docs: update images and refine punctuation in README

- Updated several images in the README for better clarity
- Refined punctuation to improve readability and consistency
- No functional or code changes included

Author: Jununn

README.md

@@ -27,8 +27,8 @@ MemU offers several convenient ways to get started right away:
 ## ⭐ Star Us on GitHub
 
 Star MemU to get notified about new releases and join our growing community of AI developers building intelligent agents with persistent memory capabilities.
+![star-us](https://github.com/user-attachments/assets/9cdc33bb-b55f-4d25-9e24-43212065eb97)
 
-![star-us](./assets/star.gif)
 
 **💬 Join our Discord community:** [https://discord.gg/memu](https://discord.gg/memu)
 
@@ -59,34 +59,34 @@ MemU offers a flexible and robust alternative, inspired by hierarchical storage
 
 Its core architecture consists of three layers: **Resource Layer → Memory Item Layer → MemoryCategory Layer.**
 
-<img width="1280" height="639" alt="image" src="https://github.com/user-attachments/assets/c34a1fdb-02fd-4542-9c10-121d79dba67f" />
+<img width="1363" height="563" alt="Three-Layer Architecture Diagram" src="https://github.com/user-attachments/assets/5a17d6fd-f960-4afd-a984-207fe2b341c8" />
 
-- **Resource Layer**
+- **Resource Layer:** 
   A multimodal raw data warehouse, also serving as the ground truth layer, providing a semantic foundation for the memory system.
 
-- **Memory Item Layer**
+- **Memory Item Layer:** 
   A unified semantic abstraction layer, functioning as the system’s semantic cache, supplying high-density semantic vectors for downstream retrieval and reasoning.
 
-- **MemoryCategory Layer**
+- **MemoryCategory Layer:** 
   A thematic document layer, mimicking human working memory mechanisms, balancing short-term response efficiency and long-term information completeness.
 
 Through this three-layer design, **MemU brings genuine memory into the agent layer, achieving:**
 
-- **Full Traceability**
+- **Full Traceability:** 
   Complete traceability across the three layers—from raw data → memory items → aggregated documents. Enables bidirectional tracking of each knowledge piece’s source and evolution, ensuring transparency and interpretability.
 
-- **End-to-End Memory Lifecycle Management**
+- **End-to-End Memory Lifecycle Management:** 
   The three core processes correspond to the memory lifecycle: **Memorization → Retrieval → Self-evolution**.
 
-- **Coherent and Scalable Memorization**
+- **Coherent and Scalable Memorization:** 
   During memorization, the system maintains memory coherence while automatically managing resources to support sustainable expansion.
 
-- **Efficient and Interpretable Retrieval**
+- **Efficient and Interpretable Retrieval:** 
   Retrieves information efficiently while preserving interpretability, supporting cross-theme and cross-modal semantic queries and reasoning.
 
-- **Self-Evolving Memory**
+- **Self-Evolving Memory:** 
   A feedback-driven mechanism continuously adapts the memory structure according to real usage patterns.
-<img width="1280" height="312" alt="image" src="https://github.com/user-attachments/assets/e2c0ac0c-e5cb-44a9-b880-89be142e1ca5" />
+<img width="1365" height="308" alt="process" src="https://github.com/user-attachments/assets/aeb2dd9a-d76a-465d-b807-9b781c9cb8aa" />
 
 ## 🚀Get Started