Skip to main content
The easiest way to add persistent memory to your AI application. Simply point your existing OpenAI SDK to GetProfile’s base URL and everything else works automatically.

​
How It Works

┌─────────────────┐     ┌──────────────────────────────────┐     ┌─────────────────┐
│                 │     │         GetProfile Proxy          │     │                 │
│   Your App      │────▶│                                  │────▶│   LLM Provider  │
│                 │     │  1. Load user profile            │     │   (OpenAI, etc) │
│                 │     │  2. Retrieve relevant memories   │     │                 │
└─────────────────┘     │  3. Inject context into prompt   │     └─────────────────┘
                        │  4. Forward to LLM               │
                        │  5. Stream response back         │
                        │  6. Extract traits (background)  │
                        └──────────────────────────────────┘

​
Quick Start

import OpenAI from 'openai';

const client = new OpenAI({
apiKey: 'gp_your_getprofile_key',
baseURL: 'http://localhost:3100/v1', // Or your GetProfile instance
defaultHeaders: {
'X-GetProfile-Id': 'user-123', // Your app's user ID
'X-Upstream-Key': 'sk-your-openai-key',
},
});

// Use exactly like OpenAI - memory is automatic!
const response = await client.chat.completions.create({
model: 'gpt-5',
messages: [{ role: 'user', content: 'Hello!' }],
});

​
Required Headers

HeaderDescriptionRequired
AuthorizationYour GetProfile API key (Bearer gp_...)Yes
X-GetProfile-IdYour app’s user identifierYes*
X-Upstream-KeyYour LLM provider API keyYes
*Can also be provided via body.user or body.metadata.profile_id

​
What Gets Injected

GetProfile automatically adds a system message with user context: 
## User Profile
Alex is an experienced software engineer who prefers concise, technical explanations.
They work primarily with Python and have been exploring distributed systems.

## User Attributes
- Communication style: technical
- Detail preference: brief
- Expertise level: advanced

## Relevant Context
- User mentioned working on a microservices migration last week
- User prefers async/await patterns over callbacks

​
Streaming Support

GetProfile fully supports streaming responses: 
const stream = await client.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Hello!" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}
Background trait extraction happens after the stream completes.

​
Per-Request Trait Overrides

You can override the trait schema for individual requests: 
const response = await client.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Help me plan my trip" }],
  // @ts-ignore - GetProfile extension
  extra_body: {
    getprofile: {
      traits: [
        {
          key: "travel_preferences",
          valueType: "array",
          extraction: {
            enabled: true,
            promptSnippet: "Extract travel style preferences",
          },
          injection: {
            enabled: true,
            template: "User travel preferences: {{value}}",
          },
        },
      ],
    },
  },
});

​
Configuration

See Configuration Overview for full proxy configuration options.

​
Next Steps

Trait Schemas

Customize what GetProfile extracts

JavaScript SDK

Programmatic access from Node.js/TypeScript