Sandboxed code execution
Modal is flexible language for dynamically defining compute tasks and running them in a secure environment.
Get started
Define any part of your environment dynamically at runtime. Use LLM-generated responses to construct container images or hardware configurations.
Persist stateful data across sessions with dynamically-provisioned network file systems. Create ad-hoc volumes for returning data from your sandbox.
Orchestrate and run any kind of code or container image, even if it's not written in Python.
Rely on strict security and isolation guarantees from our gVisor-based runtime. Run untrusted code from language models or third-parties with confidence.
Try it out
“Using Modal, Codegen has been able to move at lightning speed with full-stack AI development. The product is designed with developer experience front and center, and my team is incredibly happy and productive having it as part of our arsenal.”
“Basis is an AI platform for accountants. We use Modal to securely run LLM-augmented code on a large scale. Modal’s powerful primitives like sandboxes and file systems have allowed us to focus on our core competencies without having to waste time rolling our own infrastructure.”