Graham Neubig

One less-known feature of OpenHands is that it allows you to spin up a frontend, and then have the agent test out the frontend to make sure that it works! You can see a video demo here: youtu.be/jMyTCXpEz10

Come work with us! More and more people are deploying OpenHands to their dev teams, and we'd love to have another great person join the team and help them be successful.

6000 PRs! I knew a lot of people were using OpenHands but this honestly exceeded my expectations a bit. And we're just getting stated, hoping to have some changes soon that'll make it even easier to develop with OpenHands and increase the count even more 👀

These scores are... really good.

This was a fun webinar with tons of great questions from the audience! Hope it's helpful to people who want to know how to use coding agents effectively.

Stop by the poster sessions today at ICML Workshop on Computer Use Agents to chat about OpenHands-Versa!

I've been using agents to run ML experiments for a while now, and it's all fun and games until the agent decides it doesn't like your evaluation method and decides to change it to get higher scores 😅

In a few minutes, we're starting a webinar on "How we build OpenHands with OpenHands!" featuring tips and tricks from @gneubig, see you there! lu.ma/9sffwppt?tk=ZK…

What are the differences between developer productivity and satisfaction when using: - coding assistance through autocomplete - autonomous coding agents @valeriechen_ did the first controlled academic study answering this question, check out the results!

1/ AI agents are increasingly being deployed for real-world tasks, but how safe are they in high-stakes settings? 🚨 NEW: OpenAgentSafety - A comprehensive framework for evaluating AI agent safety in realistic scenarios across eight critical risk categories. 🧵

1/6 Retrieval is supposed to improve generation in RAG systems. But in practice, adding more documents can hurt performance, even when relevant ones are retrieved. We introduce RAGGED, a framework to measure and diagnose when retrieval helps and when it hurts.

Some updates 🚨 I finished my Ph.D at @uwcse in June 2025! After a year at AI2 as a Research Scientist, I am joining CMU @LTIatCMU & @mldcmu (courtesy) as an Assistant Professor in Fall 2026. The journey, acknowledgments & recruiting in 🧵

Heading to Vancouver for ICML✈️🇨🇦Let’s chat about coding agents, evals, and human-AI collab. I’ll also be on the job market this upcoming cycle, looking for TT faculty roles + post-docs. Here's where you'll be able to find me this week👇

Little known fact is that OpenHands is relatively good at terminal use compared to most other agents. This is because it uses tmux, allowing it to deal with interactive commands and use ctrl-c, ctrl-z, etc. Nice to see that it shows up in benchmark scores too!

TL;DR: When you add a system prompt asking the model to act "based", it might act based.

Introducing Devstral Small and Medium 2507! This latest update offers improved performance and cost efficiency, perfectly suited for coding agents and software engineering tasks.

OpenHands hit a new round number on GitHub, 60k⭐️ Thanks to everyone for the support, and belief that the future of coding should be free and open source 😃 It's amazing to see us together with other OSS greats such as @Meta llama, @OpenInterpreter, @scikit_learn, and Keras!

People are racing to push math reasoning performance in #LLMs—but have we really asked why? The common assumption is that improving math reasoning should transfer to broader capabilities in other domains. But is that actually true? In our study (arxiv.org/pdf/2507.00432), we…

Imagine coding agents finishing your requests and sending a pull request in 30 seconds 🤯 Check out this new video of OpenHands + DevStral + @Snowflake’s new inference method ArcticInference. It speeds up coding agents by as much as 2x over vLLM (which is already fast).

This is amazing! Recently there is much talk of AI for science, and this project seems to do a lot to lower the barrier of entry to participate in the hugely important problem of securing our energy future.