Overview

<Card title="$elizaOS Token Information" icon="coins" href="/tokenomics" color="#0B35F1"

Tokenomics, contract addresses, vesting schedules, and token release details </Card>

Build AI Agents in Your Language

elizaOS is available in TypeScript, Python, and Rust with identical APIs. Choose your preferred language and get started in minutes.

<CardGroup cols={3}> <Card title="TypeScript" icon="js" href="/quickstart#typescript"> The original elizaOS experience. Full Node.js ecosystem. </Card> <Card title="Python" icon="python" href="/quickstart#python"> Pythonic APIs with Pydantic models and async/await. </Card> <Card title="Rust" icon="gear" href="/quickstart#rust"> Native performance + WebAssembly for browser deployment. </Card> </CardGroup>

---

Three Commands. Any Language.

<Tabs> <Tab title="TypeScript"> ```bash bun i -g elizaos # Install the CLI elizaos create # Create your project elizaos start # Your agent is live ``` </Tab> <Tab title="Python"> ```bash pip install elizaos # Install the package python -c "from elizaos import *" # Verify installation python your_agent.py # Run your agent ``` </Tab> <Tab title="Rust"> ```bash cargo add elizaos # Add to Cargo.toml cargo build # Build your project cargo run # Run your agent ``` </Tab> </Tabs> <CardGroup cols={2}> <Card title="Quickstart" icon="rocket" href="/quickstart" horizontal /> <Card title="Examples Gallery" icon="grid-2" href="/examples/overview" horizontal /> <Card title="What You Can Build" icon="lightbulb-on" href="/what-you-can-build" horizontal /> <Card title="Plugin Registry" icon="puzzle-piece" href="/plugin-registry/overview" horizontal /> </CardGroup>

---

Why elizaOS?

<CardGroup cols={3}> <Card title="Multi-Language" icon="code"> Identical APIs in TypeScript, Python, and Rust </Card> <Card title="90+ Plugins" icon="puzzle-piece"> Discord, X, Telegram, Ethereum, Solana, OpenAI, and more </Card> <Card title="Persistent Memory" icon="brain"> Agents remember and learn from every interaction </Card> <Card title="Deploy Anywhere" icon="server"> Local, Docker, AWS, GCP, Vercel, Cloudflare, or your own infrastructure </Card> <Card title="Browser Ready" icon="globe"> Run agents client-side with WASM and PGLite </Card> <Card title="Truly Open" icon="code-branch"> Every line is open source. Extend, contribute, build together. </Card> </CardGroup>

Your agents can trade onchain, manage social media, create content, analyze data, or interact with any API, blockchain, or repository.

---

API Consistency Across Languages

All three implementations share identical interfaces:

Operation	TypeScript	Python	Rust
Create runtime	new AgentRuntime({...})	AgentRuntime(...)	AgentRuntime::new(...)
Initialize	await runtime.initialize()	await runtime.initialize()	runtime.initialize().await
Use model	runtime.useModel(type, params)	runtime.use_model(type, params)	runtime.use_model(type, params).await
Handle message	messageService.handleMessage(...)	message_service.handle_message(...)	message_service().handle_message(...)
Stop	await runtime.stop()	await runtime.stop()	runtime.stop().await

---

Quick Example

<Tabs> <Tab title="TypeScript"> ```typescript import { AgentRuntime } from '@elizaos/core'; import { openaiPlugin } from '@elizaos/plugin-openai'; import { plugin as sqlPlugin } from '@elizaos/plugin-sql';

const runtime = new AgentRuntime({ character: { name: 'Eliza', bio: 'A helpful AI assistant.', }, plugins: [sqlPlugin, openaiPlugin], });

await runtime.initialize(); console.log('Agent is ready!');

</Tab> <Tab title="Rust"> ```rust use elizaos::{AgentRuntime, RuntimeOptions, parse_character}; use elizaos_plugin_openai::create_openai_plugin;

#[tokio::main] async fn main() -> anyhow::Result<()> { let character = parse_character(r#"{ "name": "Eliza", "bio": "A helpful AI assistant." }"#)?;

}