The next evolution of the Agents SDK

The next evolution of the Agents SDK The updated Agents SDK helps developers build agents that can inspect files, run commands, edit code, and work on long-horizon tasks within controlled sandbox environments. We’re introducing new capabilities to the Agents SDK(opens in a new window) that give developers standardized infrastructure that is easy to get started with and is built correctly for OpenAI models: a model-native harness that lets agents work across files and tools on a computer, plus native sandbox execution for running that work safely. For example, developers can give an agent a controlled workspace, explicit instructions, and the tools it needs to inspect evidence: Developers need more than the best models to build useful agents—they need systems that support how agents inspect files, run commands, write code, and keep working across many steps. The systems that exist today come with tradeoffs as teams move from prototypes to production. Model-agnostic frameworks are flexible but do not fully utilize frontier models capabilities ; model-provider SDKs can be closer to the model but often lack enough visibility into the harness; and managed agent APIs can simplify deployment but constrain where agents run and how they access sensitive data. Here’s what some of the customers who tested the new SDK with us had to say: “The updated Agents SDK made it production-viable for us to automate a critical clinical records workflow that previous approaches couldn’t handle reliably enough. For us, the difference was not just extracting the right metadata, but correctly understanding the boundaries of each encounter in long, complex records. As a result, we can more quickly understand what's happening for each patient in a given visit, helping members with their care needs and improving their experience with us.” With today’s release, the Agents SDK harness becomes more capable for agents that work with documents, files, and systems. It now has configurable memory, sandbox-aware orchestration, Codex-like filesystem tools, and standardized integrations with primitives that are becoming common in frontier agent systems. These primitives include tool use via MCP(opens in a new window), progressive disclosure via skills(opens in a new window), custom instructions via AGENTS.md(opens in a new window), code execution using the shell(opens in a new window) tool, file edits using the apply patch(opens in a new window) tool, and more. The harness will continue to incorporate new agentic patterns and primitives over time, so developers can spend less time on core infrastructure updates and more time on the domain-specific logic that makes their agents useful. The harness also helps developers unlock more of a frontier model’s capability by aligning execution with the way those models perform best. That keeps agents closer to the model’s natural operating pattern, improving reliability and performance on complex tasks—particularly when work is long-running or coordinated across a diverse set of tools and systems. In addition, we realize each product is unique and rarely fits neatly into a mold. We designed Agents SDK to support this diversity. Developers get a harness that’s turnkey yet flexible—making it…