Eve is an AI agent harness that runs in an isolated Linux sandbox (2 vCPUs, 4GB RAM, 10GB disk) with a real filesystem, headless Chromium, code execution, and connectors to 1000+ services.

You give it a task and it works in the background until it's done.

I built this because I wanted OpenClaw without the self-hosting, pointed at actual day-to-day work. I’m thinking less personal assistant and more helpful colleague.

Here’s a short demo video: https://www.loom.com/share/00d11bdbe804478e8817710f5f53ac61

The main interface is a web app where you can watch work happen in real time (agents spawning, files being written, use of the CLI). There's also an iMessage integration so you can fire a task asynchronously, put your phone down, and get a reply when it's finished.

Under the hood, there's an orchestrator (Claude Opus 4.6) that routes to the right domain-specific model for each subtask: browsing, coding, research, and media generation.

For complex tasks it spins up parallel sub-agents that coordinate through the shared filesystem. They have persistent memory across sessions so context compounds over time.

I’ve packaged it with a bunch of pre-installed skills so it can execute in a variety of job roles (sales, marketing, finance) at runtime.

Here are a few things Eve has helped me with in the last couple days:

- Edit this demo video with a voice over of Garry: https://www.youtube.com/watch?v=S4oD7H3cAQ0

- Do my tax returns

- To build HN as if it was the year 2030: https://api.eve.new/api/sites/hackernews-2030/#/

AMA on the architecture and lmk your thoughts :)

P.S. I've given every new user $100 worth of credits to try it.

Boom, eve got Doom running for me on my VM and even spun up a public site

https://api.eve.new/api/sites/eve-doom/

Just gave this a try and I really like it. Was able to interact with Eve via iMessage and web UI to download a sample healthcare dataset and run some analyses on it. (Currently it's a bit unpredictable about which UI it returns results to, but if that gets fixed then this would be great for doing development on the move.) Also set it up to run some scheduled news summarisation tasks. I like how it allows for safe experimentation on OpenClaw functionality. Like others on this thread, I'm a bit hesitant about connecting to email services without knowing more about the developer and how they use data from connected services, but there's a lot of interesting things you can do with this even without connecting to anything. (The free credits are v helpful too, although the underlying Claude models burn through them quickly.) Thanks zachdive for sharing this, I had fun trying it out!

It's very telling of the current state of this industry that OP comes only 2 h after this other post: https://news.ycombinator.com/item?id=47721955

Let me just log into this random site with my Google account with literally zero information about what it is

“All .new domain names are required to comply with the .new Registration Policy, which features a usage-based restriction to ensure that all domains are being used for new actions. That means that all .new domains registrations must: Be used for action generation or online content creation; Take the user directly into the action generation or content creation flow; Resolve to the action within 100 days of registration;* and Allow Google Registry to verify compliance at no cost. While anyone can register, domains that don’t comply with this usage policy may be suspended or deleted by Google Registry without refund. So be sure you review the full .new Registration Policy before you register your .new domain to ensure that it meets our policy requirements.”