Microsoft Opens GitHub Copilot Agent Harness to Developers via Foundry

Microsoft is opening up the GitHub Copilot agent harness to outside developers through Microsoft Foundry, bringing the same orchestration infrastructure used across its Copilot products into a managed service for building and deploying autonomous agents. Announced Wednesday, the harness is now available in public preview through Foundry Agent Service and includes built-in sandboxing, reusable skills, MCP integrations, and support for subagents. Microsoft runs the agent and manages its execution environment, while developers choose a supported model and configure instructions and tools.

What the managed harness includes

Microsoft's harness manages model and tool calls, tracks context, and keeps agents within configured policies. Skills can package instructions, scripts, and supporting resources, while MCP integrations require authentication and approval. Agents can also work with files, run code, and delegate tasks to subagents, with the main agent coordinating results. The same harness now supports Copilot Code, Copilot Studio, GitHub Copilot, the CLI, and VS Code.

How developers deploy agents

The company's technical walkthrough shows a research agent. A Markdown-based skill lays out steps for collecting evidence, analyzing data, and writing a report, while an azure.yaml file defines the model deployment, tools, instructions, and harness. Developers select microsoft_copilot_preview as the harness type, deploy the agent using azd deploy --all, and invoke it through the Azure Developer CLI. They can keep agent configurations and supporting files in source control.

Runtime limits and lock-in

The Copilot harness must be selected when creating a prompt agent, and that choice cannot be changed later, even in a new version. Microsoft also controls how much CPU and memory the agent gets and how long it can sit idle. Developers can decide what their agents do, but have less control over the environment they run in. Microsoft positions its broader harness strategy as multi-model, though developers can choose only compatible models deployed through Foundry, and bringing their own models is not supported with the managed Copilot harness. Teams that want more control can use Foundry's hosted agents instead, building and running agents with their own frameworks while Microsoft handles hosting. Microsoft also announced general availability of long-running resilience for hosted agents, helping them recover from interruptions during tasks that take hours or even days.

Pricing and availability

The Copilot harness in Foundry Agent Service is free until December 1, 2026, although model inference and some tools and connected services still carry separate charges. After that, Microsoft will charge $0.0994 per vCPU-hour for compute and $0.0118 per GiB-hour for memory. Those rates may vary depending on region and customer agreement.

Sources: The New Stack