Runta Documentation
Runta is execution layer for AI agents.
Runta Execution Layer
Agent / Framework
RuntaControlled execution boundary
StateCheckpoint · Resume · Audit Trail
ControlCredentials · Egress · Usage
RuntimeIsolated runtime · Auto scaling · Idle suspend
Database
Services
Repos
APIs
Onboarding
Section titled “Onboarding” Getting Started Create an account, get a token, install tools, and start your first runtime.
Egress Restrict outbound access and review allowed or denied requests.
Auto Suspend and Wake-up Suspend idle runtimes and wake published runtimes when traffic returns.
Declarative Config Manage runtimes with repeatable configuration files.
OpenAI agents sdk Run OpenAI agents sdk workloads inside Runta runtimes.
Harbor Use Harbor workflows with Runta runtime isolation.
Reference
Section titled “Reference” Runtime Basic Create, execute commands in, resize, pause, resume, stop, and delete runtimes.
Files Copy, upload, download, read, and write files in a runtime.
CLI Reference Commands, flags, configuration, lifecycle, secrets, egress, checkpoints, and TLS.
SDK Reference Python and TypeScript interfaces for runtimes, files, egress, secrets, and checkpoints.
REST API Reference Generated API docs for runtimes, exec, checkpoints, files, audits, and secrets.
Billing Model Usage, limits, and billing behavior.