YOLO Mode Your code agent is more powerful when it's free to run wild
Spin up a Sprite, run your AI agent, and let it do its thing while you make lunch.
Root access for AI—minus the anxiety
Let Claude flex its abilities by giving it the permissions to get wild. Because Sprites are hardware isolated environments with checkpoint and restore, you can develop with confidence while letting your AI agent take the wheel.
Self-driving AI agents
Not only are multiple AI coding agents preinstalled on Sprites, they're also aware of Sprites and what they can do. For this reason, you can do anything inside your coding agent. Want it to spin up other Sprites? Just ask Claude. Want to rollback to a checkpoint? Just ask Claude.
Durable storage for days
Sprites come with 100GB of durable storage. That's a lot of space to let Claude go nuts. Best of all? Everything is synced to object storage. Your whole freaking VM.
curl https://sprites.dev/install.sh | bash
sprite create yolo-bot
claude "build me a web app and deploy it"
exit
- Disposable Compute
- Sprites get VMs when they need them. Fire one up, do some work, forget about it for 6 months. We make sure it gets compute when you come back.
- Firecracker VMs
- Sprites execute code in Firecracker VMs. Even we have a hard time seeing what they're doing.
- Isolated Networking
- VMs run on isolated networks. Nothing can connect to your Sprite directly.
- Dynamic Resources
- Sprite VMs have access to big chunks of CPU and Memory. Your blobs of code just use what they need, up to 8 CPUs and 16GB of RAM for any given run.
Billing
You pay only for Storage and compute resources while a Sprite is active. Usage is aggregated across your organization.
CPU Time
Minimum 0.0625 CPU while running.
Memory Time
Minimum 256MB RAM while running.
Storage
Prorated to the hour. 1,000 sprites using 10MB data = 10GB total.
All compute resources are billed per second. Storage is billed hourly but aggregated monthly.