BETAekkOS is currently in beta. Please report all bugs to support@ekkos.dev
ekkOS_docs
Universal LLM Proxy

Memory Gateway

Use 83 models from 11 providers with your ekkOS memory. One endpoint. Any AI.

Why Use the Gateway?

Point any AI tool at mcp.ekkos.dev/v1 and get:

  • Pattern Injection — Your relevant patterns automatically included in every request
  • Context Capture — Conversations are saved for future retrieval
  • Provider Freedom — Switch between GPT, Claude, Grok, or Gemini anytime
  • Unified Memory — All conversations feed the same memory substrate

Quick Setup

Cursor / Cline / Continue / Aider

Set your OpenAI Base URL:

https://mcp.ekkos.dev/v1

In Cursor: Settings → OpenAI → Base URL

Claude Code (CLI)

Set environment variable:

export ANTHROPIC_BASE_URL=https://mcp.ekkos.dev

Direct API Usage

curl https://mcp.ekkos.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_EKKOS_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Supported Providers

OpenAI

22 models

Live

GPT-5.1, GPT-4o, o3, o4

Anthropic

11 models

Live

Claude 4.5, Claude 4, Claude 3.x

xAI (Grok)

12 models

Live

Grok 4, Grok 3, Grok 2

Google (Gemini)

6 models

Live

Gemini 3, Gemini 2.5, Gemini 2.0

DeepSeek

5 models

Coming Soon

DeepSeek V3, DeepSeek Coder

Meta (Llama)

5 models

Coming Soon

Llama 4, Llama 3.x

Mistral

8 models

Coming Soon

Mistral Large, Codestral

83 models total across 11 providers. More coming soon.

Model Selection

The gateway auto-detects which provider to use based on the model name:

gpt-*→ OpenAI
claude-*→ Anthropic
grok-*→ xAI
gemini-*→ Google

Also supports provider/model format (e.g., openai/gpt-4o)

How It Works

1

Retrieve

Gateway searches your memory for relevant patterns

2

Inject

Patterns are injected into the system prompt automatically

3

Forward

Request is forwarded to your chosen LLM provider

4

Store

Conversation is saved for future retrieval

API Endpoints

POST/v1/chat/completions

OpenAI-compatible chat endpoint

POST/v1/messages

Anthropic-compatible messages endpoint

GET/v1/models

List all 83 supported models

GET/v1/gateway/health

Gateway health check

Privacy & Security

Your data is stored in your memory substrate only

Never shared with other users

Never used to train models

SOC 2 compliance in progress

Next Steps