
-            extractor=pref_extractor,
-            adder=pref_adder,
-            retriever=pref_retriever,
-        )
-        if os.getenv("ENABLE_PREFERENCE_MEMORY", "false") == "true"
-        else None
-    )
-
-    logger.debug("Preference memory initialized")
-
     # Initialize MOS Server
     mos_server = MOSServer(
         mem_reader=mem_reader,
@@ -298,7 +223,6 @@ def init_server() -> dict[str, Any]:
     # Create MemCube with pre-initialized memory instances
     naive_mem_cube = NaiveMemCube(
         text_mem=text_mem,
-        pref_mem=pref_mem,
         act_mem=None,
         para_mem=None,
     )
@@ -325,7 +249,7 @@ def init_server() -> dict[str, Any]:
         mem_reader=mem_reader,
         searcher=searcher,
         reranker=feedback_reranker,
-        pref_mem=pref_mem,
+        pref_feedback=True,
     )
 
     # Initialize Scheduler
@@ -384,12 +308,7 @@ def init_server() -> dict[str, Any]:
         "naive_mem_cube": naive_mem_cube,
         "searcher": searcher,
         "api_module": api_module,
-        "vector_db": vector_db,
-        "pref_extractor": pref_extractor,
-        "pref_adder": pref_adder,
-        "pref_retriever": pref_retriever,
         "text_mem": text_mem,
-        "pref_mem": pref_mem,
         "online_bot": online_bot,
         "feedback_server": feedback_server,
         "redis_client": redis_client,

{memoryos-2.0.6 → memoryos-2.0.8}/src/memos/api/handlers/formatters_handler.py

@@ -65,49 +65,14 @@ def format_memory_item(
     return memory
 
 
-def post_process_pref_mem(
-    memories_result: dict[str, Any],
-    pref_formatted_mem: list[dict[str, Any]],
-    mem_cube_id: str,
-    include_preference: bool,
-) -> dict[str, Any]:
-    """
-    Post-process preference memory results.
-
-    Adds formatted preference memories to the result dictionary and generates
-    instruction completion strings if preferences are included.
-
-    Args:
-        memories_result: Result dictionary to update
-        pref_formatted_mem: List of formatted preference memories
-        mem_cube_id: Memory cube ID
-        include_preference: Whether to include preferences in result
-
-    Returns:
-        Updated memories_result dictionary
-    """
-    if include_preference:
-        memories_result["pref_mem"].append(
-            {
-                "cube_id": mem_cube_id,
-                "memories": pref_formatted_mem,
-                "total_nodes": len(pref_formatted_mem),
-            }
-        )
-        pref_instruction, pref_note = instruct_completion(pref_formatted_mem)
-        memories_result["pref_string"] = pref_instruction
-        memories_result["pref_note"] = pref_note
-
-    return memories_result
-
-
 def post_process_textual_mem(
     memories_result: dict[str, Any],
     text_formatted_mem: list[dict[str, Any]],
     mem_cube_id: str,
 ) -> dict[str, Any]:
     """
-    Post-process text and tool memory results.
+    Post-process text, tool, skill and preference memory results.
+    Now automatically handles preference memories.
     """
     fact_mem = [
         mem
@@ -124,6 +89,11 @@ def post_process_textual_mem(
         mem for mem in text_formatted_mem if mem["metadata"]["memory_type"] == "SkillMemory"
     ]
 
+    # Extract preference memories
+    pref_mem = [
+        mem for mem in text_formatted_mem if mem["metadata"]["memory_type"] == "PreferenceMemory"
+    ]
+
     memories_result["text_mem"].append(
         {
             "cube_id": mem_cube_id,
@@ -145,6 +115,19 @@ def post_process_textual_mem(
             "total_nodes": len(skill_mem),
         }
     )
+
+    memories_result["pref_mem"].append(
+        {
+            "cube_id": mem_cube_id,
+            "memories": pref_mem,
+            "total_nodes": len(pref_mem),
+        }
+    )
+    if pref_mem:
+        pref_instruction, pref_note = instruct_completion(pref_mem)
+        memories_result["pref_string"] = pref_instruction
+        memories_result["pref_note"] = pref_note
+
     return memories_result