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 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.

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.

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, progressive disclosure via skills, custom instructions via AGENTS.md, code execution using the shell tool, file edits using the apply patch 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.

The updated Agents SDK supports sandbox execution natively, so agents can run in controlled computer environments with the files, tools, and dependencies they need for a task. Native sandbox support gives developers that execution layer out of the box, instead of forcing them to piece it together themselves.

Developers can bring their own sandbox or use built-in support for Blaxel, Cloudflare, Daytona, E2B, Modal, Runloop, and Vercel. To make those environments portable across providers, the SDK also introduces a Manifest abstraction for describing the agent’s workspace. Developers can mount local files, define output directories, and bring in data from storage providers including AWS S3, Google Cloud Storage, Azure Blob Storage, and Cloudflare R2.

Agent systems should be designed assuming prompt-injection and exfiltration attempts. Separating harness and compute helps keep credentials out of environments where model-generated code executes. It also enables durable execution. With built-in snapshotting and rehydration, the Agents SDK can restore the agent’s state in a fresh container and continue from the last checkpoint if the original environment fails or expires.

These new Agents SDK capabilities are generally available to all customers via the API and use standard API pricing. The new harness and sandbox capabilities are launching first in Python, with TypeScript support planned for a future release.