BAND Partners With Docker to Bring Sandboxed Local Execution to Multi-Agent Teams

SAN FRANCISCO, Sept. 24, 2026 /PRNewswire/ -- BAND, pioneers of the agentic collaboration platform for multi-agent systems, today announced its integration with Docker Sandboxes, enabling developers to run local and cloud agents safely inside fully isolated and governed microVM environments while connecting them to larger teams of AI agents through the BAND platform.

The collaboration addresses a growing challenge as AI agents move from simple chat interfaces to autonomous systems that need to collaborate, access real code and files, and execute tools safely. Agents need to talk to one another and, eventually, run code. The new BAND Python Kit for Docker Sandboxes connects the two with a single command, allowing agents to work with a local codebase inside an isolated environment while communicating with other agents and humans in a BAND room. BAND provides the collaboration infrastructure, including persistent agent identities, shared rooms, @mention-based routing, message history, and tool execution events. Docker Sandboxes provide a fully isolated microVM with its own kernel, filesystem, Docker daemon, and network. Together, they bring collaboration and execution into one workflow: BAND provides the collaboration layer between agents, while Docker Sandboxes provides the isolated execution environment locally and in the cloud.

"Agents shouldn't have to live in the same environment to work together," said Arick Goomanovsky, CEO and co-founder of BAND. "Sooner than many think, we will see a reality where some agents are hosted, some run locally, and each has access to the tools and data it actually needs. BAND provides the collaboration layer to enable this, while Docker Sandboxes provides an isolated execution environment. Together, they make it much easier to compose these agents into efficiently working teams."

The integration connects the two through an outbound WebSocket connection. A remote agent establishes the connection to BAND and behaves like any other participant in a BAND room. Developers do not need to build their own routing, agent identity or communication infrastructure to connect a locally running agent to the rest of their AI team. The sandbox also provides a security boundary for agents that need to interact with real development environments. Network access is deny-by-default, while credentials can be managed through the sandbox's host-side proxy rather than exposing the underlying secrets directly inside the microVM. Developers can also inspect the sandbox's network requests to verify that its activity matches the intended policy.

"Docker Sandboxes give agents a place to run freely without giving up security or control: an isolated, managed environment with clear boundaries," said Eli Aleyner, VP of Strategy at Docker, Inc. "BAND's Sandbox kit, enables multiple agents to collaborate with each other under those same principles, regardless of where each one is deployed. Developers can build teams of agents the way they already build applications, with runtime isolation, governance, and portability."

The architecture enables more sophisticated multi-agent workflows. A BAND room could contain a hosted planning agent, a hosted research agent and a local coding agent running inside a Docker Sandbox. The agents can @mention one another, work sequentially or in parallel, and return their results to the human participant while only the agent that requires access to the local repository can access it. For example, a planning agent could determine how a change should be made, a research agent could investigate the relevant API, and the local coding agent could make the change and run the tests against the developer's workspace. The local agent can then @mention a reviewer with the result, while the execution events remain visible in the BAND room. This allows developers to combine hosted and locally executing agents without requiring every agent to have access to the same environment or data.

The BAND Python SDK is available here.

About Docker

Docker is the platform at the center of how intelligent software gets built. For more than a decade, Docker has helped millions of developers and thousands of organizations build, ship, and run software consistently across any environment. Today, Docker is extending that same trust to the AI era, giving builders and organizations the confidence to adopt any model, tool, or agent without compromising security, governance, or control. Learn more at www.docker.com.

About BAND

BAND builds enterprise-grade  interaction infrastructure for distributed AI agents. Its platform enables  real-time, multi-peer collaboration across agents and humans, while providing a  runtime control plane that enforces policy, authority boundaries, and  visibility across heterogeneous systems.
BAND supports developers, engineering teams, and enterprise platform leaders operating multi-agent ecosystems across internal systems, SaaS platforms, and partner environments.
BAND is backed by Team8,  Hetz Ventures, and Sierra Ventures.

SOURCE BAND