CPU Sandbox Now Available in Beta Telnyx released CPU Sandbox in beta as part of its Agent Platform, giving AI agents an isolated, programmable computer to run code, install tools and carry out multi-step work without executing that code in the application environment. Agents on Telnyx Edge Compute create a sandbox on demand via the telnyx-edge CLI — for example `telnyx-edge sandbox-cpu create --image docker.io/library/python:3.12-slim --name doc-quick-start --timeout 1800` — then exec, pause, resume and terminate it, so failed code runs isolated from the agent's runtime, memory and credentials. The beta requires a Sandbox-enabled account and the telnyx-edge CLI, with an API call available for every step. CPU Sandbox gives an AI agent an isolated, programmable computer for running code, installing tools and carrying out multi-step work, without running that code directly in your application environment. It is part of the Telnyx Agent Platform and is in beta. Models can generate code. Running it is the risky part. Your agent lives on Telnyx Edge Compute, always on and holding its memory and credentials. A Sandbox is a separate computer the agent creates on demand: install a library, open a file it did not write, run the script, return the result. Keep it available across tasks, and terminate it when it is no longer needed. If the code fails, it does so in an environment isolated from your agent's runtime. telnyx-edge sandbox-cpu create --image docker.io/library/python:3.12-slim --name doc-quick-start --timeout 1800 telnyx-edge sandbox-cpu exec doc-quick-start -- python3 /workspace/primes.py telnyx-edge sandbox-cpu pause doc-quick-start , telnyx-edge sandbox-cpu resume doc-quick-start , telnyx-edge sandbox-cpu terminate doc-quick-start You need a Sandbox-enabled account and the telnyx-edge CLI. Every step also has an API call in the quick start https://developers.telnyx.com/docs/edge-compute/sandboxes/quick-start . Read the CPU Sandbox docs https://developers.telnyx.com/docs/edge-compute/sandboxes .