OpenHands Blog

September 24, 2026

What's New in OpenHands Enterprise: More Visibility, Governance, and Control

The latest OpenHands Enterprise release is designed to help organizations scale their agentic SDLC with better usability, governance, and visibility.

September 23, 2026

What Is An AI Dark Factory? What Lights-Out Manufacturing Teaches Us About Software

What is an AI dark factory? Learn what lights-out manufacturing teaches us about autonomous software development, verification, observability, and AI agents.

September 2, 2026

OpenHands in August: A Clearer Way to Run, Review, and Automate Agentic Work

OpenHands Agent Canvas added better automations, clearer agent activity, model controls, review workflows, and Canvas Apps in August 2026.

August 26, 2026

Use Jira Cloud in your OpenHands Enterprise Organization

Connect Jira Cloud to OpenHands once at the organization level and let teams trigger AI development workflows directly from Jira issues, from planning and bug investigation to pull requests.

August 11, 2026

NVIDIA Nemotron 3.5 Lightning and OpenHands: A Faster Path to Always-On Software Engineering Agents

OpenHands supports NVIDIA Nemotron 3.5 Lightning, a customizable open model built for always-on agents, specialized workflows, and model-agnostic software engineering automation.

August 10, 2026

OpenHands Joins the Open Secure AI Alliance to Help Build AI Security in the Open

OpenHands joins the NVIDIA-led Open Secure AI Alliance to advance open, inspectable infrastructure for building and running secure AI agents.

August 7, 2026

Open Models Are Closing the Coding Gap

Kimi K3 and Thinking Machines' Inkling shipped open weights this week. What self-hosting a frontier-class coding model buys you on your own infrastructure, and what it costs.

July 28, 2026

Coding Agents and Technical Debt

Say you forked the OpenHands app twelve months ago and never merged from upstream. You would now be 2,600 merged PRs behind, including 866 bug fixes you do not have.

July 22, 2026

Agent Sandboxing: What OpenAI got wrong with the HuggingFace hack

OpenAI accidentally hacked HuggingFace during a security exercise. Learn what they got wrong, and how you can avoid the same mistakes.

July 22, 2026

Use Azure DevOps in your OpenHands Enterprise Organization

Connect Azure DevOps to OpenHands Enterprise once at the organization level and let developers trigger AI development workflows directly from Azure Boards work items and pull request comments.

July 22, 2026

Use Bitbucket Data Center in your OpenHands Enterprise Organization

Connect Bitbucket Data Center to OpenHands Enterprise once at the organization level and let developers trigger AI development workflows directly from pull request comments—from code review and bug investigation to pull requests.

July 7, 2026

It Told Me No: How Quint Helped Us Fix a Long-Standing Race Condition

A noisy "multiple valid pods" alert plagued our on-call rotation for years, caused by a race condition in the Runtime API that spun up duplicate Kubernetes pods. This post shows how we diagnosed it, why our first two fixes fell short, and how Quint — a formal specification tool — predicted the incomplete fix and gave u…

June 22, 2026

The Verification Stack

Agents made generating code cheap. The real bottleneck is now verification: checking that a change is correct, follows repo conventions, and is something your team can trust, review, and merge. This post introduces the full verification stack — a layered set of automated verifiers that catch different mistakes at diffe…

June 18, 2026

Controlling any Coding Agent with the OpenHands Agent Canvas and SDK

OpenHands now supports the Agent Client Protocol in Agent Canvas and the OpenHands Software Agent SDK, making it possible to use Claude Code, Codex, Gemini CLI, OpenHands, or other agents on arbitrary servers of the cloud.

June 16, 2026

Introducing Agent Canvas: From Coding Agents to Org-wide Automation

Introducing Agent Canvas: OpenHands' self-hostable workspace for AI coding agent automations. Connect Slack, GitHub, and Linear to run scheduled engineering workflows at scale.

May 27, 2026

Simple, In-conversation Model Choice in OpenHands

OpenHands is making model choice a first-class part of coding-agent workflows, with saved LLM profiles, in-chat model switching, SDK primitives for routing and fallback, and a partnership with MiniMax M2.7 for high-volume agent work.

May 26, 2026

OpenHands for Customer Success: You Don't Have to Be a Developer to Use Coding Agents

A customer success manager explains how OpenHands connected Slack, HubSpot, Notion, Granola, and HappyFox into a customer intelligence system without writing code.

May 20, 2026

OpenHands Product Update - May 2026

We're excited to share a round up of the latest features in OpenHands! The latest release of the OpenHands Local GUI brings significant improvements to LLM profile management, enhanced security, and a variety of quality-of-life improvements across the platform.

May 11, 2026

The OpenHands Index: 3 Months Out

Three months after launch, the OpenHands Index adds new model results from frontier labs, startups, and new entrants, with updated views of accuracy, cost, and runtime across software engineering tasks.

May 6, 2026

From Agents to Systems: Introducing OpenHands Enterprise, the Agent Control Plane

OpenHands Enterprise gives teams a system for running AI agents across the organization, with the infrastructure required to control, observe, and scale that work. Today we are also making OpenHands Automations generally available.

April 27, 2026

Effective Strategies for Asynchronous Software Engineering Agents

CAID shows how multi-agent coding systems improve long-horizon software tasks by using the same primitives human teams already rely on: git worktrees, branches, merges, and test-based verification.

April 3, 2026

The Software Agent Control Plane

OpenHands views the software-agent stack as harness, orchestrator, and control plane. Here's why the control plane is becoming essential for running software agents securely at scale.

March 23, 2026

EvoClaw: Evaluating AI Agents on Continuous Software Evolution

EvoClaw evaluates coding agents on milestone-level, long-horizon software evolution. The early results show a clear pattern: agents keep adding new functionality, but regressions and technical debt compound faster than they can repair them.

March 18, 2026

How to Evaluate Agent Skills (And Why You Should)

Skills can make coding agents dramatically better, slightly more reliable, or actively worse. This post shows how to evaluate agent skills with deterministic tasks, verifiers, and no-skill baselines so you can measure what actually helps.

March 6, 2026

OpenHands Product Update - March 2026

We’re excited to announce new features in our latest OpenHands Cloud release that help you plan and scope your work, and discover Agent Skills more efficiently! Planning Mode BETA The new Planning Agent lets you seamlessly switch between Plan Mode and Code Mode. In Plan Mode, you can provide high-level direction and th…

March 5, 2026

Learning to Verify AI-Generated Code

LLMs made generating code cheap. The real bottleneck is verification: checking that a change is correct, follows repo conventions, and is something your team can trust, review, and merge. This post introduces the first layer of our verification stack.

March 3, 2026

The OpenHands Vulnerability Fixer: Automated Security Remediation with AI Agents

An open-source application that demonstrates how to build AI-powered tools using the OpenHands Cloud API. Scan repositories for vulnerabilities and automatically generate pull requests with fixes.

February 27, 2026

How to Create Effective Agent Skills

Skills are specialised knowledge packages that extend coding agents with domain-specific expertise. Learn how to create, deploy, monitor, and improve skills to automate your repetitive workflows.

February 20, 2026

Analyzing and Improving the OpenHands Index

How collaboration with CMU researchers helped us discover and fix a benchmark vulnerability, leading to more reliable model evaluations.

February 19, 2026

Velocity Is Dead: AI-Generated Compilers and the Future of Software

What really matters in a world where velocity of code creation is no longer the bottleneck in software engineering?

February 16, 2026

SWE-fficiency: Evaluating How to Fix Code, Not Just What to Fix

Introducing SWE-fficiency, a new benchmark that evaluates AI agents on performance engineering—measuring not just if code works, but if agents can make it fast and efficient like senior engineers.

February 12, 2026

MiniMax M2.5: Open Weights Models Catch Up to Claude Sonnet

With the new release of MiniMax M2.5, there is now an open model that is basically up to the quality of Claude Sonnet. We got early access to test it.

January 29, 2026

Introducing the OpenHands Index

The OpenHands Index is a comprehensive benchmark that tests agentic software engineering models across a broad variety of tasks.

January 21, 2026

What is a Coding Agent? Comparing Agents to AI Code Assistants

Traditional code completion tools focus on small-scale productivity, accelerating syntax recall and micro-refactors within a single file. However, as LLMs improve and systems scale, the primary developer bottleneck shifts from writing lines of code to coordinating complex tasks across multiple files and testing environ…

December 18, 2025

Refactoring COBOL to Java with AI Agents

Learn how to use AI agents to modernize legacy COBOL codebases to Java. We walk through an iterative refinement approach that uses multiple agents to convert and verify code quality until it meets your standards.

December 18, 2025

OpenHands Partners with Toad: A Universal Terminal Interface for AI Agents

OpenHands is sponsoring the development of Toad, a universal terminal interface for AI agents. Toad provides a polished, consistent experience for agentic coding tools, and OpenHands is one of its recommended agents.

December 17, 2025

Eight billion tokens in two weeks: How C3 AI brings agentic coding to every team with OpenHands

C3 AI adopted OpenHands Cloud as enterprise-grade, self-hosted agentic coding infrastructure, letting sales, solution engineers, and builders collaborate through a chat interface while workflows run directly against C3 AI’s Ontology Objects for production-aligned code. In early rollout, they processed ~8B tokens in two…

December 9, 2025

Use AI Agents in Your Favorite Editor through the Agent Client Protocol

Learn how to bring OpenHands' powerful AI coding capabilities directly into your editor using the Agent Client Protocol. Whether you use Zed, JetBrains, neovim, Obsidian, or more you can now access OpenHands without leaving your editor.

December 2, 2025

Agents in the Outer Loop

Most developers using AI are accelerating the inner loop of development. But there's an emerging paradigm of cloud-based agents that shine in the outer loop. Learn how the most effective development teams are using both.

November 19, 2025

Host Your Own Coding Agents with OpenHands using AMD Ryzen AI

Coding agents can automate many software development tasks, but running them typically requires expensive cloud APIs. With AMD's Ryzen AI Max+ 395 and Lemonade Server, you can run coding agents like OpenHands directly on your workstation while maintaining privacy and controlling costs.

New Blog

Stop Choosing Coding Models by Hand

November 18, 2025

We’ve Just Raised $18.8M to Build the Open Standard for Autonomous Software Development

OpenHands raised $18.8M in a Series A led by Madrona to build the open, secure, and model-agnostic platform for cloud coding agents. Plus, we're collaborating with AMD to make local agents even better. This funding helps us stick to our mission: powerful coding agents for every developer, for free, forever.

November 17, 2025

Debugging Production Issues with AI Agents: Automating Datadog Error Analysis

This blog and video demonstrates how to transform production errors into actionable insights automatically. Learn how the OpenHands SDK enables AI agents to debug Datadog errors, analyze code across multiple repositories, and post detailed findings—all through a simple GitHub Actions workflow.

November 5, 2025

Introducing the OpenHands Software Agent SDK

Open-source, simple to use, powerful, and highly customizable. The OpenHands software agent SDK makes it possible to build plug-and-play coding agents for any workflow.

November 4, 2025

Bring your own LLM is now available to all OpenHands Cloud users

We’re excited to announce the expansion of our Bring your own Key (BYOK) support, making this available to all new and existing users of OpenHands Cloud

October 22, 2025

Remediating CVEs at Scale with Agents

While developers adapt to terminal-based agents, forward-thinking organizations are automating CVE remediation at scale. Learn how OpenHands enables teams to tackle millions of vulnerabilities with AI-powered agents, custom dashboards, and cloud-based automation.

October 13, 2025

Host Your Own Coding Agents with OpenHands using NVIDIA DGX Spark

In this post, we explore how to set up and run coding agents using NVIDIA's DGX Spark platform combined with OpenHands, allowing for a self-hosted but versatile experience using AI for software development.

October 9, 2025

Automating Massive Refactors with Parallel Agents

Discover how AI-powered coding agents can tackle large-scale refactoring projects in days instead of months, using parallel workflows and the refactor-sdk toolkit.

October 2, 2025

A Practical Guide to Choosing the Right Language Model for Coding Agents

Coding agents are powered by large language models, but which one should you choose? We share our experiences with Claude Sonnet 4, GPT-5, and Qwen3 Coder to help you make the right decision for your specific use case.

September 18, 2025

All New OpenHands Cloud: More Model Choice, Lower Prices, Slicker Design

We're introducing a new subscription model with bring-your-own-key support, expanded model choices at API pricing, and a completely redesigned GUI experience that makes OpenHands more accessible and cost-effective than ever.

September 9, 2025

Case Study: How US Mobile Supercharges Software Engineering with OpenHands

Learn how US Mobile leveraged OpenHands to reduce development time by 80% and transform an 8-point user story into a 2-point task, enabling their engineers to focus on higher-value work while delivering features faster.

September 4, 2025

The Path to OpenHands v1

A look at how we’re stabilizing the OpenHands platform for a v1: a lightweight SDK, a streamlined CLI, and a server architecture built on a synchronous conversation model.

August 21, 2025

OpenHands Cloud OSS Credit Program: Supporting Open Source Maintainers

Get $100 to $500 in OpenHands Cloud credits to offload routine maintenance tasks to AI. We're giving back to active maintainers of established open-source projects who spend real time on upkeep.

August 14, 2025

Mitigating Prompt Injection Attacks in Software Agents

There's a major security dilemma when it comes to working with AI agents. If you give an agent access to untrusted data sources and the ability to take destructive actions, you become vulnerable to prompt injection attacks. Here's how we're addressing this challenge at OpenHands.

July 15, 2025

Access State-of-the-Art LLM models at cost via OpenHands GUI and CLI

Announcing a new OpenHands LLM provider that enables access to state-of-the-art (SOTA) agentic coding models like Claude Sonnet 4, Devstral Small, Devstral Medium, Gemini 2.5 Pro, and o4-mini at cost – without any additional pricing markup.

June 24, 2025

OpenHands Meets Slack: AI-Powered Development in Your Workspace

Bring the power of OpenHands AI development agents directly into your Slack workspace. Start conversations, get code assistance, and collaborate with AI seamlessly within your team's communication hub.

June 18, 2025

OpenHands Cloud Self-hosted: Secure, Convenient Deployment of AI Software Development Agents

OpenHands Cloud is now available as a self-hosted solution, providing secure, convenient deployment of AI software development agents. It features a 30-day free trial and is available as a source-available Helm Chart.

June 17, 2025

The OpenHands CLI: AI-Powered Development in Your Terminal

Experience the full power of OpenHands development agents directly from your command line. No Docker required, just install and start coding with AI assistance in seconds.

June 11, 2025

Walking the Line with Commercial Open Source

Navigating the challenges and opportunities of building commercial open source software, and how we're approaching it with OpenHands.

June 4, 2025

Building a Provably Versatile Agent

OpenHands Versa is a versatile agent that excels across multiple benchmarks, from software engineering to web browsing and frontend development.

May 20, 2025

Devstral: A new state-of-the-art open model for coding agents

Devstral is an agentic LLM for software engineering tasks that outperforms all open-source models on SWE-Bench Verified by a large margin.

May 7, 2025

Programmatically Access Coding Agents with the OpenHands Cloud API

The new OpenHands Cloud API allows you to start coding tasks with a single funciton call.

May 1, 2025

Vibe Coding Higher Quality Code

Vibe coding relies on AI agents to generate code, but how do we ensure the code is of high quality?

April 17, 2025

SOTA on SWE-Bench Verified with Inference-Time Scaling and Critic Model

OpenHands now tops the SWE-Bench Verified leaderboard! By training a critic model to select the best solutions from multiple agent attempts, we've significantly improved performance on real-world programming tasks.

April 9, 2025

OpenHands Context Condensensation for More Efficient AI Agents

Say 'goodbye' to long conversation frustrations. Our context condenser intelligently summarizes conversation history to maintain performance, cuts API costs by 50%, and keeps your agents responsive through even the longest problem-solving sessions.

March 31, 2025

Introducing the OpenHands Cloud

Experience the power of OpenHands AI in the cloud! With seamless GitHub integration, multi-modal communication, and parallel agent capabilities, OpenHands Cloud brings state-of-the-art AI software development to your browser.

March 31, 2025

Introducing OpenHands LM 32B -- A Strong, Open Coding Agent Model

We're excited to announce the release of OpenHands LM 32B, a new open-source model fine-tuned from Qwen Coder 2.5 Instruct 32B, specifically optimized for software development with OpenHands.

March 17, 2025

One Year of OpenHands: A Journey of Open Source AI Development

Celebrating one year of OpenHands, reflecting on our growth, milestones, and looking ahead to the future of AI-powered software development.

January 16, 2025

8 Use Cases for Generalist Software Development Agents

Exploring practical applications of generalist software development agents in real-world scenarios, with example prompts and use cases.

November 4, 2024

Announcing All Hands Online (Beta)

Today we're excited to announce our official hosted version of the OpenHands AI software developer! Learn about our new features including GitHub integration and improved multi-session support.

November 1, 2024

OpenHands CodeAct 2.1: An Open, State-of-the-Art Software Development Agent

We introduce CodeAct 2.1, achieving state-of-the-art 53% resolve rate on SWE-Bench Verified.

October 17, 2024

OpenHands: From README to open source movement

OpenHands exists because our community willed it. Here’s how it all started.

October 10, 2024

Open-source Coding Agents in your GitHub, Fixing your Issues

We introduce the OpenHands resolver, an open-source coding agent that can automatically fix issues in your GitHub repositories.

October 4, 2024

Evaluation of LLMs as Coding Agents on SWE-Bench (at 30x Speed!)

We evaluated LLMs as coding agents on SWE-Bench Lite, using an evaluation framework we built for efficient evaluation of coding agents.

September 26, 2024

Don't Sleep on Single-agent Systems

This post discusses some of the benefits of single-agent systems, and contrasts them with multi-agent systems.

September 10, 2024

Building a Frontend App with Open Source AI Agents

Luckily, with the help of recent AI tools, that barrier has significantly lowered, and it's now possible to build practical frontend apps, almost entirely automatically. In this post I'll demonstrate how I built a frontend for a GitHub Pull Request viewer using OpenHands, the open-source AI agent for software developme…

September 5, 2024

Press Release: All Hands Announces $5M to Scale AI Agent for Software Development

All Hands AI, a company making open source AI to help developers build software, today announced that it’s raised $5 million in seed funding. Menlo led the round, with additional investors including Pillar VC, Betaworks, and Rebellion.

August 20, 2024

Using OpenHands to Improve your Test Coverage

Here is a practical example of how OpenHands (Formerly OpenDevin) can improve your unit test coverage right now.

July 15, 2024

Introducing All Hands AI

Introducing All Hands AI -- we build AI software development agents for everyone, in the open.