EvoAgentX
🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
What is EvoAgentX?
🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
Overview of EvoAgentX
What it is
EvoAgentX is an open-source framework for building, evaluating, and evolving LLM-based agents or agentic workflows in an automated, modular, and goal-driven manner. It enables developers and researchers to move beyond static prompt chaining or manual workflow orchestration by introducing a self-evolving agent ecosystem where AI agents can be constructed, assessed, and optimized through iterative feedback loops.
Key features
- Agent Workflow Autoconstruction: From a single prompt, EvoAgentX builds structured, multi-agent workflows tailored to the task.
- Built-in Evaluation: It integrates automatic evaluators to score agent behavior using task-specific criteria.
- Self-Evolution Engine: Agents improve workflows using self-evolving algorithms.
- Plug-and-Play Compatibility: Easily integrate original OpenAI, Qwen, Claude, Deepseek, Kimi models through LiteLLM, siliconflow, or openrouter.
- Comprehensive Built-in Tools: EvoAgentX ships with a rich set of built-in tools that empower agents to interact with real-world environments.
- Memory Module: Supports both ephemeral (short-term) and persistent (long-term) memory systems.
- Human-in-the-Loop (HITL) Interactions: Supports interactive workflows where humans review, correct, and guide agent behavior.
Use cases
EvoAgentX can be used to automatically evolve and optimize agentic workflows using self-evolving algorithms driven by your dataset and goals. It supports Human-in-the-Loop checkpoints for supervising agents. It provides short-term and long-term memory modules for agents to remember and improve across interactions. It can automatically assemble a multi-agent workflow from a natural language goal. It empowers agents to interact with the real world through a rich library of built-in tools.
Getting started
Install EvoAgentX using pip: bash pip install evoagentx Or install from source: bash pip install git+https://github.com/EvoAgentX/EvoAgentX.git For local development: bash git clone https://github.com/EvoAgentX/EvoAgentX.git cd EvoAgentX conda create -n evoagentx python=3.11 conda activate evoagentx pip install -r requirements.txt
License and pricing
The license is not stated in the provided metadata or README. The project is categorized as open source.
Based on the project's public README and repository metadata.