Overview
Daytona is a secure, elastic platform for running AI-generated code inside isolated sandboxes. It emphasizes security by providing separated runtimes and sandboxed execution to prevent any impact on your infrastructure. Sandboxes can be created in sub-90 milliseconds and can run with any OCI/Docker image, enabling you to bring your own runtime. The platform offers programmatic control through Python and TypeScript SDKs, exposing capabilities to manage files, Git, Language Server Protocol (LSP) interactions, and code execution via an Execute API. Sandboxes can be persisted indefinitely, supporting long-running experiments, and are designed to scale with workloads. A future enhancement promises massive parallelization by forking sandbox filesystem and memory state to support concurrent AI workflows. To begin, developers create an account and API key and follow the Getting Started docs. Daytona focuses on security, isolation, and elastic infrastructure, enabling teams to iterate quickly on AI workloads while keeping production systems protected.
Features
Lightning-Fast Infrastructure
Sub-90ms Sandbox creation from code to execution.
Separated & Isolated Runtime
Execute AI-generated code with zero risk to your infrastructure.
Massive Parallelization for Concurrent AI Workflows
Fork Sandbox filesystem and memory state (Coming soon!).
Programmatic Control
File, Git, LSP, and Execute API.
Unlimited Persistence
Your Sandboxes can live forever.
OCI/Docker Compatibility
Use any OCI/Docker image to create a Sandbox.
Who Is This For?
- Developers:Use API and SDKs to securely run AI code in isolated sandboxes.
- Data scientists:Experiment with AI-generated code while maintaining production isolation and reproducibility.
- DevOps:Orchestrate secure execution of AI tasks with programmable controls across environments.
