Introducing Memly — Zero Friction Context for LLMs. Learn more →

Documentation

Quickstart

Get Memly running in under 5 minutes.

1

Create an account & get your API key

Sign up at Memly, go to the dashboard, and generate an API key. You'll get a key starting with cr_key_.

2

Configure your upstream provider

In the dashboard, add your OpenAI, Anthropic, or Gemini API key. Memly stores it encrypted (AES-256) and uses it to forward your requests.

3

Change your base URL

Replace your LLM provider's base URL with Memly. That's the only code change needed.

# Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
api_key="cr_key_your_key_here",
base_url="https://api.Memly/v1"
)

response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "user", "content": "Explain the auth module"}
]
)
4

Check the response headers

Memly injects diagnostic headers into every response so you can monitor context injection.

X-Context-Router-Mode: active
X-Context-Router-Latency-Ms: 47
X-Context-Router-Project-Id: org:abc:my-project
X-Context-Router-Cache-Hit: true
X-Context-Router-Memories-Injected: 3

Self-Hosted Deployment

For teams that need full data sovereignty, Memly can be deployed on your own infrastructure.

# Clone and run with Docker
$ git clone https://github.com/Memly/Memly
$ cp .env.example .env
$ docker compose up -d

# Your instance is now running at localhost:3700

Need more help?

Join our community or check the full API reference.