EvoAgentX

Open-source framework that builds, evaluates and self-improves multi-agent LLM workflows from a goal.

Harness by ANative-Lab

IndexedOther★ 3,402

Write a review

Get started

Setup steps are in the repository. Website · Repository

About

EvoAgentX is a framework for building, evaluating and evolving LLM-based agents and agent workflows. From a single prompt it assembles multi-agent workflows, scores agent behavior with built-in evaluators, and improves workflows with a self-evolution engine. It has short-term and long-term memory modules and human-in-the-loop checkpoints. Models are reached through its OpenAI and Qwen modules, or through LiteLLM, SiliconFlow and OpenRouter for providers such as Claude and DeepSeek.

Use cases: agent-orchestration, llm-evaluation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Languages: Python
Multi-agent: YesREADME
Orchestration: otherREADME
Memory: short-term, long-termREADME
Human in the loop: YesREADME
Model providers: openai, qwen, anthropic, deepseek, kimiREADME
Maturity: Betagithub.com

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Alternatives

Frameworks for the same language with a similar way of orchestrating agents.

Signals

Stars: 3,402
Forks: 318
Open issues: 16
Last commit: Oct 22, 2026 (6 days ago)
Last release: Jun 28, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Other
Repository: github.com/ANative-Lab/EvoAgentX
Website: anative-lab.github.io/EvoAgentX/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql

Cite this page

EvoAgentX. Agent Mart. https://agentmart.dev/harnesses/evoagentx (last updated 2026-10-24)