aiagent.club
中文
GitHub

EvoAgentX

Observation pool · not formally ranked

This project does not currently meet the main index requirement of two current dimensions across two source types.

Not ranked
Observed adoptionMissing
MomentumStale · 2026-08-23
AttentionStale · 2026-08-23
Signal confidence Based on how many independent score dimensions currently have data.
Limited0/3 · 0 source types

Methodology v2.0 · snapshot 2026-09-14 · stale after 2 days

About

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. At its core, EvoAgentX enables developers and researchers to move beyond static prompt chaining or manual workflow orchestration. It introduces a self-evolving agent ecosystem, where AI agents can be constructed, assessed, and optimized through iterative feedback loops—much like how software is continuously tested and improved.

From a single prompt, EvoAgentX builds structured, multi-agent workflows tailored to the task.

It integrates automatic evaluators to score agent behavior using task-specific criteria.

Agents don’t just…

Across sources

3.2k Stars
  • Stars 3.2k
  • Forks 294
  • Commits 1.2k
  • Releases 5