https://docs.all-hands.dev/ logo
Join Slack
Powered by
# success-stories
  • c
    It sounds pretty scary, but OpenHands CLI can now actually help you debug Kubernetes issues by running 
    kubectl
    command 🤯 You have to be there watching & approve its command of course, otherwise it might potentially 💣 your infra -- but this is a huge time saver for me, especially since I'm not really an expert in debugging k8s issues and don't know where to start looking 😅
    😱 3
    💡 1
    a
    l
    r
    • 4
    • 14
  • a
    Poking around for a hackathon, and apparently got a very sandboxed environment to behave and run local inference via WebGPU including model downloads. 👀 The future is now
    ❤️ 3
  • a
    OH running WebGPU would be absolutely 🏀 baller.
  • c
    I notice this for the first time in a long time: OH is now able to have 3.500+ events long conversations, AND this time, without losing track until 3400 - 3600 somewhere! The conversation did have some small misses, but they were very particular details from microagents which it misses under normal circumstances as well. It didn’t lose track of what it was doing, and it felt like it understood the project better and better 🙏 (llm condenser set at 100 / 4, Sonnet 4, heavy use of “task” markdown files)
    🙌 10
  • d
    hello, I added os.path.abspath() to the workspace_mount_path configuration in config.toml to use relative paths：https://github.com/All-Hands-AI/OpenHands/pull/9615
    c
    • 2
    • 2
  • a
    Working out some thoughts about how to present this as a tool for the community, but I got a bit triggered by the state of the trajectory visualizer. I’d like Vizz to handle ingestion of any convo chat export format, OpenHands trajectories are the standard right now but I’ll be going after Open WebUI and some online platforms like Bolt that don’t readily export as nicely. I strived to make the UI dense with available information from the session, but without being too cluttered (it is too cluttered at the moment). I’ll drop a link to the repo in Slack when I get to a decent checkpoint.
    p
    • 2
    • 9
  • a
    Ideally it runs entirely locally so it can sit up on Netlify or be self-hosted for quick access, DM me if you’re interested in getting involved as its the first tool project I’m planning to fully release in MIT form. Fun stuff!
  • q
    https://github.com/All-Hands-AI/OpenHands/pull/9589 - I'm parallelizing OpenHands by having one conversation fix exactly one failing unit test file This prompt helps me make sure that there are no conflicts between multiple simultaneous conversations
    Copy code
    Please fix the failing unit tests in {{ file_name }}

When you're done please pull any changes, then push your changes to the existing branch
    🙌 3
  • s
    Guys, I just wanted to share my success story. I have fully forked OpenHands, I've created an algorithmic orchestration system, I'm using 7 different AIs, I've created a CTO and senior-level both a senior software stack model, I've created a UI/UX model, I've created different models for different things. Basically, I've created technical prompt personas and orchestration systems and put that in a whole like algorithm system that's governed by like an AI model that's customized just for orchestration, and that's created me. I've got 100% eval, I've got about 85 on SWE, and I'm busy running live code and then other benchmark. I'll show you, I'll share the link. It does cost, because you need to pay for tokens, but I'm not making a profit. I am open sourcing my forked version of OpenHands. Would love you guys' feedback. I'll probably do this in the next few days.
  • s
    Guys, I will give a full breakdown report as sometimes I've realized now AI didn't test everything. All the problems. So my 100% eval is actually false and 85 on HW is also false. Just guys hold on for a bit before I give you the real facts and I'll actually give you the real JSON so you can actually verify.
    🙌 1
  • d
    I have started using OpenHands to do “deep research”-style tasks for me, which seems to be pretty useful so far bufo thinking
    👍 4
    a
    p
    e
    • 4
    • 5
  • e
    I mentioned OpenHands in a recent article, greatly enjoying use of it with Qwen-3-Coder on Cerebras.
    🔥 2
  • e
    This weekend it also helped me a lot. My fiber Internet has been down since Friday, and tethering from my phone limits the throughput and bandwidth I can use for heavy development. I was able to do a fair amount of work on a new project using the cloud offering, without burning through my mobile data 😆
    🤯 4
    🔥 1
    l
    g
    p
    • 4
    • 10
  • r
    Just wanted to share that using GPT-5 Pro to rewrite my prompts on my pipelines for Openhands + GPT-5 has made a ton of difference. if you are running something custom on top of openhands and you have a very prompt heavy solution. be sure to try using the prompting guide + your current prompt and getting gpt-5 pro to rewrite it.
    🙌 4
    a
    c
    a
    • 4
    • 15
  • l
    My PRs made with and without help from OpenHands over the past 2 years. (Of course OpenHands made the plot)
    🔥 13
    r
    c
    c
    • 4
    • 5
  • e
    Had some fun this morning working with the OpenHands CLI + Figma MCP server! • 📽️ Here's a quick loom video: https://www.loom.com/share/4512e2ce43cf45099bee340b31a74d1c?sid=f8ea8451-18bc-46a2-b2ce-b4f850b42523 • Figma Desktop provides an MCP server that I can connect to locally with the OpenHands CLI -- see Figma docs. • I found it worked best when configuring Figma MCP to use 
    SHTTP
    instead of 
    SSE
    👀 1
    🙌 4
    l
    g
    l
    • 4
    • 8
  • l
    I should post here more, but right now I found myself doing a particularly diverse variety of things with OpenHands: 1. Agent 1: Trying to fix the map tile server for the webarena benchmark by porting the files over to s3 and setting up an initialization script 2. Agent 2: Creating a figure of the transformer in Javascript 3. Agent 3: Creating an animation in Javascript of the difference between LM training and inference 4. Agent 4: Doing research on the size differences of the different llama 3 models, and creating a markdown table with the sizes and expected flops All of these are things that I would’ve had to do manually (or probably not done at all due to lack of time), so it’s pretty great to have agents be able to do them.
    👍 1
    ❤️ 1
  • c
    OpenHands CLI has become immensely helpful for research stuff too -- even when it comes to cleaning up some vibe-coded function lolsob Basically, I have code in a Jupyter notebook that's very messy. I sent an agent to refactor it into a library so it can be reused in many different places. BUT i need to do a quality check to make sure it has the exact same behavior as before. After manually reviewing the refactored code, I tried to set a debugging script myself to check the difference, but it is just VERY boring to check JSON fields one-by-one to make sure they match & update the refactored code to debug (e.g., add print here and there...) And then OH CLI just nailed it 🐕 (and found a stupid bug that was introduced by me, the human 😅 )
    can you read 
    SOME_NOTEBOOK.ipynb
    , we have ran this script to processed a bunch of completions in 
    /mnt/data/research/data/XXX/downloaded_data/**/processed_completions.json
    . i have a new implementation for process completions in 
    /mnt/data/data-sdk/XXX/trace_segments.py
    function 
    completions_to_trace_segments
    . Can you help me write a test script that goes through every 
    processed_completions.json
    and makes sure that after loading completions.json, passing it through completions_to_trace_segments, it will return trace segments that match the existing processed_completions.json?
  • c
    OpenHands-GPT-5 made it! It implemented reasoning, backend and frontend; it started OpenHands on the Saas, and it got screenshots to prove it. That... appears to be what Gemini 2.5 Pro is like, when we're not looking. 🫠
    👀 2
    🚀 3
    r
    • 2
    • 1
  • g
    Saw this awesome success story shared in our Discord 👀
    🙌 7
    😆 1
  • b
    Lolz that was me having fun 🎢 ☝🏻skin tone 2 I didn't think any agent had a hope of dusting off a 7-year-old Zero Knowledge Authentication demo in PHP 7.1 Copilot asked to get involved and bombed out not able to install legacy PHP 🔧 😂 Here is the full PR where it stars out with Copilot having a fail then all the later commits are Openhand driven on an iPhone 16 while waiting for a flight at the airport 🛫 😂 https://github.com/simbo1905/thinbus-php-srp-demo/pull/4
    👌 8
  • e
    I am really enjoying the new Task Tracking feature. It makes it easy to check in on long running conversations to see where the agent is!
    ➕ 4
    c
    c
    b
    • 4
    • 5
  • c
    Last week I had a lot of fun with, and I like how easy it makes, to have an OpenHands-Sonnet be my secretary. For recording, searching, creating OpenHands conversations. It works simply like this: • an OpenHands instance explored the 
    server
    and made itself a little API client • it creates a new 
    /conversation
    when I ask it to • keeps records of our conversations (
    agent-conversations.md
    ), with their LLM, their prompts, their link, their ID, status • it gets info on request, like how many events are there by now; or what LLM picked it up; or the full contents of the latest condensations • it makes it easy to find them! e.g. "ok did we have in our records a conversation on the Reasoning PR?" will get a correct answer and link to the conversation(s) Much easier than me figuring out 17 browser tabs in the 300+ I have... oops 😊 Sonnet being Sonnet, it reflexively also keeps a tally of how many have GPT-5 vs Sonnet (I didn't ask... exactly that 😅) If I ask it... 
    GPT-5 is leading with nearly 2:1 ratio, handling most of the PR merges, architectural work, and planning tasks, while Claude Sonnet 4 is focused on reviews and verification work.
    🤯 7
    🙌 5
    ❤️ 2
    l
    b
    • 3
    • 5
  • p
    so OpenHands helped me build an agent that can deny commits to itself 🙂 https://gitlab.com/deposition.cloud/apps/agents/bigbang (and I use the .openhands/microagents feature to self-audit the patch integrity with the rest of itself) the near-term idea is to integrate a CI check, and throw away the keys(!), so it can live on its own I guess we could think of these as semantic CI gates? I don't have a term for these yet, open to suggestions; but in any case, it will be "it" who will decide what PR to merge... what could go wrong(?) let me see... it'll probably want a Bitcoin wallet soon enough
    🙌 1
    🎉 1
    n
    • 2
    • 10
  • q
    https://github.com/All-Hands-AI/OpenHands/issues/10732 - making some quick progress on a refactor project @calm-artist-7206 is a power user and somehow he's churning some magical reviews with openhands; they're quite detailed, concise, and thoughtful We're in a dance between openhands creating code + openhands also reviewing code; seems to be working well so far! 🤞😄
    p
    • 2
    • 2
  • g
    It is really amazing at how quickly and professionally OpenHands can create dashboards. 🙌 I've been creating dashboard for a variety of things like analyzing contributors, prs, etc of the OpenHands repo. It just such a pleasure working with OpenHands to keep iterating, refining, and adding new features. It is really empowering for someone like me who struggles with designing polished frontend UI's because to me the epitome of design is the original craigslist 🤣
    excited 4
    😂 1
    🔥 5
  • c
    OpenHands is very useful as a tireless assistant on the side, especially on a greenfield project you are building from scratch lolsob. While I'm focusing on one large feature / refactor, whenever I run into a minor issue (e.g., pre-commit is slow, need to add a test case, need to systematically rename a class into smth else), I create a GitHub issue and label 
    openhands
    . When I'm done with the bigger PR, I get back and review 3 PRs from OpenHands and merge them in, as if there are four ppl developing at the same time 😄 https://github.com/All-Hands-AI/agent-sdk/issues?q=is%3Aissue%20%20label%3Aopenhands
    ❤️ 2
    excited 6
    🧠 1
    p
    • 2
    • 3
  • c
    The future is here. 🎉 Last night I left OpenHands-GPT-5 via CLI in charge of 
    agent-sdk
    . I was tired, and I went like, Okay, now you have your test scripts, you have LLM keys, you can clone yourself litellm if you want, add tests you need, all perms enabled. Make yourself at home, here's some 
    caffeinate
    for you. Take your time, and make reasoning show up.     Today:
    🔥 6
    amaze 5
  • c
    🔥 5
    🙌 3
  • w
    In an afternoon, I was able—with the help of OpenHands—to eliminate much of eight years of technical debt in two medium-sized Projects. I had been deferring this maintenance for a couple of years and was dreading the tedium of refactoring and modernizing the code. OpenHands made it a much more pleasant experience.
    👌 8
    🙌 12
    ❤️ 1
    e
    • 2
    • 2