YOLO Mode: Agent Autonomy Without the Guardrails
YOLO mode lets an AI agent run without asking permission. Learn what it is, why it's risky, and how to run it safely.
Stories from Docker
Use this page to scan recent stories from Docker, see the themes that keep appearing, and jump into complete story briefs.
Recurring themes in this source.
ProductsAgentic AIConceptsDocker AI GovernanceDocker SandboxessecurityCompanyAI/MLCommunityAI AgentGenAIEnterpriseSolutionsDocker Hardened Images
Recent curated reads
Below the Harness: Governing a Multi-Model, Multi-Harness World
We believe the future is a multi-model, multi-harness world. And we think it needs a new trust model. In 1988, Norm Hardy described a problem that had been quietly breaking systems for years: the confused deputy. A program that takes action using its permissions instead of yours. Today, every AI agent is that deputy. I
Building Reproducible AI Evaluation Workflows with Docker Sandboxes
Learn how Docker Sandboxes can make AI evaluation workflows more reproducible with consistent execution, structured artifacts, and runtime evidence.
Secure by default is your only way forward
The newest worker on your team builds with whatever it finds and never asks what deserves your trust. Our answer is a hardened foundation and a boundary built for agents.
Moving from Minimus to Docker Hardened Images
The Minimus registry goes offline on October 22. Here is the migration path, the free help Docker is offering, and where to start.
Running AI agents in GitHub Actions with Docker Sandboxes
Run AI agents in GitHub Actions with Docker Sandboxes. See how isolated agents can run Testcontainers tests, fix code, and open draft pull requests.
Coding Agent Horror Stories: The Command You Already Approved
Learn how AI coding agents can run attacker code through commands you already approved and how Docker Sandboxes limit what an attack can reach.
Docker Verified Publisher Applications Are Now Self-Serve
Apply to become a Docker Verified Publisher (DVP) now directly through Docker Hub. Get your verified content seen first by devs looking for trusted options.
17,600 Actions: Agent Security Is a Systems Problem
The OpenAI/Hugging Face incident exposed a new challenge for AI agent security. 17,600 attacker actions show why AI agent security can’t rely on human review. Explore the controls needed to constrain, observe, and govern agents at speed.
Make zero CVEs your new default
Supply-chain attacks have kept escalating while AI writes more of the code you ship. Docker's latest updates bring more software built from source into your images, keep security coverage running past end of life, carry every guarantee through your customized images, and move policy enforcement onto every developer mac
Docker VMM Public Beta: A Complete Overhaul, Built for Performance
Docker VMM is now available in public beta for Mac and Windows. Learn what this means for performance, stability, and governance and how to try it yourself.
MinIO End of Life: How to Stay Patched and Audit-Ready with Docker ELS
Supply-chain attacks have kept escalating while AI writes more of the code you ship. Docker's latest updates bring more software built from source into your images, keep security coverage running past end of life, carry every guarantee through your customized images, and move policy enforcement onto every developer mac
Read this source in the app
Open the app view when you want faster scanning, saved stories, and source-focused reading in one place.