Docker, Inc

Modern software has a lot of dependencies. And agents are now choosing them autonomously, connecting to tools across every team, and running on machines that can reach production. Mark Lechner (Docker CISO) says the starting point is simple: limit the blast radius. Watch the full panel episode where Mark Lechner joins Zach Lloyd (Warp), Gavriel Cohen (NanoClaw), and Moriah Hara (CISO Next Gen) on what that looks like in practice, from supply chain trust to credential exposure to what governed autonomous execution actually requires. → https://lnkd.in/gjydtD8Y

Every developer's workflow is different. So why should every development environment be the same? Reynald Adolphe walks through how to customize Docker Sandboxes with Kits: one YAML file that installs your tools, sets your environment variables, shares configuration files, and handles network rules. Define it once, apply it every time you spin up a sandbox. The demo also covers how to use Docker Sandboxes in the IDEs you already use (VSCode, Cursor, and more). Watch here → https://lnkd.in/eRcCgZ2h

MCP servers are easy to connect, but harder to govern at scale. Join Mark Maxwell, MBA, CISSP, CRISC's lightning talk at WeAreDevelopers to see how managed MCP access and sandboxed execution can give developers a safer path to agentic tooling. If your team is connecting agents to tools, this talk offers a clear view of the attack surface and practical ways to reduce risk. September 23-25 in San Jose. Co-hosted by Docker - find us at Booth # 101. Build what’s /next. Tickets: https://lnkd.in/duyFhgtm

With WeAreDevelopers North America just around the corner and agent sandboxes at the center of so many conversations right now, this episode of Ship Happens feels especially relevant. Per Ploug Krogslund sits down with Vasek Mlejnsky, founder of E2B, to talk about what it actually takes to build cloud sandboxes for AI agents, why the infrastructure patterns look almost orthogonal to everything we've built over the last 20 years, and why losing startups as customers means losing the edge of what's possible. Watch here → https://lnkd.in/gV4Yai9p

Docker CISO Mark Lechner will present at WeAreDevelopers North America, co-hosted by Docker. The line between a supply chain attack and an AI attack no longer exists. Agents build with whatever they find, and the controls in the stack you use were built for a review process that can no longer keep pace. In his talk, 'One Boundary for the Agentic Era,' Mark will show how one boundary, drawn where agents do their work, fixes both problems. Inside it, agents build from a secure foundation and run in isolated execution, and your teams get controls they can verify, down to what each agent can reach and what it does. September 23-25 in San Jose. Build what's /next. Session details: https://bit.ly/4x7oCJC

AI agents don't check where their dependencies come from. They pull whatever works. That makes your registry choice matter, a lot. Docker Hub is the one stop shop for container images. But if you look closer -Hub now covers MCP servers, models, hardened content, all from one trusted source. Daniel (Dan) S. will walk through what that means for your supply chain in his lightning talk at WeAreDevelopers World Congress North America. If you're responsible for what your developers and their agents pull, and from where, come see what governed distribution looks like in practice. September 23-25 in San Jose, co-hosted by Docker. Find us at Booth # 101. Build what's /next. Tickets: https://lnkd.in/duyFhgtm

A container, a seatbelt, a microVM. They're not the same boundary. Mike Coleman's lightning talk at WeAreDevelopers North America breaks down what each one protects against. He goes into where the known bypasses are, and who owns the policy: you or your vendor. If you're not sure your agent boundary will hold when something goes wrong, this talk gives you the framework to find out. September 23-25 in San Jose, co-hosted by Docker. Find us at Booth #101. Build what's /next. Tickets: https://bit.ly/4e7b7nD

Most AI evaluation discussions focus on benchmarks and scoring. The part that quietly breaks reproducibility is the execution environment. Docker Captain Karan Verma explored whether Docker Sandboxes and SBX Kits could make evaluation workflows easier to rerun, inspect, and compare. That question evolved into building the SBX AI Evaluation Kit, an open-source Mixin Kit focused on repeatable execution and structured evaluation records. Read more:

Docker CTO Tushar Jain will speak at WeAreDevelopers North America, co-hosted by Docker. In this main stage talk, Tushar will talk about how to govern the runtime, not the agent. He will build the case for a runtime below all your agents: the layer below all your harnesses, covering agent execution, tool calls, credential usage, and scoped permissions. This session will show you how to get control and visibility into all your agents, no matter the underlying model or harness. September 23-25 in San Jose. Build what's /next. https://bit.ly/4gAFLqe

Most developers running coding agents in YOLO mode have no idea what the agent can actually reach. Product Manager Eric Jia and Staff Software Engineer Kevin Wittek built Docker Sandboxes. In this demo, they walk through exactly how to use them to set up the boundary your agents actually need. The demo covers credential injection, kits, how sandboxes are different from containers, and a brand new SSH feature that lets you use Claude Desktop and VS Code with full sandbox isolation underneath. Watch the full video → https://lnkd.in/eXKXuU3N