Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H. Tran, Fuqiang Li, Ren Ma, Mingzhang Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, Junyang Lin, Robert Brennan, Hao Peng, Heng Ji, Graham Neubig• 2024

Related benchmarks

TaskDatasetResultRank
Terminal task completionTerminal-bench 2.0
Pass@131.43
43
Automated Software EngineeringSWE-bench Verified
Resolved Rate79.8
39
Software EngineeringSWE-bench Verified
Pass@172.8
18
File-level Code LocalizationSWE-Bench Lite
Acc@177.37
16
File-level LocalizationSWE-Bench-Lite latest (test)
NDCG@176.28
16
Function-level Code LocalizationSWE-Bench Lite
Acc@568.25
16
Function-level LocalizationSWE-Bench-Lite latest (test)
NDCG@563.13
16
Module-level Code LocalizationSWE-Bench Lite
Acc@583.21
16
Module-level LocalizationSWE-Bench-Lite latest (test)
NDCG@575.79
16
Software Engineering Issue ResolutionSWE-Bench Lite
Resolution Rate27.7
16
Showing 10 of 18 rows

Other info

Follow for update