Skip to content

Add "Running Agents on Kubernetes with Agent Sandbox" blogpost#54927

Merged
k8s-ci-robot merged 5 commits intokubernetes:mainfrom
janetkuo:agent-sandbox-blog
Mar 19, 2026
Merged

Add "Running Agents on Kubernetes with Agent Sandbox" blogpost#54927
k8s-ci-robot merged 5 commits intokubernetes:mainfrom
janetkuo:agent-sandbox-blog

Conversation

@janetkuo
Copy link
Copy Markdown
Member

Partnering with @justinsb

@k8s-ci-robot k8s-ci-robot added the cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. label Mar 16, 2026
@k8s-ci-robot k8s-ci-robot added area/blog Issues or PRs related to the Kubernetes Blog subproject language/en Issues or PRs related to English language size/M Denotes a PR that changes 30-99 lines, ignoring generated files. labels Mar 16, 2026
@netlify
Copy link
Copy Markdown

netlify Bot commented Mar 16, 2026

Pull request preview available for checking

Built without sensitive environment variables

Name Link
🔨 Latest commit 6aaf05d
🔍 Latest deploy log https://app.netlify.com/projects/kubernetes-io-main-staging/deploys/69baedee528c01000878e839
😎 Deploy Preview https://deploy-preview-54927--kubernetes-io-main-staging.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify project configuration.

Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
@janetkuo
Copy link
Copy Markdown
Member Author

@bexxmodd thanks for the feedback! Would you take another look?

@janetkuo
Copy link
Copy Markdown
Member Author

@lmktfy @nate-double-u this is ready for doc review. PTAL

Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Copy link
Copy Markdown
Member

@lmktfy lmktfy left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the PR. Here's a review on the content.

Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
Comment thread content/en/blog/_posts/2026/agent-sandbox.md Outdated
@janetkuo janetkuo force-pushed the agent-sandbox-blog branch from 530b09d to bcaddf2 Compare March 18, 2026 18:00
@janetkuo
Copy link
Copy Markdown
Member Author

@lmktfy thanks for the review! I've addressed all the feedback. PTAL

Copy link
Copy Markdown
Member

@lmktfy lmktfy left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

/lgtm
/approve
/hold

Remaining feedback can be addressed post-merge.

Ok to uphold at will.


The landscape of artificial intelligence is undergoing a massive architectural shift. In the early days of generative AI, interacting with a model was often treated as a transient, stateless function call: a request that spun up, executed for perhaps 50 milliseconds, and terminated.

Today, we are witnessing AI v2 eating AI v1. We are moving from short-lived, isolated tasks to deploying multiple, coordinated AI agents that run constantly. These autonomous agents need to maintain context, use external tools, write and execute code, and communicate with one another over extended periods.
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
Today, we are witnessing AI v2 eating AI v1. We are moving from short-lived, isolated tasks to deploying multiple, coordinated AI agents that run constantly. These autonomous agents need to maintain context, use external tools, write and execute code, and communicate with one another over extended periods.
Today, the world is witnessing AI v2 eating AI v1. The ecosystem is moving from short-lived, isolated tasks to deploying multiple, coordinated AI agents that run constantly. These autonomous agents need to maintain context, use external tools, write and execute code, and communicate with one another over extended periods.

(nit)
Nice to fix this use of "we" but not essential.


Whether it’s a 50-millisecond stateless task, or a multi-week, mostly-idle collaborative process, extending Kubernetes with primitives designed specifically for isolated stateful singletons allows us to leverage all the robust benefits of the cloud-native ecosystem.

The Agent Sandbox project is open source and community-driven. If you are building AI platforms, developing agentic frameworks, or are interested in Kubernetes extensibility, we invite you to get involved:
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Using "we" here is fine BTW.


To bridge this gap, SIG Apps is developing [agent-sandbox](https://github.com/kubernetes-sigs/agent-sandbox). The project introduces a declarative, standardized API specifically tailored for singleton, stateful workloads like AI agent runtimes.

At its core, the project introduces the `Sandbox` CRD. It acts as a lightweight, single-container environment built entirely on Kubernetes primitives, offering:
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
At its core, the project introduces the `Sandbox` CRD. It acts as a lightweight, single-container environment built entirely on Kubernetes primitives, offering:
At its core, the project introduces the Sandbox CRD. It acts as a lightweight, single-container environment built entirely on Kubernetes primitives, offering:

We can delete the backticks after publication, but before is even better (we don't use them around API types).


Because the AI space is moving incredibly quickly, we built an Extensions API layer that enables even faster iteration and development.

Starting a new pod adds about a second of overhead. That's perfectly fine when deploying a new version of a microservice, but when an agent is invoked after being idle, a one-second cold start breaks the continuity of the interaction. It forces the user or the orchestrating service to wait for the environment to provision before the model can even begin to think or act. `SandboxWarmPool` solves this by maintaining a pool of pre-provisioned Sandbox pods, effectively eliminating cold starts. Users or orchestration services can simply issue a `SandboxClaim` against a `SandboxTemplate`, and the controller immediately hands over a pre-warmed, fully isolated environment to the agent.
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If these are API types, drop the backticks. Especially for formal launches and similar announcements, following the style guide aims to help people build a good metal model of all our jargon.

On the other hand, field names (eg generateName) are written with the same case that they have within a manifest, and do go inside backticks.

@k8s-ci-robot k8s-ci-robot added the do-not-merge/hold Indicates that a PR should not merge because someone has issued a /hold command. label Mar 19, 2026
@k8s-ci-robot k8s-ci-robot added the lgtm "Looks good to me", indicates that a PR is ready to be merged. label Mar 19, 2026
@k8s-ci-robot
Copy link
Copy Markdown
Contributor

LGTM label has been added.

DetailsGit tree hash: a036d7f05eedb13781dc0d56b805e5cb521f0df2

@k8s-ci-robot
Copy link
Copy Markdown
Contributor

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: bexxmodd, lmktfy

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Details Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@k8s-ci-robot k8s-ci-robot added the approved Indicates a PR has been approved by an approver from all required OWNERS files. label Mar 19, 2026
@janetkuo
Copy link
Copy Markdown
Member Author

/unhold

@k8s-ci-robot k8s-ci-robot removed the do-not-merge/hold Indicates that a PR should not merge because someone has issued a /hold command. label Mar 19, 2026
@k8s-ci-robot k8s-ci-robot merged commit df4aff0 into kubernetes:main Mar 19, 2026
6 checks passed
@janetkuo
Copy link
Copy Markdown
Member Author

Addressing nits in #54962

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

approved Indicates a PR has been approved by an approver from all required OWNERS files. area/blog Issues or PRs related to the Kubernetes Blog subproject cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. language/en Issues or PRs related to English language lgtm "Looks good to me", indicates that a PR is ready to be merged. size/M Denotes a PR that changes 30-99 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants