ICLR 2025Software engineering agents U California, Berkeley Alibaba Group

OpenHands: An Open Platform for AI Software Developers as Generalist Agents

OpenHands is an open MIT-licensed platform for building AI software developers that evaluate agents on SWE-BENCH and WebArena benchmarks.

Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Tran, Hoang H., Fuqiang Li, Ren Ma, Mingqian Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, Lin, Junyang, Brennan, Robert, Hao Peng, Heng Ji, Graham Neubig

Published Jul 23, 202415 citations▲ 90 on Hugging Face Code ★ 90,160 arXiv ↗

71%

OverallHighly rated

OverallHighly ratedVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.

Readers

–

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel7/20reviewers recommend it

lenient 5/5

medium 2/10

strict 0/5

AI panel?Vote to see what the 20 AI reviewers said

Panel consensus

OpenHands earns praise as a sandboxed multi-agent platform with a strong evaluation rig and MIT release, but its thin 15-task benchmark coverage and lack of ablation leave the load-bearing layer ambiguous.

Abstract

Software is one of the most powerful tools that we humans have at our disposal; it allows a skilled programmer to interact with the world in complex and profound ways. At the same time, thanks to improvements in large language models (LLMs), there has also been a rapid development in AI agents that interact with and affect change in their surrounding environments. In this paper, we introduce OpenHands (f.k.a. OpenDevin), a platform for the development of powerful and flexible AI agents that interact with the world in similar ways to those of a human developer: by writing code, interacting with a command line, and browsing the web. We describe how the platform allows for the implementation of new agents, safe interaction with sandboxed environments for code execution, coordination between multiple agents, and incorporation of evaluation benchmarks. Based on our currently incorporated benchmarks, we perform an evaluation of agents over 15 challenging tasks, including software engineering (e.g., SWE-BENCH) and web browsing (e.g., WEBARENA), among others. Released under the permissive MIT license, OpenHands is a community project spanning academia and industry with more than 2.1K contributions from over 188 contributors.