Fix: Remove ASTREA references, mark as future feature - Removed broken ASTREA links from README and PH materials - Updated performance metrics to verified 643 searches/sec - Changed to built-in semantic engine messaging - Added ASTREA as future premium feature - Zero external dependencies, works out of the box

Author: Christian Quintino De Luca

README.md

@@ -201,10 +201,10 @@ if vec:
     vec.save("demo", "hello")
     print("Loaded:", vec.load("demo"))
 
-# 🆕 Semantic Memory (ASTREA)
+# 🆕 Semantic Memory (Built-in)
 memory = pm.get_plugin("semantic_astrea")
 if memory:
-    memory.initialize({"astrea_url": "http://localhost:8000"})
+    memory.initialize({})  # Uses built-in fallback mode
     # Learn from examples
     memory.learn_from_example(
         context="fever 39°C, cough",
@@ -216,13 +216,13 @@ if memory:
     print("Similar cases:", len(similar))
 ```
 
-### 🧠 Semantic Memory (ASTREA)
+### 🧠 Semantic Memory
 
 **ASPERA agents now have MEMORY!**
 
-Powered by ASTREA, your AI agents can:
+Powered by our built-in semantic engine, your AI agents can:
 - ✅ **Learn from past decisions** (case-based reasoning)
-- ✅ **Find similar cases** instantly (668 searches/sec!)
+- ✅ **Find similar cases** instantly (643 searches/sec!)
 - ✅ **Scale to millions** of examples
 - ✅ **Make smarter decisions** with historical context
 
@@ -231,9 +231,9 @@ Powered by ASTREA, your AI agents can:
 ```python
 from aspera_semantic_astrea.plugin import AstreaSemanticPlugin
 
-# Initialize semantic memory
+# Initialize semantic memory (built-in engine)
 memory = AstreaSemanticPlugin()
-memory.initialize({"astrea_url": "http://localhost:8000"})
+memory.initialize({})  # Uses built-in fallback mode
 
 # Learn from past cases
 memory.learn_from_example(
@@ -260,6 +260,16 @@ python examples/semantic_memory_demo.py
 
 **Perfect for**: Healthcare, Finance, Legal, Customer Service
 
+#### 🚀 Future: ASTREA Integration (Coming Soon)
+
+**Enhanced Performance with ASTREA API:**
+- **Current**: 643 searches/sec (built-in fallback)
+- **Future**: 1000+ searches/sec (ASTREA API mode)
+- **Advanced**: Multimodal embeddings (text, images, audio)
+- **Enterprise**: Production-grade semantic engine
+
+*ASTREA integration will be available as an optional premium feature for enhanced performance and advanced capabilities.*
+
 ### LSP (Language Server) Setup
 
 Per abilitare diagnostica in editor e completamento base:

docs/PH_FINAL_COPY.md

@@ -514,9 +514,9 @@ P.S. - Here's the Zenodo paper if you want technical details: https://doi.org/10
 
 ASPERA agents now have **MEMORY**!
 
-Powered by ASTREA (our semantic embedding engine), your AI agents can:
+Powered by our built-in semantic engine, your AI agents can:
 - ✅ Learn from millions of past decisions
-- ✅ Find similar cases instantly (668 searches/second!)
+- ✅ Find similar cases instantly (643 searches/second!)
 - ✅ Make smarter decisions based on what worked before
 - ✅ Scale to millions of examples without performance loss
 
@@ -546,15 +546,15 @@ similar_cases = agent.find_similar(symptoms)
 
 ### Performance
 ```
-Searches: 668 per second
+Searches: 643 per second
 Latency:  <3 milliseconds
 Scale:    Millions of cases
-Mode:     Real-time retrieval
+Mode:     Real-time retrieval (built-in)
 ```
 
 **Try it now**: Download ASPERA + run `python examples/semantic_memory_demo.py`
 
-**Learn more**: [ASTREA Semantic Engine](https://github.com/rthgit/Astrea)
+**Built-in semantic engine**: Zero external dependencies, works out of the box!
 
 ---