MarinaBox: Open-Source Sandbox Infra for AI Agents
Hey everyone, We're excited to introduce MarinaBox, an open-source toolkit for creating isolated desktop/browser sandboxes tailored for AI agents. Over the past few months, we've worked on various projects involving: 1. AI agents interacting with computers (think Claude computer-use scenarios). 2. Browser automation for AI agents using tools like Playwright and Selenium. 3. Applications that need a live-session view to monitor AI agents' actions, with the ability for human-in-the-loop intervention. What we learned: All these scenarios share a common need for robust infrastructure. So,…
What it does
In the maker’s words, at launch
Hey everyone, We're excited to introduce MarinaBox, an open-source toolkit for creating isolated desktop/browser sandboxes tailored for AI agents. Over the past few months, we've worked on various projects involving: 1. AI agents interacting with computers (think Claude computer-use scenarios). 2. Browser automation for AI agents using tools like Playwright and Selenium. 3. Applications that need a live-session view to monitor AI agents' actions, with the ability for human-in-the-loop intervention. What we learned: All these scenarios share a common need for robust infrastructure. So, we built MarinaBox to provide: • Containerized Desktops/Browsers: Easily start and manage desktop/browser sessions in a containerized environment. • Seamless Transition: Develop locally and host effortlessly on your cloud in production. • SDK/CLI for Control: Native support for computer use, browser automation (Playwright/Selenium), and session management. • Live-Session Embedding: Integrate a live view directly into your app, enabling human-in-the-loop interactions. • Session Replays: Record and replay sessions with ease. Check it out: • Documentation:https://marinabox.mintlify.app/get-started/introduction Main Repo:https://github.com/marinabox/marinabox Sandbox Infra:https://github.com/marinabox/marinabox-sandbox We’ve worked hard to make the documentation detailed and developer-friendly. For any questions, feedback, or contributions: • Discord: https://discord.gg/nAyFBSSU87 • Email: [email protected] Let us know what you think, and feel free to contribute or suggest ideas! We built this in about 10 days and a large part of the code and docs were generated using AI. Let us know if something is wrong. We would love your feedback. PS: The above version allows you to run locally. We are soon releasing self hosting on cloud.
Does the same job
all alternatives →- IBI Built a Sandbox for AgentsJan 2026 · github.com · ▲31
- ADAgent-desktop – Native desktop automation CLI for AI agentsMay 2026 · github.com · ▲99
I've been building computer-use tools for a while, and I quietly launched this about a month ago (122 Stars on GH). I figured it was worth sharing here. Over the last few months, a lot of computer-use agents have come out: Codex, Claude Code, CUA, and others. Most of them seem to work roughly like this: 1. Take a screenshot 2. Have the model predict pixel coordinates 3. Click x,y 4. Take another screenshot 5. Repeat That works, but it's slow, expensive in tokens, and fragile. If the UI shifts a few pixels, things break. And the model still doesn't know what any element actually is. But the…
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 · 17d 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 · 27d ago · cactuscompute.com
