The DropApril 6, 2026via Hacker News
Launch HN: Freestyle: Sandboxes for AI Coding Agents
Why it matters
Freestyle is addressing a critical infrastructure gap for AI agents: they need full compute environments that rival human developer setups but provision in seconds. By building bare metal infrastructure, they're enabling the next generation of coding agents to handle complex, stateful tasks that serverless platforms can't support.
Key signals
- 400ms horizontal sandbox fork with full memory preservation
- ~500ms sandbox startup time
- Full Linux + hardware virtualization support (eBPF, Fuse, systemd)
- Bare metal infrastructure investment to avoid AWS/GCP bare metal monthly cost premium
- Targets multi-tenant AI agent infrastructure at scale
- YC-backed (Launch HN post)
The hook
Not a pilot. Freestyle just launched sandboxes that fork full VM memory in 400ms—purpose-built for AI coding agents at scale.
We’re Ben and Jacob, cofounders of Freestyle (https://freestyle.sh). We’re building a cloud for Coding Agents.
For the first generation of agents it looked like workflows with minimal tools. 2 years ago we published a package to let AI work in SQL, at that time GPT-4 could write simple scripts. Soon after the first AI App Builders started using AI to make whole websites; we supported that with a serverless deploy system.
But the current generation is going much further, instead of minimal tools and basic serverless apps AI can utilize the full power of a computer (“sandbox”). We’re building sandboxes that are interchangeable with EC2s from your agents perspective, with bonus features:
1. We’ve figured out how to fork a sandbox horizontally without more than a 400ms pause in it. That's not forking the filesystem, we mean forking the whole memory of it. If you’re half way down a browser page with animations running, they’ll be in the same place in all the forks. If you’re running a minecraft server every block and player will be in the same place on the forks. If you’re running a local environment and an error comes up in process that error will be there in all the forks. This works for snapshotting as well, you can save your place and come back weeks later.
2. Our sandboxes start in ~500ms.
Demo: https://www.loom.com/share/8b3d294d515442f296aecde1f42f5524
Compared with other sandboxes, our goal is to be the most powerful. We support full Linux + hardware-virtualization, eBPF, Fuse, etc. We run full Debian with multiple users and we use a systemd init instead of runc. Whatever your AI expects to work on debian should work on these vms, and if it doesn’t send a bug report.
In order to make this possible, we’ve moved to our own bare metal racks. Early in our testing we realized that moving VMs across cloud nodes would not have acceptable performance properties. We asked Google Cloud and AWS for a quote on their bare metal nodes and found that the monthly cost was equiv...
Relevance score:82/100