// agents · ANative-Lab/EvoAgentX

EvoAgentX

EvoAgentX est un projet de agents IA open source, créé par ANative-Lab (ANative-Lab/EvoAgentX sur GitHub). Il compte 3 366 étoiles sur GitHub et 312 forks, il est publié sous la licence MIT et a été mis à jour pour la dernière fois sur GitHub le 27 août 2026.

EvoAgentX — a framework for building self-evolving ecosystems of AI agents.

★ 3,4 k étoiles⑂ 312 forksMITmis à jour août 2026

Voir sur GitHub ↗Official site ↗

▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.

// détails du projet

Détails du projet

Dépôt: ANative-Lab/EvoAgentX
Étoiles GitHub: 3 366
Forks: 312
Licence: MIT
Dernière mise à jour sur GitHub: 27 août 2026
Catégorie: Agents IA
Type de fiche: Guide d'installation complet
Site officiel: Official site

// fonctionnement

Comment ça marche

Clarify your goal
Decide the first concrete outcome you want from it, so you can pick the right example, template or mode instead of exploring everything at once.
Get the project
Clone the repository (or install the published package) and skim its README quick start for the requirements for your platform.
Install and configure
Run the documented install step and set any required configuration — such as provider keys, data sources or local services — before the first run.
Run your first task
Execute the smallest documented example end to end, confirm the output is what you expected, then adapt it to your real data or workflow.

// fonctionnalités

Pourquoi on l'adore

Automatic workflow generation

Describe a goal and EvoAgentX generates a multi-agent workflow to execute it.

Self-evolution algorithms

Built-in evolution algorithms iteratively improve agents and workflows, with published results in the README.

Tool-enabled workflows

Agents can be given toolkits such as a command-line file-operations toolkit during generation.

Human-in-the-loop

Interceptor agents can approve or reject sensitive actions (for example an email send) mid-workflow.

Built-in tools summary

A catalogue of ready tools ships with the framework for common agent tasks.

Ready applications

Worked examples include a financial information workflow and an arXiv research summariser.

// lancez-le

Lancez-le vous-même

Clone the repository
Get the source so you can inspect, configure and run it locally.
```
git clone https://github.com/ANative-Lab/EvoAgentX.git
cd EvoAgentX
```
Install EvoAgentX
Install from PyPI (or in development mode from source).
```
pip install evoagentx
```
Configure your LLM
Set your provider key and define an LLM configuration in code, as the README shows.
```
export OPENAI_API_KEY=your-key  # see README LLM Configuration
```

// cas d'usage

Ce que vous pouvez créer

Auto-generate a research workflow that summarises new arXiv papers
Build a financial-analysis agent team that improves over runs
Add human approval to any workflow step that sends or publishes
Study self-evolving agent design from a framework paper implementation

// faq

Questions fréquentes

Who maintains EvoAgentX?

It is maintained by ANative-Lab on GitHub (ANative-Lab/EvoAgentX), where the source, issues and releases live.

Is it free to use?

Yes — it is free and open source under the MIT licence, which permits use, modification and redistribution, including commercially, with attribution.

Does it need a paid API key?

Yes — EvoAgentX drives external LLMs, so you supply a provider key such as OPENAI_API_KEY; model usage is billed by that provider.

How does it compare to static multi-agent frameworks such as CrewAI or AutoGen?

Compared with static multi-agent frameworks such as CrewAI or AutoGen, EvoAgentX's distinguishing focus is: evoAgentX — a framework for building self-evolving ecosystems of AI agents. Pick it when that focus matches your need; the alternative may suit you better if its broader or different scope is the priority.

How do I get started?

Les autres projets de la catégorie Agents IA avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si EvoAgentX ne vous convient pas.

openclaw★ 391,6 k
A personal AI that really does things — on any OS, with your data staying yours.
superpowers★ 294,9 k
An agentic skills framework & software development methodology that works.
ECC★ 275,2 k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
hermes-agent★ 252,0 k
The agent that grows with you — a Python framework for adaptive AI agents.
deepseek-harness★ 245,5 k
DeepSeek's plugin-based agent harness where everything is a plugin.

// plus en agents

Plus en Agents IA

Projets de la catégorie Agents IA proches dans le catalogue, les plus proches en étoiles de EvoAgentX — continuez à explorer de part et d'autre.

beeai-framework★ 3,4 k
Build production-ready AI agents in both Python and Typescript.
google_workspace_mcp★ 3,3 k
Control Gmail, Calendar, Docs, Sheets, Drive and more from AI — a full Google Workspace MCP server.
obsidian-wiki★ 3,5 k
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
mobile-use★ 3,2 k
AI agents that use real Android and iOS apps like a human — from minitap.
ReMe★ 3,6 k
A memory management kit for agents — remember me, refine me.
AP2★ 3,2 k
An open protocol for secure AI-driven payments.

Obtenir EvoAgentX

Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.

Voir sur GitHub ↗← Plus d'outils agents IA