The Polyaxon agent sandbox roadmap
Our plans for persistent sandbox workspaces, suspend/resume, activity-aware idle suspension, and ready pools on Kubernetes—and where AX and Substrate differ.
RoadmapSandboxesAI Agents
Latest articles
The latest guides, tutorials, and product updates.
Create and automate Polyaxon sandboxes from Python
Create a sandbox service with SandboxClient, choose its image, run Python, download the output, and stop the workspace from one Python script.
SandboxesPythonTutorials
Run background commands in Polyaxon sandboxes
Start a background process, save its execution ID, reconnect to status and logs, and distinguish command limits from the lifetime of a Polyaxon sandbox.
PolyaxonSandboxesPython
Orchestrate parallel coding agents with Polyaxon
Run parallel coding agents in separate Polyaxon workspaces, collect candidate patches, evaluate independently, and merge only reviewed changes.
AI AgentsSandboxesCollaboration
Set up a Polyaxon code execution workspace
Enable sandbox execution on a Polyaxon service, reuse its image and compute settings, run commands through the SDK, and preserve results before cleanup.
SandboxesPythonTutorials
Run a sandbox workflow from the Polyaxon CLI
Start a sandbox-enabled Polyaxon service, upload two files, run a command, download its result, and release the workspace from the CLI.
ProductCliSandboxes
What is an AI sandbox? Development environments and execution isolation
Understand AI sandboxes for development and agent execution, including runtime isolation, credentials, storage, network access, GPUs, and lifecycle.
SandboxesAI AgentsKubernetes
Make sandbox selection a platform decision
Evaluate sandbox selection as a Polyaxon platform decision covering execution contracts, identity, scheduling, state, evidence, and operational ownership.
Platform EngineeringSandboxesAI Agents
Configure Python sandboxes for untrusted LLM code
Configure Polyaxon Python sandbox services with minimal privileges, controlled writable paths, bounded resources, and separate handling of untrusted LLM code.
PythonSandboxesSecurity
Distinguish sandboxes, runtimes, and code interpreters
Distinguish the security boundary, process runtime, and interpreter session when designing Polyaxon code execution for AI agents.
SandboxesArchitectureAI Agents
Manage long-lived AI agent workspaces
Manage long-lived Polyaxon agent workspaces with explicit ownership, reproducible environments, checkpoints, bounded lifetimes, and safe replacement.
SandboxesAI AgentsOperations
Operate remote code execution with Polyaxon
Operate remote code execution through Polyaxon with explicit session ownership, command receipts, artifact collection, and safe retry decisions.
SandboxesAI AgentsOperations
Keep Polyaxon sandboxes ready with bounded lifetimes
Keep Polyaxon sandbox services ready for active sessions while controlling idle cost, absolute lifetime, state persistence, and cleanup.
SandboxesPerformanceOperations
Choose a code execution API for AI workflows
Compare code execution API shapes and implement clear request, result, cancellation, and artifact contracts for Polyaxon agent workflows.
AI AgentsAPISandboxes
Benchmark coding-agent sandboxes with Polyaxon
Benchmark coding-agent sandboxes with controlled workloads, reproducible Polyaxon runs, latency distributions, recovery scenarios, and quality-adjusted results.
SandboxesBenchmarksAI Agents
Evaluate security controls for AI sandbox platforms
Evaluate AI sandbox platforms using explicit security acceptance criteria, and map Polyaxon capabilities to application and Kubernetes controls.
SecuritySandboxesPlatform Engineering
Choose state lifetimes for AI agent workspaces
Choose appropriate lifetimes for agent process memory, sandbox files, persistent volumes, artifacts, and application state in Polyaxon.
AI AgentsStorageSandboxes
Connect agent tool calls to Polyaxon execution
Translate agent tool requests into authorized Polyaxon sandbox execution with bounded commands, structured results, and explicit lifecycle ownership.
AI AgentsSandboxesPython