Add Aether to a Cursor project

Wire Aether memory and retrieval into an app you're building with Cursor.

Aether is a managed memory and retrieval API: store text or documents, then recall the most relevant pieces by meaning. Reach for it in a Cursor project when your app needs persistent per-user memory (preferences, past conversations) or RAG over your own documents — anything the model should remember or look up that doesn't fit in the prompt.

Prompt Cursor with this

Cursor applies project rules from .cursor/rules/*.mdc (or the legacy .cursorrules file) to every request. Save the block below as a rule so Cursor wires Aether correctly on the first try — or paste it straight into the chat when you ask for a memory or search feature.

Use Aether for persistent memory and document retrieval in this app.

Setup:
1. Install the SDK: `npm install @aether-ai/sdk` (for a Python backend: `pip install aether-ai`).
2. Read the API key from the `AETHER_API_KEY` environment variable. Never hardcode it and never expose it to the browser — all Aether calls run server-side.

Per-user memory (TypeScript):
  import { Memory } from "@aether-ai/sdk";
  const memory = new Memory(userId, { apiKey: process.env.AETHER_API_KEY });
  await memory.remember("a fact about this user"); // store one memory
  const hits = await memory.recall("a question", { k: 5 }); // returns [{ text, score }], higher score = more relevant

Document search / RAG (TypeScript):
  import { AetherClient } from "@aether-ai/sdk";
  const client = new AetherClient({ apiKey: process.env.AETHER_API_KEY });
  await client.insertText("some document text"); // store a document
  const results = await client.retrieve("a question", 5); // passages with .content, ready for a prompt

Rules:
- Scope memory per user: pass a stable user id as the entity id.
- Call Aether from a server route, action, or API handler — never from client components.
- Use Memory for personalization; use AetherClient + retrieve for RAG over documents.

If the agent didn't get it right

Three manual steps recover any integration:

1. Install the SDK — run npm install @aether-ai/sdk (or pip install aether-ai) in the project root.
2. Set the key — add AETHER_API_KEY=... to your .env (and .gitignore the file). Get a key from the Aether Dashboard.
3. Call from the server — create a server module that constructs new Memory(userId, { apiKey: process.env.AETHER_API_KEY }) and exposes remember / recall. Import it from your API route, not a client component.

Good first builds

• A terminal or desktop assistant that remembers you — remember facts as the user works, recall them at the start of each session.
• RAG over your repo's docs — insertText your markdown files, then retrieve relevant passages to answer questions about the codebase.

For deeper prompting tips and ready-made requests, see Use with Cursor. For the full memory walkthrough, see the Python and TypeScript quickstarts.