Skip to content

sei-protocol/sei-agent

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

30 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Sei Agent πŸ€–

An intelligent AI-powered Twitter bot that autonomously generates content, engages with users, and provides real-time market insights for the Sei blockchain ecosystem.

License: MIT Node.js TypeScript


Table of Contents

  1. What is Sei Agent?
  2. Key Features
  3. Quick Start
  4. Character System
  5. Contributing

What is Sei Agent?

Sei Agent is an autonomous AI Twitter bot built specifically for the Sei blockchain ecosystem. It combines advanced AI capabilities with real-time market data to create engaging, informative content while maintaining authentic interactions with the crypto community.

Why Sei Agent?

  • 🎯 Purpose-Built: Designed specifically for blockchain and DeFi communities
  • 🧠 Intelligent: Uses advanced AI to generate contextual, relevant content
  • ⏰ Autonomous: Runs 24/7 with smart scheduling and content planning
  • πŸ“Š Data-Driven: Integrates real-time market data, news, and analytics
  • 🎭 Personality: Customizable character aspects for authentic engagement
  • πŸ”§ Extensible: Plugin-based architecture for easy customization

Key Features

πŸ€– Autonomous Content Generation

  • Smart Scheduling: Automated posting with customizable timing
  • Market Intelligence: Real-time crypto market data and analysis
  • News Integration: Automated business and world news updates
  • Dynamic Personality: Multiple character aspects that activate based on time and context

🐦 Advanced Twitter Integration

  • Intelligent Replies: Context-aware responses to mentions and interactions
  • Target Engagement: Actively engages with specified accounts
  • Anti-Spam Protection: Built-in similarity detection and rate limiting
  • Dry Run Mode: Test your bot without actually posting

πŸ“Š Data & Analytics

  • Stock Market Data: Automated stock and crypto market updates
  • Dune Analytics: On-chain data insights and metrics
  • Sei Network Stats: Real-time blockchain analytics
  • Custom Data Sources: Extensible plugin system for new data feeds

βš™οΈ Easy Configuration

  • Character Profiles: JSON-based character configuration
  • Flexible Scheduling: Cron-style job scheduling
  • Environment Variables: Simple .env file configuration
  • Multiple Personalities: Switch between different character aspects

Quick Start

Prerequisites

  • Node.js v23.3.0 (use nvm use to switch versions)
  • pnpm package manager
  • OpenAI API key
  • Twitter account credentials
  • Docker (optional, for containerized setup)

Installation

  1. Clone and install

    git clone https://github.com/your-org/sei-agent.git
    cd sei-agent
    nvm use  # Switch to Node v23.3.0
    pnpm install # export SHARP_IGNORE_GLOBAL_LIBVIPS=1 if sharp error
  2. Configure environment

    cp .env.example .env
    # Add your OpenAI API key and Twitter credentials to .env
  3. Create database

    mkdir -p data
    touch data/db.sqlite
  4. Build Project

    pnpm run build
  5. Start the agent

    pnpm start --character=characters/sensei1202.character.json

    That's it! Your Sei Agent will start posting and engaging automatically. πŸŽ‰

Docker Setup (Alternative)

You can also run Sei Agent in a Docker container:

  1. Ensure Docker daemon is running on your system

  2. Build and start the Docker container

    pnpm docker

    This command builds the Docker image, starts the container, and gives you a bash shell inside the container.

  3. Start the agent inside the container

    pnpm start --character=characters/sensei1202.character.json

VS Code Development Container

For VS Code users, this project includes devcontainer support for an integrated development experience:

  1. Install the Remote - Containers extension in VS Code
  2. Open the project folder in VS Code
  3. Click the green button in the lower left corner or run the Remote-Containers: Reopen in Container command
  4. VS Code will build and start the container, then connect to it automatically

Need detailed setup help? See our comprehensive Setup Guide for environment variables, troubleshooting, and advanced configuration.


Character System

Sei Agent uses a sophisticated character system that enables dynamic personality switching and contextual behavior.

Character Aspects

Each character can have multiple "aspects" that activate based on time and context:

Example Aspects

  • πŸͺ Trader: Market analysis and trading insights
  • 🧘 Meditation: Zen philosophy and mindfulness content
  • πŸ’¨ Breathwork: Breathing techniques and wellness
  • β‚Ώ Crypto Enthusiast: General crypto market commentary
  • ☯️ Zen Practitioner: Philosophical and spiritual content

Dynamic Scheduling

Aspects activate automatically based on:

  • Time of day: Different personalities for different hours
  • Day of week: Weekend vs weekday behavior
  • Intensity levels: How active each aspect should be
  • Weights: Priority when multiple aspects overlap

Customization

Create your own character by editing JSON files:

{
  "name": "YourBot",
  "bio": "Your bot's personality...",
  "characterBios": {
    "aspects": {
      "trader": {
        "bio": "Market expert personality",
        "weight": 5,
        "schedules": [
          {
            "days": [1, 2, 3, 4, 5],
            "hours": [9, 15],
            "intensity": 0.8
          }
        ]
      }
    }
  }
}

Contributing

We welcome contributions to Sei Agent! Here's how you can help:

Development Setup

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/amazing-feature
  3. Make your changes and test thoroughly
  4. Submit a pull request

Areas for Contribution

  • New Plugins: Add support for additional data sources or platforms
  • Character Templates: Create new personality templates
  • Analytics: Improve data visualization and reporting
  • Security: Enhance safety and rate limiting features
  • Documentation: Improve guides and examples

Code Style

  • Use TypeScript for type safety
  • Follow existing code patterns
  • Add tests for new features
  • Update documentation as needed

License

MIT License - see LICENSE file for details.


Support


Built with ❀️ for the Sei ecosystem

Powered by ElizaOS and the open source community

About

An open source Sei agent built with Eliza

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •