elizaos/eliza

📈 Trending★ 18,394TypeScriptAudience · developerComplexity · 4/5ActiveLicenseSetup · moderate

Mindmap

mindmap
  root((Eliza))
    What it does
      Build AI agents
      Deploy agents
      Multi-agent coordination
    Core components
      Runtime engine
      Plugin system
      Memory management
    Plugins available
      Discord Telegram
      Web browsing
      Model providers
    Developer tools
      CLI scaffolding
      Web dashboard
      Example projects
    Key features
      Model-agnostic
      Real-time management
      Agent evaluation

mindmap root((Eliza)) What it does Build AI agents Deploy agents Multi-agent coordination Core components Runtime engine Plugin system Memory management Plugins available Discord Telegram Web browsing Model providers Developer tools CLI scaffolding Web dashboard Example projects Key features Model-agnostic Real-time management Agent evaluation

Things people build with this

USE CASE 1

Build a Discord bot that answers questions and performs tasks autonomously without manual intervention.

USE CASE 2

Create a customer support agent that handles inquiries across multiple messaging platforms simultaneously.

USE CASE 3

Deploy coordinated teams of AI agents that work together to research topics and summarize findings.

USE CASE 4

Develop a web-connected agent that browses the internet and searches documents to answer user questions.

Tech stack

TypeScriptNode.jsDiscord APITelegram API

Getting it running

Difficulty · moderate Time to first run · 30min

Requires API keys for Discord/Telegram and Node.js environment setup to see agents in action.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

In plain English

Eliza (elizaOS) is an open source TypeScript framework for building and deploying autonomous AI agents. An "agent" in this context is software that can carry on conversations, perform tasks, and make decisions on its own, connected to various external services. The framework is organized around a few key concepts. The core runtime handles the agent's decision-making loop and memory. Plugins extend the runtime with specific behaviors, for example, there are plugins that connect an agent to messaging platforms like Discord and Telegram, plugins that give agents access to web browsing or document search, and plugins for working with various AI model providers. On top of this plugin system, developers can build full deployable products (called projects) that include their own user interface. Eliza comes with a command-line tool for scaffolding new agents and projects quickly, a web dashboard for managing agents in real time, and support for running multiple coordinated agents together. It also includes a set of ready-made example projects and evaluation tools for testing how well agents perform on various tasks. The project is designed to be model-agnostic, meaning the same agent code can run with different AI models from different providers by swapping configurations. It is licensed under the MIT license.

Copy-paste prompts

Prompt 1

How do I create a new agent using Eliza's CLI tool and connect it to Discord?

Prompt 2

Show me how to write a custom plugin for Eliza that integrates with my own API.

Prompt 3

How do I run multiple coordinated agents together in Eliza and have them share information?

Prompt 4

What's the process for swapping between different AI model providers in an Eliza agent without changing the agent code?

Prompt 5

How do I use Eliza's evaluation tools to test how well my agent performs on specific tasks?

Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.