OpenHands is the leading open source agent for software development, usable through a CLI, GUI, SDK, or IDE github.com/OpenHands/OpenHan…
- Tweets 991
- Following 19
- Followers 10,881
- Likes 724
Pinned Tweet
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.
7
13
196
64,336
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!)
38
260
1,985
308,880
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 🙌☁️
36
126
863
227,281
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.
16
97
784
128,463
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.
13
39
484
44,212
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.
13
43
407
70,691
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.com/All-Hands-AI/Open…
4
19
248
23,325
Due to popular demand, we have released two smaller versions of OpenHands LM:
* 7B: huggingface.co/all-hands/ope…
* 1.5B: huggingface.co/all-hands/ope…
These can be used in resource-constrained settings or as draft models to speed inference!
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 🙌☁️
7
35
246
28,025
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 🚀
Meet Devstral, our SOTA open model designed specifically for coding agents and developed with @allhands_ai
mistral.ai/news/devstral
3
29
243
40,810
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…
16
30
241
32,414
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! 🧵
6
22
228
35,693
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.
7
25
201
13,726
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.
5
28
173
19,066
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.
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 open agents are exciting!
5
21
166
32,546
We tested out Claude 4 in OpenHands, and yeah, it's good.
70.4% on SWE-Bench Verified out of the box, +10 points over 3.7 Sonnet.
Our vibe checks also passed, so it's available in OpenHands and the OpenHands Cloud today.
5
14
143
24,039
The SWE-Bench verified leaderboard has been updated and OpenHands is both number one overall, and the only open source agent in the top 10! swebench.com/
Read more about our approach of the OpenHands critic here: all-hands.dev/blog/sota-on-s…
4
22
142
15,838
We just released, open source, the strongest AI software developer to date:
🥇 53% resolve rate on SWE-Bench Verified
🥇 41.7% resolve rate on SWE-Bench Lite
Details: all-hands.dev/blog/openhands…
🧵↓
7
25
125
39,613
It's great to see OpenHands LM on the top 10 trending models on Hugging Face along with so many other big names we respect!
Here's the link to the HF page: huggingface.co/all-hands/ope…
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 🙌☁️
5
20
121
28,494
Wow! OpenHands LM is now pretty easy to use locally thanks to @lmstudio!
🔥 New model: OpenHands LM 32B, an impressively strong open coding agent model from @allhands_ai
Run in the terminal:
lms get openhands-lm-32b
🚀🙌
1
13
111
10,383
Devstral is the number one model on @huggingface today 🎉 Thanks everyone for the support!
huggingface.co/models
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 🚀
5
14
107
22,776
🔥
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 top-tier performance across multiple agentic coding benchmarks among open models, including SWE-bench-Verified!!! 🚀
Alongside the model, we're also open-sourcing a command-line tool for agentic coding: Qwen Code. Forked from Gemini Code, it includes custom prompts and function call protocols to fully unlock Qwen3-Coder’s capabilities. Qwen3-Coder works seamlessly with the community’s best developer tools. As a foundation model, we hope it can be used anywhere across the digital world — Agentic Coding in the World!
💬 Chat: chat.qwen.ai/
📚 Blog: qwenlm.github.io/blog/qwen3-…
🤗 Model: hf.co/Qwen/Qwen3-Coder-480B-…
🤖 Qwen Code: github.com/QwenLM/qwen-code
2
4
104
5,539
Want state-of-the-art AI agents to help your software development process?
Don't want your private codebases to travel outside your VPC?
We have just released the OpenHands Self-hosted Cloud, which provides all the features of the OpenHands cloud within a private firewall.
5
5
101
9,170
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).
4
16
102
7,091
Having appropriate tests makes a world of difference for agent-driven development.
If your agent can write a test to localize a bug or exercise a new feature, the following implementation is much more solid.
OpenHands+GPT-5 is now 🥇 on the SWT-Bench testing leaderboard!
6
18
101
22,241
Great video by @Sentdex on "Programming using LLM Agents in 2025" demonstrating some great tips on how to get the most out of LLM coding agents (using OpenHands as an example) piped.video/watch?v=WKF__cJT…
The idea of evolving model architectures is pretty cool too 😀
4
17
92
11,291
One major obstacle to using AI agents is cost.
At OpenHands, we developed *context condensers* technique that *reduces API costs by 2x* on our state-of-the-art agent while maintaining quality according to SWE-bench and vibe checks.
4
7
87
9,888
We built OpenHands in the open (~60K ⭐️ on GitHub).
Now we’re giving back to the OSS ecosystem.
Announcing the OpenHands Cloud OSS Credit Program → $100–$500 credits for maintainers.
👉 Learn how to apply!
1
7
79
9,650
Congratulations to the @Zai_org team on the release of this new open-weights model.
We're happy to see that OpenHands is yet again being used as a platform state-of-the-art open weights LM research!
Introducing GLM-4.5 and GLM-4.5 Air: new flagship models designed to unify frontier reasoning, coding, and agentic capabilities.
GLM-4.5: 355B total / 32B active parameters
GLM-4.5-Air: 106B total / 12B active parameters
API Pricing (per 1M tokens):
GLM-4.5: $0.6 Input / $2.2 Output
GLM-4.5-Air: $0.2 Input / $1.1 Output
Tech Blog: z.ai/blog/glm-4.5
Weights: huggingface.co/zai-org/GLM-4…
Z.ai API: docs.z.ai/guides/llm/glm-4.5
OpenRouter: openrouter.ai/z-ai
Develop Tools: docs.z.ai/scenario-example/d…
Try them now: chat.z.ai
1
5
76
6,614
Want to programmatically use AI agents to perform coding and maintenance tasks in the background with a single function call?
Now you can do so with the OpenHands API!
🧵 about use cases and how to get started below.
4
17
73
9,092
We're enjoying using the CLI when logged in to servers, or just to spin up a session in a low-friction way. Hope that you like it too!
Here is:
- A blog with more details: all-hands.dev/blog/the-openh…
- Docs: docs.all-hands.dev/usage/how…
- Slack for support: join.slack.com/t/openhands-a…
3
4
67
7,314
"I threw an issue from a side project at 6 AI tools today: Claude Code, OpenAI Codex (the CLI version), Factory, Devin, Jules, and All Hands. None resolved the issue in one-shot, though eventually All Hands got the job done and its PR was merged."
yoav.blog/2025/06/10/compari…
1
13
68
4,641
OpenAI released a new coding agent today Codex, exciting development in the coding agent space! openai.com/index/introducing…
We're going to go through some of the key interesting points on the thread here.
2
7
68
10,744
At @allhands_ai we are dedicated to:
1. Making OpenHands the best agent for software development
2. Doing it in an open, community-driven way
To make this sustainable, we formed a company around the project.
@rbren_dev explains our philosophy in our new blog.
2
5
68
5,474
AI Coding Agents: What Works and What Doesn't
We've released the video of our recent webinar, where @rbren_dev shares some of the lessons we've learned over the past year of using software development agents.
piped.video/watch?v=_rltvykJ…
1
5
63
9,215
OpenHands LM is now served by @FeatherlessAI on @openrouter!
openrouter.ai/all-hands/open…
You can try it out there if you'd like to test OpenHands with the LM before using it locally.
5
10
64
6,833
OpenHands is the best agent on Multi-SWE-Bench, a new benchmark for testing coding agents on 8 different languages!
We'll continue to improve, what languages do you want to work on with OpenHands?
🔥 Can your LLM fix bugs beyond Python?
Meet our Multi-SWE-bench — the first multilingual benchmark for issue resolving.
Not just Python, but Java, TS, JS, Go, Rust, C, and C++🧩
💥 1,632 real-world issues
✅ Verified by 68 engineers
📦 Dockerized, reproducible, battle-tested
🧠 Covers easy, medium, and hard bug fixes
📊 Designed to benchmark LLMs as true dev agents
To scale beyond benchmarks, we also launch Multi-SWE-RL —
🎮 An open-source RL community to build interactive training environments for LLMs as autonomous agents.
🌱 4,723 containerized issue-resolving tasks, 7 languages, and counting.
🤝 We invite the community to contribute, expand, and shape the future of software-native RL.
It took us a year to build.
Now let’s see what your model can do.
🏆 Leaderboard: multi-swe-bench.github.io
📄 Paper: arxiv.org/abs/2504.02605
🧬 Code: github.com/multi-swe-bench/m…
📚 Multi-SWE-bench Dataset: huggingface.co/datasets/Byte…
🎮 Multi-SWE-RL Dataset: huggingface.co/datasets/Byte…
#LLM #RL #SWEbench #OpenAI #Anthropic #DeepSeek #Doubao
11
62
5,836
In this work with UC Berkeley and CMU, we found that o1 underperforms Claude when used in OpenHands. We're still digging into details, but we thought it'd be interesting to share our intermediate results now!
Reasoning is not a panacea for agents, other elements are necessary.
Surprising find: OpenAI's O1 - reasoning-high only hit 30% on SWE-Bench Verified - far below their 48.9% claim. Even more interesting: Claude achieves 53% in the same framework. Something's off with O1's "enhanced reasoning"... 🧵1/8
2
6
59
6,461
We are proud to announce that All Hands has raised $5M to build the world’s best software development agents, and do it in the open 🙌
all-hands.dev/
Thank you to @MenloVentures and our wonderful slate of investors for believing in the mission!
All Hands AI raises $5M to build open source agents for developers tcrn.ch/3MxNUvB
3
6
59
55,707
One of our goals is that AI Agents for software development can be invoked from everywhere developers work.
Because of this, it is possible to call OpenHands through a GUI, CLI, github, and an API. And now you can communicate with OpenHands agents through slack!
2
7
57
9,703
Last week we announced that OpenHands is the strongest software developer in the world.
Today we're officially announcing an online app that makes OpenHands easier to use than ever: all-hands.dev/blog/announcin…
It's currently in beta and rolling out quickly, sign up today!
We just released, open source, the strongest AI software developer to date:
🥇 53% resolve rate on SWE-Bench Verified
🥇 41.7% resolve rate on SWE-Bench Lite
Details: all-hands.dev/blog/openhands…
🧵↓
5
11
56
6,824
We're excited to end 2024 with OpenHands becoming the 70th most starred Python repo on GitHub! We’ve come so far in these 9 months or so, and thanks a bunch to the wonderful maintainers, contributors, and community that brought us here 🚀
2
8
53
6,730
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.
3
3
54
11,761
OpenHands 0.34.0 is released! It features two new UI improvements to OpenHands that should make OpenHands easier and more fun to use!
1
5
54
7,647
🔥
69.6% on swe-bench verified and great scores across the board. Can't wait to try it out in OpenHands ourselves!
53
5,730
LLM-powered coding agents are all the rage, but how good are various LLMs when used as coding agents?
To figure this out, we:
- Developed cloud-based infra for agent eval that speeds evals by 30x or more
- Used this to evaluate 10 SOTA open & closed models
all-hands.dev/blog/evaluatio…
2
7
51
12,623
A little less than a year after its creation, OpenHands has received 50k stars on github. Thanks for the love everyone, we have the best community ♥️
Let's keep working to make the best software development agents be open software developer agents.
2
7
50
5,376
OpenHands has long been one of the best coding agents overall, and especially top open source agents. But running it required a docker sandbox and GUI, and many of our users asked for a more light-weight alternative. This CLI solves this.
2
1
48
8,983
OpenHands now the 90th most starred Python repo on Github 🌠
It’s truly an honor to be listed with other great libraries like the OpenAI gym, LLaMA-Factory, ray, and gradio! Really proud of our community and everything we’ve done, let's continue to go🚀
github.com/All-Hands-AI/Open…
2
5
46
9,336
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: piped.video/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.
8
45
6,983
OpenHands 0.27.0 is out! Some exciting progress over the past two weeks:
github.com/All-Hands-AI/Open…
- Context condensation with large time/money savings on long conversations
- Addition of claude-3.7 as a provider
- Integration with gitlab
4
44
3,355
ReasonerAgent is an exciting new open-source reasoning agent that can solve long-horizon web tasks.
Built on the OpenHands BrowserAgent!
🤖Thrilled to introduce _ReasonerAgent_ - A fully open source, ready-to-run agent that does research🧐 in a web browser and answers your queries
Use ReasonerAgent to help you:
✈️search for flights,
🛍️compile shopping options,
🗞️research news coverage, etc.
📘Check out more 👇
1/6
8
40
5,429
OpenHands LM, is an open-weights 32B model based on @Alibaba_Qwen, that we trained using the agent training infra at @allhands_ai
In short, we use the SWE-Gym environment, and perform many rollouts with existing models to get agent trajectories for training.
2
2
41
6,109
Try it out in OpenHands following the directions here!
docs.all-hands.dev/usage/llm…
Introducing Devstral Small and Medium 2507! This latest update offers improved performance and cost efficiency, perfectly suited for coding agents and software engineering tasks.
1
5
41
2,789
In implementing this, we added a few pieces of functionality:
1. slash commands to make it easy to change settings
2. a confirmation mode to allow you to check commands before you run them
1
36
8,644
Announcing the release of OpenHands 0.16.0 🙌
github.com/All-Hands-AI/Open…
OpenHands now authenticates to your repositories as a github app. This means that (1) no more need to get a github personal access token, and (2) you can control which repos OpenHands has access to!
2
3
35
1,620
We're currently dealing with a surge of interest in app.all-hands.dev (+50% users over the course of a few days).
It's great to see so many people excited to try out coding agents, and we're working hard to keep everything running smoothly, but apologies for any blips 🙏
1
1
36
5,973
You're sleeping on AI SWEs: engines.dev/blog/sleeping-on…
Nice blog post about why agents for AI development can greatly speed productivity over the standard workflow (using OpenHands as an example of course 😀).
3
35
3,009
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!
2
1
34
3,136
The newest version of OpenHands is a pretty good front-end dev too!
Protip: Tell OpenHands to bring up the frontend to click through and test the functionality. You can even watch it in real-time on the browser.
We just updated the SWE-bench Multimodal leaderboard with new systems from @refact_ai, @allhands_ai and @TU_Muenchen. Congrats to all teams on pushing the state-of-the-art performance!
SWE-bench Multimodal challenges AI systems to fix issues that are described using screenshots.
2
3
33
2,692
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).
1
10
34
7,764
Try it out in OpenHands following the directions here! docs.all-hands.dev/usage/llm…
4
33
4,173
Check out:
- The blog for technical details and usage instructions: all-hands.dev/blog/introduci…
- The checkpoints on hugging face if you want to start right away: huggingface.co/all-hands/ope…
1
9
31
8,480
We're excited to announce that the first OpenHands meetup will take place in NYC 🗽 on Monday, Feb 24!
You can sign up here: lu.ma/nzxa1qmq Space is limited!
We're also planning to do something in SF 🌉 so stay tuned as well.
2
7
29
4,892
OpenHands 0.21.0 is out! Some big changes 🎉
github.com/All-Hands-AI/Open…
* OpenHands can now be used in 10 languages (e.g. Chinese, Japanese, Arabic, Spanish)
* You can use OpenAI o1 and set reasoning_effort
* You can use a separate LM as a draft editor
1
5
28
3,975
OpenHands LM punches above its weight, resolving 37.4% of real-world issues, accuracy competitive to DeepSeek, a model 20x the size!
It can be run locally on a machine with a single 3090 GPU for instance. It also has 128k context for long agent trajectories and large code bases.
2
2
29
5,264
📈So far, in November, OpenHands authored or co-authored ~60% of commits to the openhands-resolver github.com/All-Hands-AI/open… repo and ~20% of the main repo github.com/All-Hands-AI/Open…
1
2
31
9,514
Say hello to our new name, OpenHands!
If you'd like to help us build software development agents in an open and collaborative way:
* Join our open source community: github.com/All-Hands-AI/Open…
* Apply for our open positions: allhandsai.applytojob.com/ap…
Announcement: the maintainers team of the OpenDevin open AI software development agent have decided to rename the project to OpenHands 🙌
github.com/All-Hands-AI/Open…
We have also made a big 0.9.0 release with a number of new features, read below for details.
1
5
30
5,783
We have a bunch of exciting features in OpenHands 0.38.0!
- Native Windows support (no WSL)
- Browser screenshots
- More customizability of sandboxes
We also released a Chrome extension allowing for one-click starts of OpenHands from github!
1
3
29
2,764
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.
2
31
4,987
📣Announcing OpenHands 0.10.0!📣
Our biggest release in a while with
- A brand new UI
- Ability to connect to Github projects w/ tokens
- Getting started examples
- Many resiliancy improvements
- Support for running sandboxes on @modal_labs
github.com/All-Hands-AI/Open…
2
4
30
4,841
On Tuesday June 24th 11:30AM Eastern, we're having a webinar by All Hands CEO @rbren_dev on "AI Coding Agents: What Works and What Doesn't."
We'd love to see you there! lu.ma/cudxstkw
4
27
1,687
As part of the 1-year anniversary of OpenHands, we wrote a quick one-year retrospective including both the things we've done and the things we're looking forward to next!
all-hands.dev/blog/one-year-…
It's the first birthday of OpenHands today 🎉
One year ago today @huybery created the OpenDevin repo, shortly after @gneubig committed the first frontend code. The rest is history!
At this week's OpenHands community meeting we'll recap the past year and look at the year ahead.
4
27
2,997
Wow, congratulations to ByteDance on the great release of Doubao-Seed-Code, achieving very competitive scores on SWE-Bench and Multi-SWE-Bench with OpenHands.
Looking forward to try it out ourselves.
ByteDance just launched Doubao-Seed-Code, a model specifically designed for programming tasks.
It supports native 256K long context and has claimed the top spot on the SWE-Bench Verified leaderboard.
2
3
27
11,188
OpenHands context compression in action! If you used OpenHands before and thought it was a bit expensive, try again with the latest version, it's cheaper, snappier, and still effective.
2
24
3,201
How good is Devstral? Pretty good. Compared to other general-purpose models evaluated in OpenHands, at 22B it beats models that are 10x the size by 8-10 points.
It also beats specialized models trained on SWE-Bench, and smaller closed models like Claude Haiku and gpt-4o-mini.
2
2
26
2,334
‼️We’re charting the path to OpenHands v1 🎉
We’ve heard your feedback
- Increase development velocity to ship new feature quick
- Easily deploy more agents in your applications
- Quickly refactor code to better your UX
We are resetting so you can build, ship, and grow faster
1
4
27
1,751
New research by CMU, OpenHands, and several other institutions on creating a large dataset for training agentic language models!
We just built and released the largest dataset for supervised fine-tuning of agentic LMs, 1.27M trajectories (~36B tokens)!
Up until now, large-scale SFT for agents is rare - not for lack of data, but because of fragmentation across heterogeneous formats, tools, and interfaces.
To solve this, we introduce the Agent Data Protocol, a new “interlingua” between a broad variety of heterogeneous agent datasets - coding, browsing, API/tool use - and unified agent training pipelines downstream.
We unified 13 datasets into ADP, converted them to be compatible with multiple agent frameworks, and observed ~20% average gains, reaching SOTA/near-SOTA without domain-specific tuning.
📄 Read our paper: arxiv.org/abs/2510.24702
🌐 Check our project website: agentdataprotocol.com/
And this is just getting started, we can add more datasets, further expand the resources, and make training agent LMs easy for all. We’d love to have you join the shared effort and help to make ADP the open standard for the community 🚀
3
26
5,020
This opens many possibilities, such as:
- Running many agents in parallel
- Solving github issues autonomously from
- Performing all kinds of maintenance tasks
See the attached video for some example use cases!
2
2
24
4,020
Nice guide from the folks at @cognition_labs on using coding agents, it all resonates! devin.ai/agents101
You can pair this with our own guide on "vibe coding higher quality code" to learn emerging best practices around agentic coding: all-hands.dev/blog/vibe-codi…
4
25
1,620
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/ap…
Please apply to join us if this sounds like a job you'd enjoy 🙌
1
3
24
6,157
There are two ways of solving SWE-bench style bug fixing tasks:
- Agents like OpenHands (github.com/All-Hands-AI/Open…): which take actions exploring around the codebase, editing files, etc.
- Fixed workflows like Agentless (github.com/OpenAutoCoder/Age…): which only use a fixed workflow.
1
1
23
2,312
Congrats to the @Zai_org team, and we're happy to see OpenHands supporting state-of-the-art open weights model research!
1
19
1,864
Anthropic has a new blog on using code to implement more efficient agents that a few people have pointed out to us.
Some have asked, how can I use this in OpenHands? The answer is, well you always could 😃 OpenHands is based on the CodeAct agent, which does precisely this.
2
2
23
1,743
Mitigating prompt-injection in software agents ‼️
The Good 😇
The Bad 😈
And a playbook on how to stay safe 🦾
Read to learn more👀
#AIsecurity #LLMAgents #PromptInjection
2
3
23
3,299
Claude-3.7 is now selectable as a verified model in OpenHands! Seems like a great model, have fun everyone 🚀
1
3
21
2,671
Our Pittsburgh OpenHands meetup is this Feb 21 and the CMU Swartz Center!
The agenda includes:
* an intro to coding agents
* chat by volunteer OpenHands users
* discussion of research challenges
* hackathon
Food will be served, and a few slots remain!: lu.ma/7kwrjwgl
1
3
21
6,129
Getting OpenHands+Devstral working on your computer is easy.
Follow our directions here: docs.all-hands.dev/modules/u…
Or watch the video of us setting it up in real-time with @lmstudio
1
2
22
3,285
Nice blog! We also posted a similar take on this a few months ago: all-hands.dev/blog/dont-slee…
1
1
23
2,724
In the bay area? 🌉 Want to talk about technology and use cases of AI agents in software development?
On 3/26 we're having an SF meetup with coding agent users/researchers, led by the developers of OpenHands and founders of @allhands_ai
Come join us! lu.ma/durei3f9
5
22
8,558
How does it work? Every fixed number of turns, we use an LLM to condense the previous context, keeping important information and removing unnecessary information.
More details in our blog: all-hands.dev/blog/openhands…
1
1
21
874
New paper by University of Illinois tests the ability of agents to aid cybersecurity research: SEC-Bench.
It tests both PoC input generation and automated vulnerability patching.
HT @develacker, @ZiqiCharles, Hanxiao Lu, @lingmingzhang
1
3
19
2,883
devstral! all-hands.dev/blog/devstral-…
You can see directions to set it up here: docs.all-hands.dev/usage/llm…
1
21
3,866
Exciting release of OpenHands 0.14.0:
* We have ⭐️integrated VSCode!⭐️ - you can now an IDE to edit files directly from the OpenHands interface
* Better support for non-function-calling LMs
* Better support for long sessions
* Robustness improvements
github.com/All-Hands-AI/Open…
1
6
20
3,073
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: piped.video/CLpwray59-k
2
20
6,348
Fixed workflows can work well with smal models on exactly the tasks they were designed for, but do not adapt as well to the broader set of tasks that you may want AI to do for you.
We want agents to do much more: all-hands.dev/blog/building-…
So at OpenHands we're all-in on agents!
1
2
20
3,145
Announcing OpenHands 0.9.5!
github.com/All-Hands-AI/Open…
- Modifications to support OpenAI o1 models
- Added better error displays
- Many improvements to UI-based configuration
- Improved responsiveness to users starting/stopping the agent
4
19
1,794
We're offering $50 in free credits to let people check out the OpenHands Cloud today! Take a look at:
- Our blog for more details: all-hands.dev/blog/introduci…
- Start using the app: app.all-hands.dev/
5
2
20
3,277
