A production-level framework for creating, managing, and evolving AI agents to solve complex tasks through collaboration.
What is Evolving Agents?
Evolving Agents is an open-source framework designed for creating, managing, and evolving AI agents. It enables intelligent agents to communicate, collaborate, and evolve based on semantic understanding and past experiences, making it ideal for solving complex tasks. The framework supports core functionalities like intelligent agent evolution, inter-agent communication, and semantic search.
Key Features
- Intelligent Agent Evolution: Dynamically reuses, evolves, or creates new agents based on semantic similarity.
- Inter-Agent Communication: Supports task delegation and collaboration using standardized protocols like ACP.
- Semantic Search & Smart Library: Quickly finds relevant agents or tools using semantic search.
- YAML Workflow: Defines complex agent collaboration processes using human-readable YAML.
- Multi-Framework Support: Integrates agents from frameworks like BeeAI and OpenAI.
- Governance & Firmware Injection: Enforces domain-specific rules for system stability.
Technical Principles
- Semantic Understanding: Uses NLP techniques to convert text into semantic vectors for similarity assessment.
- Agent Communication Protocol (ACP): Implements JSON-RPC-based communication for efficient collaboration.
- Smart Library: Central repository for agents with version control and performance tracking.
- YAML Workflow: Breaks down complex tasks into steps executed by specialized agents.
Use Cases
- Document Processing: Automates analysis of invoices and contracts.
- Healthcare: Coordinates medical diagnosis and record management.
- Financial Services: Conducts risk assessment and investment analysis.
- Customer Service: Intelligently resolves customer issues.
Getting Started
Visit the GitHub repository to explore the framework and its documentation.