The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910157217202176 |
|---|---|
| author | Wang, Xingyao Rosenberg, Simon Michelini, Juan Smith, Calvin Tran, Hoang Nyst, Engel Malhotra, Rohit Zhou, Xuhui Chen, Valerie Brennan, Robert Neubig, Graham |
| author_facet | Wang, Xingyao Rosenberg, Simon Michelini, Juan Smith, Calvin Tran, Hoang Nyst, Engel Malhotra, Rohit Zhou, Xuhui Chen, Valerie Brennan, Robert Neubig, Graham |
| contents | Agents are now used widely in the process of software development, but building production-ready software engineering agents is a complex task. Deploying software agents effectively requires flexibility in implementation and experimentation, reliable and secure execution, and interfaces for users to interact with agents. In this paper, we present the OpenHands Software Agent SDK, a toolkit for implementing software development agents that satisfy these desiderata. This toolkit is a complete architectural redesign of the agent components of the popular OpenHands framework for software development agents.
To achieve flexibility, we design a simple interface for implementing agents that requires only a few lines of code in the default case, but is easily extensible to more complex full-featured agents with features such as custom tools, memory management, and more. For security and reliability, it delivers seamless local-to-remote execution portability, integrated REST/WebSocket services. For interaction with human users, it can connect directly to a variety of interfaces, such as visual workspaces (VSCode, VNC, browser), command-line interfaces, and APIs. Compared with existing SDKs from OpenAI, Claude and Google, OpenHands uniquely integrates native sandboxed execution, lifecycle control, model-agnostic multi-LLM routing, and built-in security analysis. We validate the architecture empirically: production deployment data shows that V1 substantially reduces system-attributable failures over V0 with negligible event-sourcing overhead, and evaluations across multiple models and benchmarks demonstrate strong agent performance. Put together, these elements allow the OpenHands Software Agent SDK to provide a practical foundation for prototyping, unlocking new classes of custom applications, and reliably deploying agents at scale. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03690 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents Wang, Xingyao Rosenberg, Simon Michelini, Juan Smith, Calvin Tran, Hoang Nyst, Engel Malhotra, Rohit Zhou, Xuhui Chen, Valerie Brennan, Robert Neubig, Graham Software Engineering Artificial Intelligence Agents are now used widely in the process of software development, but building production-ready software engineering agents is a complex task. Deploying software agents effectively requires flexibility in implementation and experimentation, reliable and secure execution, and interfaces for users to interact with agents. In this paper, we present the OpenHands Software Agent SDK, a toolkit for implementing software development agents that satisfy these desiderata. This toolkit is a complete architectural redesign of the agent components of the popular OpenHands framework for software development agents. To achieve flexibility, we design a simple interface for implementing agents that requires only a few lines of code in the default case, but is easily extensible to more complex full-featured agents with features such as custom tools, memory management, and more. For security and reliability, it delivers seamless local-to-remote execution portability, integrated REST/WebSocket services. For interaction with human users, it can connect directly to a variety of interfaces, such as visual workspaces (VSCode, VNC, browser), command-line interfaces, and APIs. Compared with existing SDKs from OpenAI, Claude and Google, OpenHands uniquely integrates native sandboxed execution, lifecycle control, model-agnostic multi-LLM routing, and built-in security analysis. We validate the architecture empirically: production deployment data shows that V1 substantially reduces system-attributable failures over V0 with negligible event-sourcing overhead, and evaluations across multiple models and benchmarks demonstrate strong agent performance. Put together, these elements allow the OpenHands Software Agent SDK to provide a practical foundation for prototyping, unlocking new classes of custom applications, and reliably deploying agents at scale. |
| title | The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2511.03690 |