OpenHands (@OpenHandsDev) / X

OpenHands

983 posts

OpenHands

@OpenHandsDev

OpenHands is the leading open source agent for software development, usable through a CLI, GUI, SDK, or IDE github.com/OpenHands/Open…

Joined May 2024

Pinned
OpenHands
@OpenHandsDev
Mar 2
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.
63K
OpenHands
@OpenHandsDev
Jun 17, 2025
Introducing the OpenHands CLI, a new coding CLI that: - Has top accuracy (similar to Claude Code) - Is completely open source, MIT licensed - Is model agnostic, use an API or bring your own - Is simple to install and run `pip install openhands-ai` and `openhands` (no Docker!)
00:00
309K
OpenHands
@OpenHandsDev
Mar 31, 2025
Today, we're excited to make two big announcements! - OpenHands LM: The strongest 32B coding agent model, resolving 37.4% of issues on SWE-bench Verified 📈 - OpenHands Cloud: SOTA open-source coding agents from your computer, phone, github, with $50 in free credits 🙌☁️
227K
OpenHands
@OpenHandsDev
Jul 16, 2025
Kimi-K2 is definitely the first strong open-weight competitor to Claude Sonnet. 65.4% on SWE-Bench Verified in OpenHands, just 2.6 points shy of Claude Sonnet 4 with the same 100 iterations. API cost is 4x cheaper, together with all benefits of open weights.
128K
OpenHands
@OpenHandsDev
Jul 14, 2025
OpenHands is live on TerminalBench and gets 41.3% with claude-4-sonnet, 6 points better than Claude Code! If you want to use an agent that can use the terminal, in your terminal -- try out the OpenHands CLI.
00:00
44K
OpenHands
@OpenHandsDev
Apr 17, 2025
We created a new state-of-the-art agent on the SWE-Bench Verified leaderboard, at a 66.4 resolve rate! It is based on: 1. A strong base agent (using Claude-3.7 Sonnet). 2. A specially-trained "critic model" that can distinguish good solutions from bad ones.
71K
OpenHands
@OpenHandsDev
Jul 17, 2025
Replying to @OpenAI
This is exciting! If you want an agent that can browse the web, do deep research, and write/run code that you can use on your own computer, you can try out OpenHands too:
GitHub - OpenHands/OpenHands: 🙌 OpenHands: AI-Driven Development
From github.com
23K
OpenHands
@OpenHandsDev
Apr 1, 2025
Due to popular demand, we have released two smaller versions of OpenHands LM: * 7B: huggingface.co/all-hands/open… * 1.5B: huggingface.co/all-hands/open… These can be used in resource-constrained settings or as draft models to speed inference!
OpenHands
@OpenHandsDev
Mar 31, 2025
Today, we're excited to make two big announcements! - OpenHands LM: The strongest 32B coding agent model, resolving 37.4% of issues on SWE-bench Verified 📈 - OpenHands Cloud: SOTA open-source coding agents from your computer, phone, github, with $50 in free credits 🙌☁️
OpenHands/openhands-lm-7b-v0.1 · Hugging Face
From huggingface.co
28K
OpenHands
@OpenHandsDev
May 21, 2025
We collaborated with @MistralAI to release a new open coding agent LLM, Devstral. OpenHands+Devstral is 100% local 100% open, and is SOTA for the category on SWE-Bench Verified: 46.8% accuracy. We're one step closer to an expert AI coder on your computer. Let's gooo 🚀
41K
OpenHands
@OpenHandsDev
Aug 8, 2025
We evaluated GPT-5 in OpenHands and it's the new number one coding agent model for us! Using exactly the same tools and harness it's 1.4 points better than Claude Sonnet 4 at 60% of the price. Full results here: docs.google.com/spreadsheets/d…
32K
OpenHands
@OpenHandsDev
Jun 17, 2025
Congratulations to Moonshot AI on their release of Kimi-Dev-72B, an open-weights model that achieves a great score of 60.4% on SWE-Bench Verified! Our community tried it in OpenHands, but it didn't work well, only 17% accuracy... Is this surprising? Actually not really! 🧵
36K
OpenHands
@OpenHandsDev
Jun 25, 2025
It finally happened 😭 After 8 months of hard work, the OpenHands agent surpassed the last human developer on our repository, @xingyaow_. Fellow humans, we had a good run.
14K
OpenHands
@OpenHandsDev
Jun 5, 2025
What if we could have *trustworthy* agents that don't just write code, but also do research, understand multimodal content, and perform many practically useful tasks? Today at OpenHands, we released a new agent that gets SOTA or competitive performance on 8 diverse tasks.
00:00
19K
OpenHands
@OpenHandsDev
Apr 29, 2025
It's great to see that Qwen3 works out-of-the-box with OpenHands! We've heard from community members that Qwen3-30B-A3B also works quite well, and achieves reasonable speed (50-60 tokens/s) even on a Mac M1 processor.
Qwen
@Alibaba_Qwen
Apr 29, 2025
Replying to @Alibaba_Qwen
We also evaluated the preliminary performance of Qwen3-235B-A22B on the open-source coding agent Openhands. It achieved 34.4% on Swebench-verified, achieving competitive results with fewer parameters! Thanks to @allhands_ai for providing an easy-to-use agent. Both open models and
33K