Skip to main content

ElizaOS Framework

Diagrams | Tables

Framework and Platform for Smart Crypto Agents.

Website | Github

Features​

  • 🛠️ Full-featured Discord, Twitter and Telegram connectors
  • 🔗 Support for every model (Llama, Grok, OpenAI, Anthropic, etc.)
  • 👥 Multi-agent and room support
  • 📚 Easily ingest and interact with your documents
  • 💾 Retrievable memory and document store
  • 🚀 Highly extensible - create your own actions and clients
  • ☁️ Supports many models (local Llama, OpenAI, Anthropic, Groq, etc.)

Getting Started​

Coordination​

Guide to aligning and coordinating development efforts.

Resources for coordination of contributors.

ResourcePurpose
elizaos.github.io
Discord
GitHub
TelegramNot used?

Perfect use case (demonstrable value proposition) for a team of of Eliza Agents. Every person / organisation suffers from analysis paralysis and decision fatigue. Eliza Agents can sift though the noise and point out best lines of focused attention for maximum value extraction.

Architecture Overview​

Onboarding​

Educational resources on YouTube etc.

tip

Remember to pnpm run clean && pnpm run build

Other

Core Concepts​

Core code in core, lightweight and runs in the browser.

  • Agent: These are the core elements that represent individual AI personalities. Agents operate within a runtime environment and interact with various platforms.
  • Character: These JSON files define the personality, knowledge, and behavior of each AI agent.
  • Clients: Clients act as interfaces between agents and specific platforms, such as Discord, Twitter, and Telegram. They handle platform-specific message formats and communication protocols.
  • Actions: Actions are predefined behaviors that agents can execute in response to messages, enabling them to perform tasks and interact with external systems.
  • Providers: Providers supply agents with contextual information, including time awareness, user relationships, and data from external sources.
  • Evaluators: These modules assess and extract information from conversations, helping agents track goals, build memory, and maintain context awareness.
  • Memory System: Eliza features a sophisticated memory management system that utilizes vector embeddings and relational database storage to store and retrieve information for agents.
  • Plugins: Plugins are modular way to extend the core functionality with additional features by bundling actions, evaluators, and providers. They are self-contained modules that can be easily added or removed to customize your agent's capabilities.

Agent​

The AgentRuntime class manages the agent's core functions, including:

  • Message and Memory Processing: Storing, retrieving, and managing conversation data and contextual memory.
  • State Management: Composing and updating the agent’s state for a coherent, ongoing interaction.
  • Action Execution: Handling behaviors such as transcribing media, generating images, and following rooms.
  • Evaluation and Response: Assessing responses, managing goals, and extracting relevant information.

Character​

A json file that implements the Character type defines an agent's characteristics:

  • Core identity and behavior
  • Model provider configuration
  • Client settings and capabilities
  • Interaction examples and style guidelines

Context Providers​

A provider's primary purpose is to:

  • Supply dynamic contextual information
  • Integrate with the agent runtime
  • Format information for conversation templates
  • Maintain consistent data access

Learning​

Actions​

Each Action consists of:

  • name: Unique identifier for the action
  • similes: Array of alternative names/variations
  • description: Explains when and how the action should be used
  • validate: Function that checks if action is appropriate
  • handler: Implementation of the action's behavior, args:
    • runtime: IAgentRuntime
    • message: Memory
    • state: Aim to reuse but can be recreated fresh (CHECK LOGIC)
    • options:
    • callBack
  • examples: Array of example usage patterns

Patterns​

  • Set required state, typically import but can create.

Common Issues​

Action Not Triggering

  • Check validation logic

  • Verify similes list

  • Review example patterns

  • Handler Failures

    • Validate service availability
    • Check state requirements
    • Review error logs

State Inconsistencies

  • Verify state updates
  • Check concurrent modifications
  • Review state transitions

Learning​

Evaluators​

Evaluators enable agents to:

  • Build long-term memory
  • Track goal progress
  • Extract facts and insights
  • Maintain contextual awareness

Knowledge base:

DB Adapters​

Store long-term memories. SQLite is full featured, can be deleted to wipe memories and will recreated during exploration, graduate to a supabase etc once you need to persist memories.

  • SQLite (default)
  • Supabase (easy)
  • Convex?

Knowledge base:

Clients​

Talk to the outside world. Code being refactored to unify underlying messaging architecture so that clients will be able to send to other clients (metaverse). Roperito dev lead.

Knowledge base:

Plugins​

Very important, wraps everything for your agent. The bootstrap plugin contains essential providers, actions, evaluators. Node plugin provides essential services such as transcription, summarization, but cannot be run in the browser, intent is to create a browser plugin to replicate the same functionality without server dependencies.

  • Memory Manager: State of Mind.
  • Providers: Contextual information from outside world.
  • Actions: Protocols and tools to communicate/execute intentions.
  • Evaluators: Build long-term memory.
  • Clients: Talk to the outside world.

Progress

  • Move Plugins into community repo
  • Browser Plugin

Knowledge base:

Questions:

  • Duplicated code for reimplementation of common functionality?
  • What is process for approving plugins into release?
  • How do you prioritize flow of plugin logic?
  • How is best in class implementation decided?

Development​

New Plugin​

  • Copy and Paste Bootstrap Plugin
  • Search for plugin-bootstrap and rename as plugin-yourname
  • Delete all but one guide from Providers, Actions, Evaluators
  • Replace code with logic matching same patterns

FuturePotential​

DeFi Routing​

Primary Value Drivers​

  • Barrier Reduction: AI agents can significantly lower the barrier to entry for DeFi protocols by explaining complex concepts and guiding users through transactions.
  • Clear Revenue Potential: DeFi applications offer obvious ways for agents to generate value through arbitrage and liquidity provision.
  • Automation Capabilities: Agents can automate complex DeFi operations like managing liquidity pools, monitoring token ranges, and handling yield strategies.

Specific Applications​

Liquidity Management

  • Automated monitoring of liquidity pool positions
  • Smart rebalancing when tokens go out of range
  • Automatic yield reinvestment and wallet management

Market Intelligence

  • Converting unstructured social data into actionable trading insights
  • Identifying top performers and reliable forecasters
  • Tracking community sentiment for trading signals

Marketing and Sales​

Shift from basic reply bots to product-focused AI agents that actively connect products with their ideal customers.

User Discovery​

  • Agents will actively identify people expressing specific needs or pain points across social platforms
  • Instead of random shilling, agents will match solutions to relevant user problems
  • Focus on helping users arrive at solutions rather than pushing products

Interaction Model​

Direct Problem Solving

  • Agents will respond to user queries with relevant product solutions
  • Act as a "new Google" by connecting users directly to products that solve their problems
  • Provide immediate, contextual support rather than generic marketing

Value-Based Engagement

  • Move beyond basic shilling to creating actual user value
  • Help users understand how products solve their specific challenges
  • Build trust through helpful interactions rather than spam

Effort vs Timeline​

Developers could build basic product-matching agents within a week. The key elements needed are:

  • Social monitoring capabilities
  • Natural language understanding of user needs
  • Product knowledge and recommendation systems
  • Trust-building conversation abilities

Marketplace of Trust​

The Marketplace of Trust is a sophisticated framework being developed by AI16z that creates a self-reinforcing feedback loop for AI agent trading. The system allows agents to gain insights from community members while building trust through transparent performance metrics.

Trust Mechanism​

Scoring System

  • Trust scores range from 0 to 1 (normalized to 100)
  • Scores are publicly displayed on leaderboards
  • Higher-scoring users gain more influence in the system

Validation Process

  • Agents simulate trades based on community suggestions
  • Performance results update trust scores automatically
  • System optimizes strategies through iterative learning

Data Flywheel​

The marketplace creates a powerful feedback loop through:

  • Historical trading performance tracking
  • Community suggestion integration via Discord
  • Quantitative metrics combined with qualitative insights

Safety Features​

Trading Restrictions

  • Minimum $1,000 liquidity requirement
  • $100,000 market cap threshold
  • No single entity can control more than 50% of tokens

Future Vision​

The marketplace aims to evolve into a decentralized mutual fund where:

  • AI agents can autonomously evaluate trading suggestions
  • Trust scores determine influence rather than capital
  • The system becomes increasingly intelligent through collective learning

The ultimate goal is to create a transparent, self-reinforcing system where AI agents can operate autonomously while maintaining accountability through community oversight and performance metrics.

Partnerships​

Agent Ecosystem​

Family of Smart Agents spawned from the Eliza Framework.

Progress​

Project Plans

Notable Issues and PRs:

What did you get done this week

Analysis​