Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
Abdulrahman Alfozan | عبدالرحمن الفوزان
279 posts
Abdulrahman Alfozan | عبدالرحمن الفوزان
@alfozan
Agents @OpenAI | previously @useNash, @Meta | @MIT, @UCBerkeley | @RaedVC
San Francisco, CA Katılım Mart 2009
1K Takip Edilen3.2K Takipçiler
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
The updated Agents SDK is now available in TypeScript, with support for sandbox agents and an open-source harness built in.
OpenAI Developers@OpenAIDevs
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
English
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
The ability to scale agent infrastructure on-demand is crucial.
Learn how we built a massively parallel research agent with the @OpenAI Agents SDK with Modal Sandboxes:
modal.com/blog/building-…
OpenAI Developers@OpenAIDevs
Agents that run code need a controlled workspace ready when work starts. @modal shares why scale matters for long-running agents built with the Agents SDK.
English
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
OpenAI updates its Agents SDK to help enterprises build safer, more capable agents techcrunch.com/2026/04/15/ope…
English
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
Today, we’re launching a Rather Large™ update to the OpenAI Agents SDK.
Agents SDK now allows you to scale Codex-style agents in production, without building the whole harness yourself. We’ve brought all of the stuff of modern agents: computer-use, skills, memory, compaction, and more to the same platforms you’re already using.
English
The next evolution of the Agents SDK
OpenAI Developers@OpenAIDevs
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
English
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
Time to build 🚀
→ Sandbox guide with demos & code examples:
developers.openai.com/api/docs/guide…
→ open-source harness:
github.com/openai/openai-…
English
Manifests give agents a portable workspace contract: file access, output locations, and external data sources, with sandbox integrations that work across providers including @Cloudflare, @Vercel, @modal, @e2b, @daytonaio, plus storage backends S3, GCS, Azure Blob, and R2.
Observability & tracing make each run easier to inspect: turns, tools, handoffs, sandbox actions, timings, and more.
English
Agents become truly powerful when they have a real place to work 🧰
Excited to share the next evolution of the OpenAI Agents SDK: native sandbox execution, plus a fully open-source harness that manages tools, skills, context, handoffs, memory, orchestration and more.
English
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
Introducing OpenAI Frontier—a new platform that helps enterprises build, deploy, and manage AI coworkers that can do real work. openai.com/index/introduc…
English
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
Inside our in-house AI data agent
It reasons over 600+ PB and 70k datasets, enabling natural language data analysis across Engineering, Product, Research, and more
Our agent uses Codex-powered table-level knowledge plus product and organizational context
openai.com/index/inside-o…
English
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
Abdulrahman Alfozan | عبدالرحمن الفوزان retweetledi
OpenAI is co-founding the Agentic AI Foundation (AAIF) under the Linux Foundation alongside Anthropic and Block to support open, interoperable standards for agentic AI.
We’re also donating AGENTS .md to help establish open standards that enable safe, reliable agents across tools, repositories, and ecosystems. openai.com/index/agentic-…
English