Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

ax

ax: A declarative orchestrator for running autonomous agent workloads in a cluster.

What problem it solves

Autonomous agents accumulate state, require strict isolation, call model APIs and tool servers, and can continue consuming resources without supervision. AX addresses these requirements through declarative primitives for sandboxed execution, prepared workspaces, model configuration, lifecycle control, and direct inspection.

Key features

  • Declarative task manifests — Tasks, workspaces, and models are declared through YAML manifests and managed through a kubectl-shaped CLI.

    Source: README

  • Isolated sandboxed execution — Tasks run as sandboxed actors with isolation and CPU and memory limits.

    Source: README

  • Prepared workspaces — Workspaces pre-wire Git repositories, MCP servers, and skill packages so agents begin with their required resources configured.

    Source: README

  • Lifecycle checkpointing — Operators can suspend an agent, preserve its state, and resume it from the point where it stopped.

    Source: README

  • Interactive task inspection — The CLI can open a shell in a running sandbox so operators can inspect the agent's workspace and activity.

    Source: README

Quick start

Copied verbatim from the project's README.

go install github.com/google/ax/cmd/ax@latest
export AX_IMAGE_REPO=<your-registry>   # e.g. gcr.io/my-project
make images
make deploy

Who it may suit

Inference: This project may suit platform engineers and agent developers who need to operate autonomous workloads in Kubernetes clusters with declarative configuration, sandbox isolation, and lifecycle controls.

Topics to discuss

  • Which manifest and workspace abstractions should be standardized for agent orchestration?

  • How should teams observe and control long-running autonomous agent workloads?

  • What should the stable lifecycle, checkpointing, and sandboxing specifications include?


Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/google/ax#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/google/ax

Comments

…