OpenAI updates its Agents SDK to help enterprises build safer, more capable agents

Source: TechCrunch

Overview

Agentic AI is the tech industry’s newest success story, and companies like OpenAI and Anthropic are racing to give enterprises the tools they need to create these automated little helpers. To that end, OpenAI has now updated its agents software development toolkit (SDK), introducing a number of new features designed to help businesses create their own agents that run on the backs of OpenAI’s models.

New Features of the Agents SDK

Sandbox Capability

The SDK now includes a sandboxing ability, allowing agents to operate in controlled computer environments. This mitigates the risks associated with running agents in an unsupervised fashion, which can be risky due to their occasionally unpredictable nature. With sandbox integration, agents can work in a siloed capacity within a particular workspace, accessing files and code only for specific operations while protecting the system’s overall integrity.

In‑distribution Harness for Frontier Models

The updated SDK provides developers with an in‑distribution harness for frontier models. In agent development, a “harness” refers to the components surrounding the model that enable deployment and testing. An in‑distribution harness allows agents to work with files and approved tools within a workspace, leveraging the most advanced, general‑purpose models available (frontier models definition).

“This launch, at its core, is about taking our existing Agents SDK and making it so it’s compatible with all of these sandbox providers,” said Karan Sharma, product team at OpenAI.
“The hope is that this, paired with the new harness capabilities, will allow users to go build these long‑horizon agents using our harness and with whatever infrastructure they have.”

Long‑horizon tasks are generally considered to be more complex and multi‑step work.

Availability and Pricing

The new harness and sandbox capabilities are launching first in Python, with TypeScript support planned for a later release. OpenAI also plans to add more agent capabilities—such as code mode and subagents—to both Python and TypeScript.

The updated Agents SDK capabilities are being offered to all customers via the API and will use standard pricing.

Image Credit: OpenAI