ERA

I am not working on web or server stuff. I'm building a better primitive for infrastructure via microvm's (think virtual machine but fast and easy to use). I am about to launch a complete rewrite of this: https://github.com/BinSquare/ERA

It will be possible to run from a node SDK soonTM! Here's the work-in-progress here: https://github.com/BinSquare/ERA/tree/main/era-agent/sdk/nod... I'm not very familiar with node to be fair so it's taking a little longer for me to get that going.

Krunvm has some breaking issues that I'm trying to upstream fixes to: https://github.com/containers/krunvm/pull/74. Amazing project and maintainer btw. This product is effectively wrapper that has some fixes + devX glue that makes the experience hopefully faster. I try to improve the cleanup, logging, resources monitoring as an example: https://github.com/BinSquare/ERA/blob/main/era-agent/vm_serv... The recipes and skills stuff is pretty experimental, we're trying to see if we can make this a full environment where agents can just have all the tools they need to build along with full privilege (sudo) because it's inside a microvm!

Just watched this video by ThePrimeagen (https://www.youtube.com/watch?v=efwDZw7l2Nk) about attackers jailbreaking Claude to run cyber attacks. The core issue: AI agents need isolation. We built ERA to fix this – local microVM-based sandboxing for AI-generated code with hardware-level security. Think containers, but safer. Such attacks wouldn't touch your host if running in ERA. GitHub: https://github.com/BinSquare/ERA Quick start: https://github.com/BinSquare/ERA/tree/main/era-agent/tutoria... Would love your thoughts and feedback!

I built a sandbox geared for safe ai code executions using microvm's that works locally (mac + linux). It's meant to be a different/more secure approach compare to what Claude's doing with their sandboxing runtime: https://code.claude.com/docs/en/sandboxing. Instead of relying on linux + Mac's technology for containerization, this project spins up a completely virtual environment on a separated kernel for better security.

AI agents are all the rage right now and I’ve been wanting to test running AI-generated code locally. But most “agent runtimes” today are actually just running Docker locally or ask for my credit card if I want to test untrusted “agents” on their cloud-managed solution. I built ERA with some hackathon friends — an open-source secure runtime that launches microVMs to execute code with true isolation. Some add-ons because we need it: we’ve got persistent storage and multi-language support as long as there’s a Docker image for it (we packed it with Python, Node, Ruby, Go, etc.). Under the hood we use krunvm + Buildah to boot microVMs that behave like single-process containers with VM-grade isolation. Under THAT hood, it’s using libkrun which powers Firecracker. Open Source: https://github.com/BinSquare/ERA/ Docs + Quickstart + Waitlist for E