SDKs & Libraries

Stable

Integrate elizaOS Cloud with official SDKs and community libraries.

Quick Start

Since elizaOS Cloud is 100% OpenAI API compatible, you can use any existing OpenAI SDK by simply changing the base URL. No special SDK required!

TypeScript


import OpenAI from 'openai';
 
const client = new OpenAI({
apiKey: process.env.ELIZA_API_KEY,
baseURL: 'https://cloud.milady.ai/api/v1',
});
 
const response = await client.chat.completions.create({
model: 'gpt-4o',
messages: [{ role: 'user', content: 'Hello!' }],
});
 
console.log(response.choices[0].message.content);

Python


from openai import OpenAI
 
client = OpenAI(
    api_key="ek_xxx",
    base_url="https://cloud.milady.ai/api/v1"
)
 
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)
 
print(response.choices[0].message.content)

cURL


curl -X POST "https://cloud.milady.ai/api/v1/chat/completions" \
  -H "Authorization: Bearer $ELIZA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

JavaScript / TypeScript

Installation


npm install openai
# or
bun add openai

Basic Usage


import OpenAI from "openai";
 
const client = new OpenAI({
  apiKey: process.env.ELIZA_API_KEY,
  baseURL: "https://cloud.milady.ai/api/v1",
});

Streaming


const stream = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Tell me a story" }],
  stream: true,
});
 
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

Embeddings


const embedding = await client.embeddings.create({
  input: "Hello world",
  model: "text-embedding-3-small",
});

Python

Installation


pip install openai

Basic Usage


from openai import OpenAI
 
client = OpenAI(
    api_key="ek_xxx",
    base_url="https://cloud.milady.ai/api/v1"
)
 
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)
 
print(response.choices[0].message.content)

Streaming


stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)
 
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

elizaOS-Specific APIs

For APIs that extend beyond OpenAI compatibility (images, video, voice), use direct HTTP calls:

Image Generation


const response = await fetch("https://cloud.milady.ai/api/v1/generate-image", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ELIZA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    prompt: "A sunset over mountains",
    model: "google/gemini-2.5-flash-image",
  }),
});
 
const data = await response.json();
console.log(data.images[0].url);

Video Generation


const response = await fetch("https://cloud.milady.ai/api/v1/generate-video", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ELIZA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    prompt: "A cat playing piano",
    model: "fal-ai/veo3",
  }),
});
 
const data = await response.json();
console.log(data.video.url);

Framework Integrations

LangChain


import { ChatOpenAI } from "@langchain/openai";
 
const model = new ChatOpenAI({
  openAIApiKey: process.env.ELIZA_API_KEY,
  configuration: {
    baseURL: "https://cloud.milady.ai/api/v1",
  },
  modelName: "gpt-4o",
});
 
const response = await model.invoke("Hello!");

Vercel AI SDK


import { generateText } from "ai";
import { createOpenAI } from "@ai-sdk/openai";
 
const openai = createOpenAI({
  apiKey: process.env.ELIZA_API_KEY,
  baseURL: "https://cloud.milady.ai/api/v1",
});
 
const { text } = await generateText({
  model: openai("gpt-4o"),
  prompt: "Hello!",
});

LlamaIndex


from llama_index.llms.openai import OpenAI
 
llm = OpenAI(
    api_key="ek_xxx",
    api_base="https://cloud.milady.ai/api/v1",
    model="gpt-4o"
)
 
response = llm.complete("Hello!")

MCP Client

Connect to elizaOS Cloud MCP endpoint:


import { Client } from "@modelcontextprotocol/sdk";
 
const client = new Client({
  url: "https://cloud.milady.ai/api/mcp",
  headers: {
    Authorization: `Bearer ${process.env.ELIZA_API_KEY}`,
  },
});
 
await client.initialize();
 
const tools = await client.listTools();
const result = await client.callTool("generate_image", {
  prompt: "A sunset",
});

Community Libraries

Since elizaOS Cloud is OpenAI-compatible, you can use any OpenAI SDK in your preferred language:

Language	Library	Installation
Go	`sashabaranov/go-openai`	`go get github.com/sashabaranov/go-openai`
Rust	`async-openai`	`cargo add async-openai`
Ruby	`ruby-openai`	`gem install ruby-openai`
PHP	`openai-php/client`	`composer require openai-php/client`

Simply configure the base URL to https://cloud.milady.ai/api/v1 and use your elizaOS API key.

Feature Support

Feature	OpenAI SDK	Direct REST
Chat Completions	✅	✅
Streaming	✅	✅
Embeddings	✅	✅
Image Generation	❌	✅
Video Generation	❌	✅
Voice / TTS	❌	✅
Knowledge Base	❌	✅
MCP Tools	❌	✅
Agents API	❌	✅

OpenAI SDK compatibility covers chat, embeddings, and streaming. For elizaOS-specific features like image/video generation, use direct REST calls.

Contributing

We welcome SDK contributions! See our GitHub for guidelines.

Next Steps

Complete API documentation

API Reference

Get started quickly

Quickstart

Code examples

Examples