AgentGym
Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.
Create custom environments for training AI agents using the AgentGym framework and learn from interactive experiences.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeCode and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.
AgentGym has 838 stars on GitHub. It has been forked 116 times. AgentGym is written mainly in Python. It has been in active development since 2024. AgentGym is available under the MIT license. Its main topics are agent, large-language-models, llm, llm-based-agent.
What is AgentGym?
Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.
Is AgentGym open source?
AgentGym is an open-source project. It is released under the MIT license.
Is AgentGym free?
Yes. AgentGym is free and open source — you can use, modify and self-host it.
What license does AgentGym use?
AgentGym is available under the MIT license.
What language is AgentGym written in?
AgentGym is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/woooodyy-agentgym.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.