Open Computer Use
Hi everyone, I'm Vasek (https://x.com/mlejva), the CEO of the company behind this - https://e2b.dev. The company is called E2B. We're an open-source (https://github.com/e2b-dev) devtool that makes it easy to run untrusted AI-generated code in our secure sandboxes. You can think of us as coding runtime for LLMs. You can self host us on GCP (https://github.com/e2b-dev/infra/blob/main/self-host.md) and we're working on AWS, then Azure, and any Linux machine. This repo is one of our open-source projects that we're…
What it does
In the maker’s words, at launch
Hi everyone, I'm Vasek (https://x.com/mlejva), the CEO of the company behind this - https://e2b.dev. The company is called E2B. We're an open-source (https://github.com/e2b-dev) devtool that makes it easy to run untrusted AI-generated code in our secure sandboxes. You can think of us as coding runtime for LLMs. You can self host us on GCP (https://github.com/e2b-dev/infra/blob/main/self-host.md) and we're working on AWS, then Azure, and any Linux machine. This repo is one of our open-source projects that we're releasing to show developers what they can build with E2B. We used our sandboxes that are powered by AWS's Firecracker and gave them GUI with Linux. At the same time we made it easy to control this cloud computer with our Desktop SDK (https://github.com/e2b-dev/desktop). Essentially building a virtual desktop computer for AI and we gave it to LLMs to control it. Here's a demo we showed at an event - https://x.com/tereza_tizkova/status/1878834392891838556 We think computer use is still highly experimental but it feels sort of similar like AI codegen in early 2023. You see the sparks but it's not there just yet. However, we wanted to research if open-source LLMs could at least get some results. Here we're using Llama 3.2, Llama 3.3, and an OS-Atlas as a base model (fine-tuned Qwen). If you have any questions, happy to answer them! We're also hiring! If you're a fullstack engineer, distributed systems engineer, AI engineer, product designer, or GTM person and based in SF send me a hello to vasek @ e2b.dev!
Pricing, as stated on its site
Free — Open Computer Use is an open-source project hosted on GitHub with no pricing mentioned. It is freely available as an open-source tool for running AI-generated code in secure sandboxes, with self-hosti
checked September 2026 · prices change
Does the same job
all alternatives →- OSOpen-source user onboarding and KYC flow made with Svelte (~50kb)2022 · github.com · ▲254
Hi everyone, We’re building an open-source identity and risk management platform and we’ve just released the first chunk of code, a fully customizable KYC flow & UI, to the public. We’ve chosen to use Svelte so our flows would be lightweight (it is ~50kb gzipped). Next up: - Adding forms and components for it to be used as a full onboarding flow. - Releasing an open-source case management dashboard, for manual approval of users. - Releasing an open-source rule engine, to help automate decisions. We’d love to hear your feedback, suggestions, or any question you’ve got. And if the rest of the…
- IBI built an OSS alternative to Azure OpenAI services2023 · github.com · ▲200
Hey HN, I am proud to show you guys that I have built an open source alternative to Azure OpenAI services. Azure OpenAI services was born out of companies needing enhanced security and access control for using different GPT models. I want to build an OSS version of Azure OpenAI services that people could self host in their own infrastructure. "How can I track LLM spend per API key?" "Can I create a development OpenAI API key with limited access for Bob?" "Can I see my LLM spend breakdown by models and endpoints?" "Can I create 100 OpenAI API keys that my students could use in a classroom…
- IBI built a service to help companies reduce AWS spend by 50%2022 · usage.ai · ▲123
Hey HN: Kaveh here, the founder of https://www.usage.ai/ We help companies drive down AWS EC2 spend. Why? Because the way it's done now is a pain. DevOps and Software Engineers end up spending time managing costs rather than focusing on business problems. Previous to founding Usage, I worked on high-performance computing research at JP Morgan Chase and as a software engineer at a number of smaller startups. Here's how it works: We are typically brought in by a DevOps manager to cut AWS EC2 costs. The app is entirely self-service and the savings are generated automatically,…
- BOBoxyHQ – open-source alternative to Auth0/WorkOS2022 · boxyhq.com · ▲176
Hi HN, we are Deepak and Sama, co-founders of BoxyHQ (https://boxyhq.com/). BoxyHQ provides an open-source platform for developers to quickly integrate enterprise features into their software solutions. These include SAML Single Sign-On (SSO), Audit logs, with more to come :) Every B2B startup faces a common challenge when it comes to selling into the Enterprise; they need to allocate time and resources to support all the requirements to make their offering enterprise-grade. Supporting these requirements is a significant undertaking for the engineering team, especially since…
- RLRunning LLMs in one line of Python without Docker2023 · lepton.ai · ▲68
Hello Hacker News! We're Yangqing, Xiang and JJ from lepton.ai. We are building a platform to run any AI models as easy as writing local code, and to get your favorite models in minutes. It's like container for AI, but without the hassle of actually building a docker image. We built and contributed to some of the world's most popular AI software - PyTorch 1.0, ONNX, Caffe, etcd, Kubernetes, etc. We also managed hundreds of thousands of computers in our previous jobs. And we found that the AI software stack is usually unnecessarily complex - and we want to change that. Imagine if you are a…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, January 2025
the whole month →- IM
Hello! I'm Byran. I spent the past ~6 months engineering a laptop from scratch. It's fully open-source on GH at: https://github.com/Hello9999901/laptop
Dev tools · 2025 · byran.ee
- TITetris in a PDF▲1,289
I realized that the PDF engines of modern desktop browsers (PDFium and PDF.js) support JavaScript with enough I/O primitives to make a basic game like Tetris. It was a bit tricky to find a union of features that work in both engines, but in the end it turns out that showing/hiding annotation "fields" works well to make monochrome pixels, and keyboard input can be achieved by typing in a text input box. All in all it's quite janky but a nice reminder of how general purpose PDF scripting can be. The linked PDF is all ASCII so you can just open it in a text editor, or have a look at…
Life & fun · 2025 · th0mas.nl
Create lifelike, personalized AI avatars from text prompts
AI · 2025 · jogg.ai
