AETHER · examples

From your own stackMove to working example.

Explore working server-side HTTP examples for the Compress and Generate endpoints, including RAG and agent integration patterns.

Quick Start Documentation

Sample Gallery

Starting points close to real usage flows.

Explore working server-side HTTP examples for the Compress and Generate endpoints, including RAG and agent integration patterns.

Node.js backend

Fetch and Express with TypeScript or Compress call from Next.js route handler.

Python service

Basic example with async request, timeout, and error handling using HTTPX.

RAG optimization

Pipeline that optimizes the retriever output according to the query and transfers it to the model call.

Agent memory

Flow that minimizes agent results and task history before the next agent step.

Quick Start

Start with a single call.

Generate your API key, submit your input, and use the optimized context with your existing model provider.

Open installation steps →

const response = await fetch("https://api.aether.tr/v1/compress", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <API_KEY>",
    "Idempotency-Key": crypto.randomUUID(),
    "Content-Type": "application/json"
  },
  body: JSON.stringify({ context, query, level: "auto" })
});

const payload = await response.json();
if (!response.ok) throw new Error(payload.error?.code ?? "AETHER_API_ERROR");
const optimizedContext = payload.data.compressed;

Smaller context. More controlled AI cost.

Contact our team to add Aether Compress to your current LLM workflow.