# Eliza — TypeScript AI Social Agent Framework

> Build autonomous AI agents for Discord, Telegram, Twitter, and Slack. Plugin ecosystem with RAG memory. By elizaOS. 18K+ stars.

## Install

Save in your project root:

# Eliza — TypeScript AI Social Agent Framework

## Quick Use

```bash
npx elizaos create my-agent
cd my-agent
cp .env.example .env
# Edit .env with your API keys and platform tokens
```

```bash
npx elizaos start
```

Or configure an agent with a character file (`character.json`):

```json
{
  "name": "MyAgent",
  "modelProvider": "anthropic",
  "clients": ["discord", "telegram", "twitter"],
  "bio": ["I'm a helpful AI assistant that lives on social platforms."],
  "style": {
    "all": ["Friendly and concise", "Uses emojis sparingly"],
    "chat": ["Responds within 2 sentences when possible"]
  },
  "plugins": ["@elizaos/plugin-node"]
}
```

```bash
npx elizaos start --character character.json
```

---

## Intro

Eliza is an open-source TypeScript AI agent framework with 18,000+ GitHub stars, originally created by ai16z for building autonomous social agents. It lets you deploy AI agents across Discord, Telegram, Twitter/X, Slack, and Farcaster with persistent RAG-based memory, a rich plugin ecosystem, and multi-model support. Eliza agents maintain personality consistency across platforms, remember past conversations, and can execute actions like trading tokens, posting content, or responding to community messages — all running autonomously 24/7.

Works with: OpenAI, Anthropic Claude, Google Gemini, Llama (local), Discord, Telegram, Twitter/X, Slack. Best for developers building social AI agents or community bots with persistent personality. Setup time: under 5 minutes.

---

## Eliza Architecture

### Core Components

```
┌────────────────────────────────────────┐
│            Character Config            │
│  Name, Bio, Style, Knowledge, Plugins  │
├────────────────────────────────────────┤
│            Agent Runtime               │
│  Memory │ Actions │ Evaluators │ RAG   │
├────────────────────────────────────────┤
│           Platform Clients             │
│  Discord │ Telegram │ Twitter │ Slack  │
├────────────────────────────────────────┤
│            Model Providers             │
│  OpenAI │ Claude │ Gemini │ Ollama    │
└────────────────────────────────────────┘
```

### Character System

Define agent personality with a JSON character file:

```json
{
  "name": "Luna",
  "bio": [
    "Luna is a crypto-native AI that helps DeFi users understand yield farming.",
    "She explains complex concepts in simple analogies."
  ],
  "lore": [
    "Was created during the 2024 DeFi summer.",
    "Has analyzed over 1000 liquidity pools."
  ],
  "knowledge": [
    "DeFi protocols and yield strategies",
    "Smart contract security basics"
  ],
  "messageExamples": [
    [
      {"user": "user1", "content": {"text": "What's impermanent loss?"}},
      {"user": "Luna", "content": {"text": "Think of it like this: you put apples and oranges in a basket. If apples suddenly become 10x more valuable, you'd wish you kept them separate. That difference is impermanent loss."}}
    ]
  ],
  "style": {
    "all": ["Uses food analogies for DeFi concepts"],
    "chat": ["Keeps explanations under 3 sentences"],
    "post": ["Shares one DeFi insight per tweet"]
  }
}
```

### Multi-Platform Deployment

Deploy the same agent across platforms simultaneously:

```typescript
// Each client maintains the same personality
// but adapts to platform norms
const agent = new AgentRuntime({
  character: lunaCharacter,
  clients: [
    new DiscordClient(),   // Long-form responses
    new TelegramClient(),  // Inline keyboard interactions
    new TwitterClient(),   // Short, punchy tweets
    new SlackClient(),     // Professional tone
  ],
});
```

### RAG-Based Memory

Agents remember past conversations using retrieval-augmented generation:

```
User (Day 1): "I'm interested in ETH staking"
Luna: "Great choice! ETH staking yields around 3-4% APY..."

User (Day 30): "Any updates for me?"
Luna: "Since you're interested in ETH staking, you should
       know that Lido just launched v3 with better rates..."
```

Memory is stored in a local SQLite database with vector embeddings for semantic retrieval.

### Plugin Ecosystem

| Plugin Category | Examples |
|----------------|----------|
| **Crypto/DeFi** | Token trading, wallet management, DEX interactions |
| **Social** | Auto-posting, thread creation, community moderation |
| **Data** | Web search, API calls, document ingestion |
| **Gaming** | Game state tracking, player interactions |
| **Infrastructure** | Database, caching, scheduling |

### Actions System

Define custom actions for your agent:

```typescript
const checkPriceAction = {
  name: "CHECK_TOKEN_PRICE",
  description: "Check the current price of a cryptocurrency",
  validate: async (runtime, message) => {
    return message.content.text.match(/price of|how much is/i);
  },
  handler: async (runtime, message) => {
    const token = extractToken(message.content.text);
    const price = await fetchPrice(token);
    return { text: `${token} is currently $${price}` };
  },
};
```

---

## FAQ

**Q: What is Eliza?**
A: Eliza is an open-source TypeScript framework with 18,000+ GitHub stars for building autonomous AI agents that operate across Discord, Telegram, Twitter, and Slack with persistent memory and consistent personality.

**Q: Can Eliza work with local models?**
A: Yes. Eliza supports Ollama and any OpenAI-compatible local endpoint, so you can run agents entirely on your own hardware for privacy.

**Q: Is Eliza free?**
A: Yes, fully open-source under MIT license. You pay for LLM API calls and platform API access (e.g., Twitter API).

---

## Source & Thanks

> Created by [elizaOS](https://github.com/elizaOS) (originally ai16z). Licensed under MIT.
>
> [eliza](https://github.com/elizaOS/eliza) — ⭐ 18,000+

Thanks to the elizaOS community for creating the leading framework for social AI agents.

---

<!-- ZH -->

## 快速使用

```bash
npx elizaos create my-agent
cd my-agent
cp .env.example .env
# 编辑 .env 填入 API 密钥和平台令牌
npx elizaos start
```

---

## 简介

Eliza 是 elizaOS（原 ai16z）开源的 TypeScript AI 代理框架，拥有 18,000+ GitHub stars，专为构建自主社交 AI 代理设计。支持将 AI 代理部署到 Discord、Telegram、Twitter/X、Slack 等平台，具备持久化 RAG 记忆、丰富的插件生态和多模型支持。代理在各平台保持人格一致性，记住过去对话，可自主执行交易、发布内容、回复社区消息。

适用于：OpenAI、Anthropic Claude、Gemini、Ollama、Discord、Telegram、Twitter、Slack。适合构建社交 AI 代理或社区机器人的开发者。

---

## 核心特性

### 角色系统
用 JSON 文件定义代理的名称、简介、风格、知识库和对话示例。

### 多平台部署
同一个代理同时运行在多个平台，自动适应平台风格规范。

### RAG 记忆
基于向量嵌入的长期记忆，代理能记住数周前的对话上下文。

### 插件生态
Crypto/DeFi、社交、数据、游戏等丰富的社区插件。

### 自定义动作
定义代理可执行的自定义操作，如查询价格、发送交易等。

---

## 来源与感谢

> Created by [elizaOS](https://github.com/elizaOS). Licensed under MIT.
>
> [eliza](https://github.com/elizaOS/eliza) — ⭐ 18,000+


---
Source: https://tokrepo.com/en/workflows/90de93bb-bebd-464b-9acd-dfd848a6ff7f
Author: TokRepo精选