OpenAI updates its Agents SDK with native sandboxing and an in-distribution harness for frontier models to help deploy and test agents on long-horizon tasks
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.
TechCrunch Lucas Ropek
Related Coverage
- The next evolution of the Agents SDK OpenAI
- OpenAI's Agents SDK separates the harness from the compute The New Stack · Frederic Lardinois
- OpenAI updates Agents SDK with new sandbox support for safer AI agents The Decoder · Matthias Bastian
- OpenAI updates Agents SDK, adds sandbox for safer code execution Help Net Security · Anamarija Pogorelec
- Cursor 3 Introduces Agent-First Interface, Moving Beyond the IDE Model InfoQ · Steef-Jan Wiggers
- OpenAI Agents SDK improves governance with sandbox execution AI News · Ryan Daws
- OpenAI's Agents SDK 2026 Update: What's New in Building AI Agents Digit · Vyom Ramani
Discussion
-
@sungkim
Sung Kim
on bluesky
This is interesting release from OpenAI. — They have released Codex as API, or AgentSDK with its own sandbox. — openai.com/index/the-ne...
-
@vincent_koc
Vincent Koc
on x
Harness-in-the-loop 😎
-
@cloudflaredev
@cloudflaredev
on x
Long-running agents are the future - we're excited to partner with OpenAI as a sandboxing partner for their new Agents SDK launch! Get started: https://developers.cloudflare.com/ ...
-
@openaidevs
@openaidevs
on x
Customize the Agents SDK to fit your stack. Use it out of the box, or adapt the models, tools, instructions, and orchestration logic your agent needs. The Agents SDK capabilities are available to all API customers. https://openai.com/...
-
@openaidevs
@openaidevs
on x
Bring your own environment. The Agents SDK now supports sandbox execution with providers including @Cloudflare, @Vercel, @modal, @e2b, and more. Keep files, credentials, and execution state in your environment while passing approved context to the model. [image]
-
@whoiskatrin
Kate
on x
you can build a Python agent that accepts a coding task, executes it inside a Cloudflare Sandbox, and copies the output files to your local machine @OpenAIDevs x @CloudflareDev Check out our guide here: https://developers.cloudflare.com/ ...
-
@openaidevs
@openaidevs
on x
Improve agent performance with a harness that keeps long-running agents on track. It manages the agent loop across tools, context, and traces. The sandbox preserves working state across pauses, retries, and resumptions. [image]
-
@_lopopolo
Ryan Lopopolo
on x
The new Agents SDK is what I wish I had in September 2025. It leans into the truth that all agents are coding agents and the thoughtfulness the team has put into “bring your own sandbox” is just fantastic. Let the SDK do the plumbing; focus your energy on your users. Let's build!
-
@vercel_dev
@vercel_dev
on x
Use Vercel Sandbox with the OpenAI agents SDK as an official extension. Build agents that can run code, read files, and analyze data safely inside isolated microVMs. Control the compute and data flow from your secure cloud environment.
-
@stevenheidel
Steven Heidel
on x
we just launched a big update to the Agents SDK. you can now bring your own compute/storage and connect it up to our agent loop to handle things like computer-use, skills, memory, and compaction
-
@openaidevs
@openaidevs
on x
Build long-running agents with more control over agent execution. New capabilities in the Agents SDK: • Run agents in controlled sandboxes • Inspect and customize the open-source harness • Control when memories are created and where they're stored [image]
-
@modal
@modal
on x
Agents need computers. And they need a lot of them. Modal is an official sandbox provider for the @OpenAI Agents SDK. [video]