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.
Docker Blog Articles
Updated 6 min ago · 10 articles from Docker Blog
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.
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 q...
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 buil...
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.
MinIO End of Life: How to Stay Patched and Audit-Ready with Docker ELS
MinIO reached end of life in February 2026. Docker Extended Lifecycle Support (ELS) keeps end-of-life software like it patched, compliant, and audit-ready fo...
Ad
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.
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...
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.
