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
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.
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.
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.
It manages the agent loop across tools, context, and traces. The sandbox preserves working state across pauses, retries, and resumptions.
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.
openai.com/index/the-next…
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.
openai.com/index/the-next…
Generated by Thread Navigator
Press ⌘ + S to quick-export