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

By Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh and 14 more. International Conference on Learning Representations, 2024

820 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/1d07e5b6f978cf69c0186f3d5f434fa92d471e46

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. W. Tam
2. Jiajie Zhang
3. Jidong Zhai
4. Linxi (Jim) Fan
5. Zhengxiao Du

Citations in the corpus

• A-MEM: Agentic Memory for LLM Agents (2025, neutral): “They integrate LLMs with external tools and delicate workflows to improve reasoning and planning abilities.”
• Why Do Multi-Agent LLM Systems Fail? (2025, neutral): “Building on this characteristic, multi-agent systems are increasingly explored in various domains, such as software engineering (Qian et al., 2023; Wang et al., 2024d), drug discoveries (Gottweis et al., 2025; Swanson et al., 2024), scientific simulations (Park et al., 2023b), and general-purpose…”
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents (2024, neutral): “Systems like ChatGPT already offer LLMs with tool integration—such as web search and code interpreter—to millions of users, and specialised LLM agents have been developed in domains like chemistry (Bran et al., 2023; Boiko et al., 2023) and software engineering (Wang et al., 2024).”
• GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models (2025, positive): “For evaluation, we use OpenHands [42] v0.”
• SweRank: Software Issue Localization with Code Ranking (2025, unknown): “More details in Appendix A. Evaluation Datasets: We utilize SWE-Bench-Lite (Jimenez et al., 2023) and LocBench (Chen et al., 2025) Baselines: Our primary comparison is against prior agent-based localization methods.”
• Neurosymbolic Repo-level Code Localization (2026, unknown): “Meanwhile, LLM-based retrieval techniques have been proposed to improve code localization performance by leveraging semantic understanding [3, 10, 17, 22, 26, 27, 29, 30, 32, 36].”
• LocAgent: Graph-Guided LLM Agents for Code Localization (2025, unknown): “Specifically, Open-Hands (Wang et al., 2025) implements a gener-alist coding agent that supports bash commands like grep and tools for viewing files.”
• GraphLocator: Graph-Guided Causal Reasoning for Issue Localization (2025, unknown): “Despite its importance, automating this task is fundamentally difficult; even state-of-the-art large language models (LLMs) and frameworks [39, 45, 47] fail to localize the file to be changed over half of the issues in recent benchmarks [50].”
• Agentic Software Issue Resolution with Large Language Models: A Survey (2025, unknown): “…into scaffolds is either achieved by prompting the LLM directly through prompt engineering [45, 66, 91, 123, 133, 139, 163, 164] or by constructing an agent capable of accessing the repository to collect context before generating the test [4, 13, 26, 31, 51, 101, 115, 140, 143, 144, 157, 173, 174].”
• Improving Code Localization with Repository Memory (2025, unknown): “Orthogonally, our approach leverages commit histories to construct a repository-specific memory grounded in the codebase’s evolution.”