Nov 6
Docker Sandboxes vs. Containers: Choosing the Right Isolation for AI Agents
A container shares the host kernel. Docker Sandboxes are microVMs with their own kernel and private Docker Engine. See how they differ and when to use each.
Docker · Company blog · 11 a month · 27 posts since Aug 31, 2026
Nov 6
A container shares the host kernel. Docker Sandboxes are microVMs with their own kernel and private Docker Engine. See how they differ and when to use each.
Nov 5
See how CNCF Score improved container security with Docker Scout, Hardened Images, and the Docker-Sponsored Open Source Program.
Nov 5
Docker partners with ActiveState to continue to provide one standard for trusted content across everything you and your teams build on.
Nov 2
Docker Sandboxes support three ways to organize an agent’s code: shared mounts, Git worktrees, and clone mode. Here’s how to choose between them.
Nov 2
Docker is a founding member of the Blueprint Alliance, a 12-company reference architecture for securing AI agents, built around four governance questions.
Oct 29
An AI code review agent invented a CVE and recommended dangerous fixes. Learn how Docker Sandboxes contain agents and why their output needs verification.
Oct 28
Docker is launching the Navigator Partner Program, with three tiers, co-selling benefits, and a new incentive for every registered AI governance deal.
Oct 23
PHP2Shell and the eMudhra certificate compromise landed in the same week. Docker published a fixed PHP image within 24 hours and rebuilt the trust store across the catalog.
Oct 22
Container security spans the image, build, and runtime. See the practical steps that shrink your attack surface and keep vulnerabilities out of production.
Oct 22
On Tuesday, October 20, 2026, Docker began tracking two critical vulnerabilities in PHP, CVE-2026-109618 and CVE-2026-109619, commonly known as PHP2Shell.
Oct 21
In July, Docker, Snyk and Keycard published Agent Baseline, an open, vendor-neutral reference architecture that defines security outcomes for running AI agents in the enterprise.
Oct 21
Run AI agents in Docker Sandboxes with BAND AI. Learn how to connect isolated agents, collaborate across environments, and manage access securely.
Oct 16
The 2026 Stack Overflow Developer Survey shows only 7% of developers trust AI output for important decisions. Here’s what that means for running agents safely.
Oct 14
Harbor can now run every eval task in Docker Sandboxes Docker Sandboxes are MicroVM environments to run agents like Claude Code, Codex, Cursor, and more safely With Sandboxes, define custom network policies for fair, reproducible evals Run...
Oct 14
Learn the top AI agent security risks, from prompt injection to excessive autonomy and credential exposure, and how to contain them.
Oct 12
CVE-2026-105445: Docker Hub account conversion could re-assign personal access tokens to a new owner. Read what happened, who was affected, and the fix.
Oct 1
At WeAreDevelopers, Docker introduced Cloud Sandboxes, the open Sandbox Kit specification, and a commitment to bring Kits to the CNCF for neutral governance.
Sep 24
Run agents on your laptop, in the cloud, and move between them with one command, all safely. Earlier this year we launched Docker Sandboxes: microVM environments where coding agents can work autonomously in a safe way.
Sep 24
Docker is bringing the open source Sandbox Kit Spec to the CNCF, so AI agent permissions become a neutral, vendor independent standard built on OCI.
Sep 24
Docker's Sandbox Kit Specification v3 packages an AI agent's network rules, credentials, and volumes as an ordinary, pinnable OCI image.
Sep 24
Docker's WeAreDevelopers keynote shows how Sandboxes, Kits, and Cloud Sandboxes give AI agents strong isolation and reproducible authority.
Sep 22
Meet the partners and customers bringing practical AI, security, and development sessions to the Docker Pavilion at WeAreDevelopers.
Sep 8
Learn about the key benefits of sandbox environments with Docker including isolation, definable controls, secrets credential handling, and more.
Sep 3
YOLO mode lets an AI agent run without asking permission. Learn what it is, why it's risky, and how to run it safely.
Sep 2
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.
Docker's own blog on docker.com, found by the daily check.
AI and agents (12), Security (7), Infrastructure (3) in the last six months.
Across Glyph:advisories·openperks·problems·Changefeed·socials·standards·startups
Listed on Blogs Sep 27, 2026. No changes to its feed, status or cadence since.