from aegis_memory import AegisClient

# Connect to Aegis
client = AegisClient(
    api_key="dev-key",
    base_url="http://localhost:8000"
)

# Store a memory
result = client.add(
    content="User prefers dark mode and Python",
    agent_id="assistant",
    user_id="user_123"
)

print(f"Stored memory: {result.id}")

# Query by semantic similarity
memories = client.query(
    query="What are the user's preferences?",
    user_id="user_123",
    top_k=5
)

for memory in memories:
    print(f"- {memory.content} (score: {memory.score:.2f})")

- User prefers dark mode and Python (score: 0.94)

# Add more memories
client.add("User is a backend developer", user_id="user_123")
client.add("User's project uses FastAPI", user_id="user_123")
client.add("User prefers async/await patterns", user_id="user_123")

# Now query for tech stack
memories = client.query("What tech stack does the user use?", user_id="user_123")
for m in memories:
    print(f"- {m.content}")

- User's project uses FastAPI
- User prefers async/await patterns
- User is a backend developer
- User prefers dark mode and Python

# Get context for an LLM prompt
context = client.query(
    query="user preferences for code generation",
    user_id="user_123",
    top_k=3
)

context_str = "\n".join([f"- {m.content}" for m in context])

prompt = f"""Based on what you know about this user:
{context_str}

Generate a FastAPI endpoint for user authentication."""

# Now send to your LLM of choice