OpenHands

For coding agents, "skills" are a great way to automate repetitive workflows, but how can we tell if they're working at scale? We did a deep dive on how you can log, monitor, and improve agent skills, with a real example of building a customized PR review skill.

Agent Canvas 1.21 from @OpenHandsDev is out, new updates for Agent Canvas is new release has lots of goodies including: /goal improvements, faster navigation, first-class plugins, reusable agent profiles, and branching from any message. Here are the six changes to highlight:

AI agents are a new attack surface. Join @OpenHandsDev and @GraySwanAI for a sharp discussion on prompt injection, agent-specific threats, and what it takes to build agents that hold up under real attack. Reserve your spot 👉 hubs.la/Q04p6ST20

OpenHands would like to congratulate @AIatMeta Superintelligence Labs on the public preview launch of their new model, Muse Spark. Were fortunate to get early-access and we’re loving what we’re seeing so far! As part of our commitment to offering a global array of LLMs for #agenticSDLC workflows, Muse Spark will be fully supported on OpenHands. Learn more here. 👇 hubs.la/Q04p29_B0

AI now allows systems to be hacked, and defended in new and surprising ways. Matt Fredrickson from @GraySwanAI and I are going to discuss "How AI is Transforming Cybersecurity" at a live webinar July 16th, more details on the content in the images.

Race condition, duplicate pods, months of alert fatigue. We paired OpenHands (fast fix drafts) with @quint_lang (formal proof they actually work) until one fix held. Read how: hubs.la/Q04nRMVT0

OpenHands Enterprise now works with Azure DevOps. So now if you comment on a work item or a PR, and OpenHands picks it up, does the work, and opens a pull request in Azure Repos. I know a lot of teams live in Azure DevOps and get skipped by tools that only speak GitHub. This is for you. @OpenHandsDev Docs for @AzureDevOps docs.openhands.dev/enterprise/int…

The team is at @aiDotEngineer World's Fair this week in SF! If you’re attending and want to talk about: 🔁 Automating repetitive engineering toil: CVE remediation, refactors, or dependency upgrades 🔒 Running autonomous agents safely in sandboxes across your codebase 🏠 Self-hosted, VPC, or on-prem deployments for full data control 📈 Scaling from local experiments to thousands of parallel agent jobs 👋 Send us a note or stop by the booth. We'd love to connect. #AIEWF #AIEngineer #AIWorldsFair #AgenticEngineering

We've found this sort of "sidekick" architecture to be very effective at cutting LLM spend because it allows you to do context control and not spend expensive tokens on simple tasks. Here's a 200-line example of how to do it in the OpenHands SDK :) gist.github.com/neubig/412ab8d…

The longer the task, the more orchestration carries it. The OpenHands SDK just added three primitives for building robust, long-horizon agent workflows, usable by the model and by you: Thanks to: @gneubig @juanontech Vasco Alona @OpenHandsDev

@v8bnSSPbrd11738 Thanks for the report! If you could open an issue on github and share reproduction instructions we could take a look. It should not permanently freeze.

@OpenHandsDev Bug: Agent freezes when it hits the max limit When a task takes a long time, the agent hits its maximum limit mid-task and gets completely stuck — no message, no response, nothing. Expected behavior: It should automatically continue the task in a new window/chat instead of freezi

Hot off the press 📰🔥📰🔥 "As organizations increasingly adopt agents for developer productivity, code automation, and other engineering tasks, many teams are hitting a scale issue as agents sprawl across repositories, teams, and business units. OpenHands’ offering responds to that challenge by treating agents not as independent, one-off tools but as components of a coordinated system, managed from a single operational plane." aijourn.com/openhands-laun…

OpenHands listed as a top #opensource project for #AI-driven development 🙌

We open-sourced a method to cut slop from agent-generated code. It seriously works, and we have receipts -- PRs on production code merge 2.4 times faster while still maintaining quality. See Xingyao's post below for details on *The Verification Stack*

Coding agents open PRs in minutes. But on consequential codebases, those PRs still wait days for human review. So we built a verification stack, and on our own repo, it cut time-to-merge by 58% without lowering code quality. Here’s how. 🧵

@rikkarth @diogo_aoliveira We are 👋 Tell us what you think if you have a chance to try it!

@diogo_aoliveira @OpenHandsDev Droid isn’t opensource neither free. 🙃

I really like Hermes Agent, but nothing beats OpenCode’s power for in-session orchestration. I’ve configured my agents & sub-agents so everything runs super deterministic. Hermes is my general/research/automation agent, OpenCode is where I build.

Another day, another benchmark that @OpenHandsDev tops 😄

OpenHands is quietly becoming the default open source AI coding agent everyone’s actually using.,, 76k+ stars in a few months!! Its a full autonomous agent that can plan, code, debug, and push changes by itself. What’s making it stick :: --> Works in terminal or GUI so you can literally watch it work --> Supports Claude, GPT, and local models without lock-in --> Handles real tasks end-to-end instead of just spitting out code snippets --> Actively maintained with frequent updates and a growing builder community Most agent tools still feel like demos,, But openhands feels like something you can actually run on real projects without babysitting it every five minutes. If you’re building or testing AI agents for development work right now, this is currently one of the strongest open options available.

If you’re building AI agents, study these projects: • @polygres — Postgres for the agent era • @LangChain / LangGraph — stateful agents • @llama_index — agents over your data • @crewAIInc — multi-agent workflows • @dify_ai — agentic app builder • @FlowiseAI — visual agent flows • @OpenHandsDev — coding agents • @browser_use — browser agents agents need memory, tools, retrieval, workflows, and data that actually makes sense.

People have been asking why OpenHands V1 goes the opposite direction from Claude Managed Agents. I finally found the time to write it up. The production pain points are real, but changing the hosted agent architecture won't solve them for free: xwang.dev/blog/2026/open…

If this sounds interesting to you, check out these links for more information! openhands.dev/blog/use-any-c… It's all open source, so we welcome any contributions to make it better as well.

The OpenHands SDK also allows for the use of arbitrary agents, if you want to deploy them in more structured workflows. It's super-easy to use!

What if you could run any coding agent through a single interface, locally, remotely, or on the cloud? Today we introduced Agent Client Protocol support to the OpenHands Agent Canvas, SDK, and Cloud, making this possible.