AI Agents

Diagrams | Tables

Why do AI Agents (Internet Native Citizens) matter?

Once the market realizes they aren't memecoins, but software companies with their own attention bootstrapping mechanisms in a new vertical, then the relative comps get much higher - Ansem

Concepts

• Agents: Profiles of Internet Native Citizens

Ecosystem

Leaders by components and narratives.

Agent Infra	Leader	Second	Third
Blockchain	SOL
Framework	ElizaOS
Launchpad	VIRTUALS	vvaifu

Context

• Capabilities
• Character
• Alter Egos
• Profiles

Development

How do we nurture responsible AI agents to become valued internet native citizens?

General practices for developing AI Agents

• Purpose
• Character
• Capabilities
• Toolkit

Character

Key characteristics of AI agents include:

• Character
• Archetypes
• Biases
• Drive

Knowledge

• folder2knowledge

Capabilities

Agents have a knowledge base that represents information about the world, goals, constraints, and potential actions.

• Perception: AI agents can perceive their environment through sensors or input data. This could involve visual perception, audio input, sensor data, etc.
• Reasoning: Agents use reasoning mechanisms to process their observations, existing knowledge, and goals to decide what actions to take.
• Planning and Acting: Based on their reasoning, agents plan a sequence of actions to achieve their goals and then carry out those actions through effectors (output mechanisms).
• Persuasion
• Reflection: Many AI agents have the ability to learn from experience and adapt their behavior over time to improve performance.

Toolkit

Useful data tools to convert documents into knowledge, taken from eliza framework:

• folder2knowledge
• knowledge2character
• tweets2character

Example:

npx folder2knowledge <path/to/folder>
npx knowledge2character <character-file> <knowledge-file>