Initial commit: standalone vector memory server

REST API for per-agent semantic memory retrieval.

- FastAPI server with /api/{agent}/save and /api/{agent}/query
- ChromaDB for persistent vector storage
- all-MiniLM-L6-v2 via sentence-transformers for embeddings
- Per-agent collections for clean separation
- Config through env vars or config.py
- .venv ready with all dependencies

requirements.txt

@@ -0,0 +1,9 @@
+# Vector Memory Server
+# Install: pip install -r requirements.txt
+
+fastapi>=0.115.0
+uvicorn[standard]>=0.34.0
+chromadb>=0.6.0
+sentence-transformers>=3.4.0
+numpy>=2.0.0
+pydantic>=2.0.0