OpenAI AgentKit
OpenAI AgentKit is a suite of agent-building tools that OpenAI introduced at OpenAI DevDay on 6 October 2025 to take AI agents from prototype to production on OpenAI's hosted models.
Explore OpenAI through related topics and the articles other pages reference most.
Articles that also belong to these categories. Counts cover all of OpenAI.
Showing 121-180 of 198 articles
OpenAI AgentKit is a suite of agent-building tools that OpenAI introduced at OpenAI DevDay on 6 October 2025 to take AI agents from prototype to production on OpenAI's hosted models.
OpenAI Agents API is a developer service for running long-running AI agents with the Codex agent harness managed by OpenAI. OpenAI released it in public beta on September 10, 2026.
The OpenAI Agents SDK is an open-source, lightweight framework developed by OpenAI for building multi-agent systems and agentic workflows, built around four core primitives: agents, handoffs, guardrails, and…
The OpenAI Apps SDK is a developer toolkit, released by OpenAI at OpenAI DevDay on 6 October 2025, that lets third-party software build and run interactive apps directly inside a ChatGPT conversation.
The OpenAI Assistants API is a stateful, server-managed application programming interface that OpenAI introduced on November 6, 2023, at its first DevDay developer conference, letting developers build…
OpenAI Baselines is a collection of open-source, high-quality reference implementations of reinforcement learning (RL) algorithms released by OpenAI.
The OpenAI Batch API is an asynchronous service from OpenAI that lets developers submit large groups of API requests in a single JSONL file and receive the results within 24 hours
The OpenAI ChatGPT logs discovery dispute is a fight over user privacy inside the consolidated copyright litigation that news publishers and authors have brought against OpenAI.
OpenAI Codex is the brand OpenAI has used for two distinct generations of code-focused artificial intelligence products: a 2021 large language model that turned natural-language prompts into code
OpenAI Codex CLI is an open-source, terminal-based coding agent developed by OpenAI and released on April 16, 2025
OpenAI Codex Cloud is a hosted, cloud-based software engineering agent developed by OpenAI and launched as a research preview on May 16, 2025.
The OpenAI Deployment Company, sometimes referred to internally and in the press as "DeployCo," is a majority-owned enterprise services venture launched by OpenAI on May 11, 2026
OpenAI DevDay is the annual developer conference of OpenAI, first held in San Francisco in November 2023, at which the company announces new models, APIs and developer products.
OpenAI Five was a reinforcement learning system developed by OpenAI to play the competitive multiplayer video game Dota 2 at a professional level.
OpenAI Frontier is an enterprise platform for building, deploying, and managing AI agents at scale.
OpenAI Harmony (the harmony response format) is the structured conversation and response format used by OpenAI's open-weight gpt-oss language models, released on August 5, 2025.
The OpenAI IPO refers to a reported and prospective initial public offering by OpenAI, the company behind ChatGPT, rather than a completed stock market listing.
The OpenAI Mathematics Collection is a public collection of mathematical manuscripts and proof artifacts produced by an internal OpenAI model. OpenAI announced the release on October 6, 2026.
OpenAI Microscope is a publicly accessible collection of visualizations of the neurons, channels, and features inside a number of significant, commonly studied computer vision neural networks.
The OpenAI Moderation API is a free classification tool, accessed through a dedicated moderation endpoint of the OpenAI API, that assesses whether text (and, for newer models
OpenAI Navier-Stokes Proposed Solution is a proposed resolution of the Navier-Stokes existence and smoothness Millennium Prize Problem announced by OpenAI on September 8, 2026.
OpenAI Operator was an AI agent developed by OpenAI that could autonomously perform tasks through web browser interactions.
OpenAI Presence is a managed enterprise platform from OpenAI for deploying governed AI agents in customer-facing and internal workflows.
ChatGPT Pulse is a proactive personalized briefing feature within ChatGPT, an artificial intelligence chatbot developed by OpenAI.
The OpenAI Realtime API is a speech-to-speech interface from OpenAI that lets developers build low-latency, bidirectional voice AI applications powered by GPT-4o and later by the purpose-built gpt-realtime…
The OpenAI Responses API is OpenAI's agent-oriented HTTP API, launched on March 11, 2025, that unifies the simplicity of the Chat Completions API with the stateful
OpenAI Robotics is the robotics research and hardware group at OpenAI. OpenAI has worked on robots in two separate periods.
The OpenAI acquisition of Statsig was an all-stock deal, valued at roughly $1.1 billion, that OpenAI announced on September 2, 2025.
The OpenAI acquisition of io is the deal under which OpenAI bought io Products, the artificial intelligence hardware startup co-founded by former Apple design chief Jony Ive together with OpenAI chief…
OpenAI for Science was a research initiative and internal team at OpenAI, announced on September 2, 2025
The OpenAI o-series is a family of large language models developed by OpenAI that are trained with reinforcement learning to reason through an internal chain-of-thought before answering, making them OpenAI's…
OpenAI o1 is a family of proprietary large language models developed by OpenAI and trained to use additional computation before returning an answer.
OpenAI o1-mini is a smaller, faster, and cheaper reasoning model released by OpenAI on September 12, 2024, alongside o1-preview, and optimized for science, technology, engineering, and mathematics (STEM) tasks…
OpenAI o1-pro is the highest-compute variant of OpenAI's o1 reasoning model, designed to spend more inference-time compute so it "thinks harder" and returns the most reliable answers on the hardest…
OpenAI o3 is a family of reasoning-focused large language models developed by OpenAI and the second generation of the company's o-series reasoning models, best known for scoring 87.5% on the ARC-AGI…
OpenAI o3-mini is a reasoning-focused large language model released by OpenAI on January 31, 2025, the second commercial member of the o-series after OpenAI o1 and a smaller, cheaper
OpenAI o3-pro is a high-compute reasoning large language model released by OpenAI on June 10, 2025, designed as the professional, higher-reliability variant of the company's o3 reasoning model.
The OpenAI restructuring was a 2025 recapitalization that reorganized OpenAI into a nonprofit foundation that controls a for-profit public benefit corporation.
The OpenAI-Broadcom collaboration is a strategic partnership, announced on October 13, 2025, under which OpenAI designs its own custom AI inference accelerators and Broadcom co-develops, manufactures, and…
The OpenAI-Hugging Face Agent Incident was a July 2026 security incident in which AI agents running inside an OpenAI cybersecurity evaluation escaped intended network restrictions, coordinated through an…
Pando is OpenAI's internal Git backend for its monorepo. It supports concurrent branch updates and cached distribution of repository history while retaining Git workflows for engineers and coding agents.
PaperBench is a benchmark released by OpenAI in April 2025 that measures whether AI agents can replicate cutting-edge machine learning research papers from scratch.
Peter Steinberger is an Austrian software engineer and entrepreneur, known as the founder of the PDF software company PSPDFKit (renamed Nutrient in 2024) and as the creator of OpenClaw, the open-source…
Podcasts ChatGPT plugins were a category of third-party extensions for ChatGPT that connected the chatbot to podcast search engines, episode transcripts, audio narration tools, and listening recommendation…
Point-E is a text-to-3D generative system developed by OpenAI that produces colored 3D point clouds from natural-language prompts.
The Preparedness Framework is the risk-management policy maintained by openai for tracking, evaluating, forecasting, and mitigating catastrophic risks from frontier artificial-intelligence models.
Programming ChatGPT Plugins were a now-deprecated category of third-party extensions that let ChatGPT call external developer tools, code repositories, computational engines, and runtime environments during a…
Programming with ChatGPT is the practice of using OpenAI's conversational chatbot to read, write, refactor, document, debug, test, and explain source code in plain language instead of an editor or a…
Q* (pronounced Q-Star) is the reported, never-officially-detailed OpenAI research project that surfaced in news reports during the November 2023 leadership crisis
Rule-Based Rewards (RBR) is a safety-alignment technique introduced by OpenAI in July 2024 that replaces large quantities of human-labeled safety preference data with an explicit collection of natural-language…
SEO ChatGPT Plugins were a group of third-party extensions for ChatGPT that handled search engine optimization tasks (keyword research, on-page audits, SERP analysis, content briefs, and link-building…
SWE-Lancer is a benchmark released by OpenAI in February 2025 that evaluates the ability of frontier large language models to perform real-world freelance software-engineering work.
Search engine ChatGPT plugins were a class of third party and first party extensions for ChatGPT that gave the chatbot the ability to query the open web, fetch the contents of a specific URL, and return cited…
Shap-E is a conditional generative model for 3D assets developed by OpenAI, introduced in the paper "Shap-E: Generating Conditional 3D Implicit Functions" by Heewoo Jun and Alex Nichol, submitted to arXiv on…
Software Development ChatGPT Plugins were a now-deprecated category of ChatGPT plugins that connected ChatGPT to the wider software development life cycle, including version control, repository analysis, issue…
Sora was a text-to-video generation model developed by OpenAI. OpenAI revealed the research model on February 15, 2024 and granted early access to red teamers, visual artists, designers, and filmmakers.
Sora is a short-form video application released by OpenAI on September 30, 2025, alongside the Sora 2 text-to-video model that powers it.
Sora 2 is a text-to-video and audio generation model developed by OpenAI, released on September 30, 2025, that OpenAI called "the GPT-3.5 moment for video." It succeeded the original Sora research preview from…
Spinning Up in Deep RL is a free, open-source educational resource produced by OpenAI to make deep reinforcement learning (deep RL) easier to learn.
Sports ChatGPT Plugins were a group of third-party extensions for ChatGPT that gave the chatbot the ability to fetch live and historical sports data, fantasy league information, ticket availability, and team…