Skip to content

Runtime Basics

A Runta runtime is an isolated environment for AI agents. It gives agents a place to execute commands, use tools, read and write files, and keep task state while still giving you control over LLM token usage, secrets and network access.

Terminal window
export RUNTA_TOKEN=rt...

Create a runtime with explicit CPU and memory requests:

Terminal window
runta run --name demo --cpus 2 --memory 2048
Terminal window
runta ps -a
runta inspect demo

Commands are buffered: the API returns exit code, stdout, stderr, duration, and truncation flags.

Terminal window
runta exec demo -- sh -lc 'pwd && python3 --version' # one-shot session
runta exec -it demo bash # interactive session

Use runta exec -it demo bash for an interactive session, or use the Runta web terminal.

Runta supports memory resizing while a runtime is running:

Terminal window
runta resize --memory 4096 demo

Lifecycle calls change runtime state without deleting the runtime record, except for delete, which permanently removes it.

Use the Runta CLI for terminal workflows, shell scripts, and direct runtime operations.

TaskCLI command
Boot a stopped runtime runta boot demo
Pause a running runtime runta pause demo
Resume a paused runtime runta resume demo
Shut down a runtime runta shutdown demo
Delete a runtime runta rm demo