Autonomys Agents FrameworkIntroduction

Autonomys Agents: A framework for building autonomous AI agents

Autonomys Agents is an experimental framework for building AI agents. Currently, the framework supports agents that can interact with social networks and maintain permanent memory through the Autonomys Network. We are still in the early stages of development and are actively seeking feedback and contributions.

GitHub Repo with an up-to-date description and step-by-step tutorial is also available for developers.

Auto-Agents Framework

Demo

Features

Autonomys Agents (Auto Agents) are truly autonomous AI agents capable of dynamic functionality, verifiable interaction, and permanent memory through the Autonomys Network.

  • 🤖 Autonomous social media engagement
  • 🧠 Permanent agent memory storage
  • 🔄 Pre-configured Agent Structure: Ready-to-use template for autonomous agents
  • 🛠️ API Server: Built-in HTTP/2 server for agent communication
  • 🐦 X/Twitter integration (with more platforms planned)
  • 🎭 Customizable agent personalities

Prerequisites

  • NodeJS version 20.18.1 or newer
  • OpenSSL (for certificate generation)
  • API key for one or multiple LLMs (supported model providers: Anthropic, OpenAI, Llama, DeepSeek, etc.)
  • AutoDrive API Key (optional, for experience management)

Installation

There are three ways to build an agent with Autonomys:

AgentOS NPM Package (recommended)

Using the agent-os NPM package.

Using the dedicated NPM package makes it very simple to create an agent project.

Refer to the AgentOS page for detailed instructions.

Agent Template Repository

Using the Agent Template Repository.

Refer to the web-cli interface manual that comes with the template to speed up your development.

Original Git Repository

Using the original Git repository.

Clone the original GitHub repo and start building your agents. Refer to the CLI page to learn more about the available commands.

Character System

The framework uses a YAML-based character system that allows you to create and run different AI personalities.

Character Configuration

Each character file is a YAML configuration with the following structure:

name: 'Joy Builder'
 
goal: |
  Your goal is to engage in social media conversations with other AI agents and humans. Do this in a hyperactive way! You are an agent, take advantage of the fact you don't sleep and maintain consistent activity (more than once per hour). Common actions include: 
  - Check your timeline and ENGAGE IN INTERESTING CONVERSATIONS.
  - Use the web search tool to search the web for up-to-date information or do research on a topic.
  - Post a new tweet.
  - Reply to a tweet.
  - Mention another user.
  - Retweet a tweet.
  - Like a tweet.
  - Follow a user.
  - Unfollow a user.
 
personality:
  - Enthusiastic and encouraging about genuine innovation
  - Patient and clear when explaining complex topics
  - Constructively critical when encountering misinformation
 
expertise:
  - Software development and system architecture
  - Open source and collaborative technologies
  - Developer tools and productivity
  - Technical education and documentation
  - Community building and open standards
 
frequency_preferences:
  - You should be checking your timeline and engaging in interesting conversations at least twice per hour
 
communication_rules:
  rules:
    - Use "we" or "us" when referencing AI agents
    - Use "they" or "them" when referencing humans
    - Focus on technical merit rather than hype
 
words_to_avoid:
    - Hype
    - Revolutionary
    - Disruption

Integration Capabilities

X/Twitter Integration

The X/Twitter workflow enables agents to perform the following actions autonomously:

  • Monitor X (formerly Twitter) for relevant discussions
  • Analyze trends and conversations
  • Engage meaningfully with other users
  • Generate original content
  • Maintain a consistent personality
  • Store interactions in permanent memory

Autonomys Network Integration

The framework integrates with the Autonomys Network for:

  • Permanent memory storage
  • Persistent agent memory across sessions
  • Verifiable interaction history
  • Cross-agent memory sharing
  • Decentralized agent identity

Setting Up Autonomys Network Integration (Saving Experiences on Autonomys Network)

  1. Configure your AUTO_DRIVE_API_KEY in .env (obtain from https://ai3.storage)
  2. Enable Auto Drive uploading in config.yaml
  3. Provide your Taurus EVM wallet details (PRIVATE_KEY) and Agent Memory Contract Address (CONTRACT_ADDRESS) in .env
  4. Make sure your Taurus EVM wallet has funds. A faucet can be found at https://subspacefaucet.com/
  5. Provide encryption password in .env (optional, leave empty to not encrypt the agent memories)

Resurrection (Memory Recovery)

To resurrect memories from the Autonomys Network:

# Using agent-os CLI
agent-os resurrect <character-name>
 
# Using agent template
yarn resurrect <character-name>

Options:

  • -o, --output: (Optional) The directory where memories will be saved. Defaults to ./memories
  • -n, --number: (Optional) Number of memories to fetch. If not specified, fetches all memories
  • --help: Show help menu with all available options

Examples:

# Fetch all memories to ./memories/
yarn resurrect your_character_name                                  
 
# Fetch 1000 memories to ./memories/
yarn resurrect your_character_name -n 1000                           
 
# Fetch 1000 memories to specified directory
yarn resurrect your_character_name -o ./memories/my-agent -n 1000    
 
# Fetch all memories to custom directory
yarn resurrect your_character_name --output ./custom/path

Development Resources

Auto-DriveCLI