Architecture Overview
GetProfile provides the LLM Proxy for automatic, transparent integration with your existing OpenAI-compatible applications.Proxy Flow (Automatic)
The proxy sits between your application and the LLM provider, enriching every request with user context automatically.Request Flow
1
Request Received
Your app sends a chat completion request to the GetProfile proxy with a user
identifier.
2
Profile Loaded
GetProfile looks up the user’s profile using the
X-GetProfile-Id header or
user field.3
Context Assembled
The proxy gathers:
- User traits (name, preferences, expertise level)
- Profile summary
- Relevant memories from past conversations
4
Prompt Enriched
Context is injected into the system message: ``` ## User Profile Alex is an
experienced software engineer who prefers concise, technical explanations. ##
User Attributes - Communication style: technical - Expertise level: advanced
Relevant Context - User mentioned working on a microservices migration last
week ```5
Request Forwarded
The enriched request is sent to the upstream LLM provider.
6
Response Streamed
The LLM response is streamed back to your app in real-time.
7
Background Processing
After the response completes, GetProfile asynchronously:
- Extracts new traits from the conversation
- Stores relevant memories
- Updates the profile summary if needed
Three-Layer Architecture
Key Components
Memory Engine
Memory Engine
Responsible for: - Storing conversation messages - Extracting facts and
memories using LLM - Retrieving relevant memories for context - Generating
profile summaries
Trait Engine
Trait Engine
Responsible for: - Loading trait schemas (default + custom) - Extracting
structured traits from conversations - Managing confidence scores - Building
injection context
Profile Manager
Profile Manager
Orchestrates: - Profile creation and lookup - Context assembly for requests
- Coordinating memory and trait engines
Choosing an Integration
See the Integration Options guide for detailed comparison.