All Hands AI
@allhands_ai
We build AI software development agents, in the open. Developing OpenHands: https://github.com/All-Hands-AI/OpenHands
We’ve heard from a lot of OpenHands users that: 1. rate limits block them from using OpenHands efficiently 2. they’d like to switch between LLMs for different tasks To help with this, we have opened up an OpenHands LLM Provider that is available to all OpenHands cloud users.
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
@allhands_ai I love you guys. This is such an amazing product. I've never had an AI that managed to do VISUAL TESTING TOO!!!!!!! Cursor is only textual.
Do you love AI agents, open source, and helping to make development teams more productive? If so, All Hands AI has a position open for a forward deployed engineer! allhandsai.applytojob.com/apply/v5Dip8MJ… Please apply to join us if this sounds like a job you'd enjoy 🙌
Nothing more frustrating than seeing "private scaffold" on public benchmark results I love that model providers like Qwen and Mistral are now reporting their results specifically using OpenHands as the scaffold--feels like we're becoming a standard here x.com/Alibaba_Qwen/s…
>>> Qwen3-Coder is here! ✅ We’re releasing Qwen3-Coder-480B-A35B-Instruct, our most powerful open agentic code model to date. This 480B-parameter Mixture-of-Experts model (35B active) natively supports 256K context and scales to 1M context with extrapolation. It achieves…
🔥 69.6% on swe-bench verified and great scores across the board. Can't wait to try it out in OpenHands ourselves!
>>> Qwen3-Coder is here! ✅ We’re releasing Qwen3-Coder-480B-A35B-Instruct, our most powerful open agentic code model to date. This 480B-parameter Mixture-of-Experts model (35B active) natively supports 256K context and scales to 1M context with extrapolation. It achieves…
Just added auth to this in just a couple hours using `openhands` from @allhands_ai !! Amazing experience!!
loom.com/share/97620e12…
We've been using OpenHands agents to build OpenHands for the past year or so, and have learned a lot along the way! Check out our webinar video on "How we build OpenHands with OpenHands" where we share some of our tips and tricks: youtu.be/CLpwray59-k
Nice new research work by @tiktok_us on benchmarking performance optimization by LLM agents: arxiv.org/abs/2507.12415 OpenHands w/ Sonnet 3.7 achieves the best results, optimizing 44 functions in popular open-source code bases (compared to human experts' 184).
If you’re using OpenHands Cloud, you can now run kimi-k2 (and many other SOTA models) right from the OpenHands CLI & self-hosted UI — no more juggling API keys. All usage is billed at cost, with no markup.
We’ve heard from a lot of OpenHands users that: 1. rate limits block them from using OpenHands efficiently 2. they’d like to switch between LLMs for different tasks To help with this, we have opened up an OpenHands LLM Provider that is available to all OpenHands cloud users.
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…
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.
There’s a new open-source coding agent in town 👀 Meet Devstral — built by @MistralAI + @allhands_ai for multi-step, full-repo software engineering tasks. Agentic. Efficient. Free to use. Let’s dive in 👇
OpenHands (the open-source coding agent by @allhands_ai) could be renamed HandsOff. It is, in my experience, the best of the open agents in autonomous execution. If you want to vibe and interact with AI there are many options. But for delegating complete tasks to AI - OpenHands.
OpenHands has made 6000 PRs and has a merge rate of 88% on open-source projects: insights.logicstar.ai This is by far the most of any open source agent, and comparable to Devin and Claude Agent.
Introducing Devstral Small and Medium 2507! This latest update offers improved performance and cost efficiency, perfectly suited for coding agents and software engineering tasks.
Try it out in OpenHands following the directions here! docs.all-hands.dev/usage/llms/loc…
Introducing Devstral Small and Medium 2507! This latest update offers improved performance and cost efficiency, perfectly suited for coding agents and software engineering tasks.