Use case

AI memory API for agents and LLM apps

Mnexium gives AI products persistent memory, chat history, user profiles, structured records, and agent state through one API. Use it when your app needs to remember users and carry context across sessions.

Short answer

An AI memory API is the durable context layer between your application and the model. Mnexium handles learning, recall, history, profiles, records, and state so teams can keep using OpenAI, Claude, or Gemini while adding long-term context.

Persistent memory

Store facts, preferences, summaries, and context that should survive beyond one prompt.

Chat history

Attach conversations to stable subject and chat IDs so users can resume where they left off.

Profiles and records

Keep structured user and application data available to the model when it matters.

Provider flexibility

Use OpenAI, Anthropic Claude, and Google Gemini without rebuilding memory logic per provider.

Minimal API example

Add an mnx object to a model request to control memory learning, memory recall, and history.

curl -X POST "https://mnexium.com/api/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "x-mnexium-key: $MNX_KEY" \
  -H "x-openai-key: $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{ "role": "user", "content": "Remember that I prefer concise answers." }],
    "mnx": {
      "subject_id": "user_123",
      "chat_id": "chat_abc",
      "learn": true,
      "recall": true,
      "history": true
    }
  }'

When Mnexium is a fit

  • Your product needs memory across sessions, not just within one chat window.
  • You need profiles, records, and state alongside semantic memory.
  • You want a managed memory layer instead of maintaining extraction, retrieval, and context assembly yourself.
  • You need provider portability across OpenAI, Claude, and Gemini.

Next steps