# Learn > Curated docs, videos, and demo apps for OpenAI developers. Docs pages are available at `/learn/.md`. Curated resources are listed here with their canonical destination URLs. ## Documentation sets - [Combined learn docs](https://developers.openai.com/learn/llms-full.txt): Single-file Markdown export of learn docs and curated items. ## Code - [Agents SDK — Python](https://github.com/openai/openai-agents-python): Python SDK for developing agents with OpenAI. - [Agents SDK — TypeScript](https://github.com/openai/openai-agents-js): TypeScript SDK for developing agents with OpenAI. - [Agents SDK quickstart](https://openai.github.io/openai-agents-python/quickstart/): Quickstart project for building agents with the Agents SDK. - [ChatKit advanced samples](https://github.com/openai/openai-chatkit-advanced-samples): Advanced samples showcasing the capabilities of ChatKit (part of AgentKit). - [ChatKit starter app](https://github.com/openai/openai-chatkit-starter-app): Integrate ChatKit with an Agent Builder workflow in your application. - [Computer Use API — starter app](https://github.com/openai/openai-cua-sample-app): Sample app showcasing Computer Use API integration. - [CS agents demo](https://github.com/openai/openai-cs-agents-demo): Demo showcasing customer service agents orchestration. - [Frontend testing demo](https://github.com/openai/openai-testing-agent-demo): Demo application for frontend testing using CUA. - [openai.fm](https://github.com/openai/openai-fm): Code samples for speech processing from the openai.fm repo. - [Plugin UI examples](https://github.com/openai/openai-apps-sdk-examples): Example UI and corresponding MCP servers for ChatGPT plugins. - [Realtime & Twilio starter app](https://github.com/openai/openai-realtime-twilio-demo): Starter app integrating realtime agents with Twilio. - [Realtime agents starter app](https://github.com/openai/openai-realtime-agents): Starter app demonstrating realtime agent capabilities. - [Realtime console](https://github.com/openai/openai-realtime-console): Console application demonstrating realtime API usage. - [Realtime solar system](https://github.com/openai/openai-realtime-solar-system): Demo of realtime agent interactions in a solar system example. - [Responses starter app](https://github.com/openai/openai-responses-starter-app): Starter application demonstrating OpenAI Responses API with tools. - [Sora starter app](https://github.com/openai/openai-sora-sample-app): Sample app showcasing integrations with Sora in the API. - [Structured outputs samples](https://github.com/openai/openai-structured-outputs-samples): Sample code demonstrating structured outputs with OpenAI APIs. - [Support agent demo](https://github.com/openai/openai-support-agent-demo): Demo showing a customer support agent with a human in the loop. ## Cookbook - [Codex Prompting Guide](https://developers.openai.com/cookbook/examples/gpt-5/codex_prompting_guide): Codex models advance the frontier of intelligence and efficiency and our recommended agentic coding model. Follow this guide closely to ensure you’re getting th - [Comparing Speech-to-Text Methods with the OpenAI API](https://developers.openai.com/cookbook/examples/speech_transcription_methods): Cookbook to compare speech-to-text methods and choose the right approach. - [Developing Hallucination Guardrails](https://developers.openai.com/cookbook/examples/developing_hallucination_guardrails): Cookbook to build hallucination guardrails with evals for support agents. - [Doing RAG on PDFs using File Search in the Responses API](https://developers.openai.com/cookbook/examples/file_search_responses): Cookbook to search PDFs with the Responses API file search tool. - [Eval Driven System Design - From Prototype to Production](https://developers.openai.com/cookbook/examples/partners/eval_driven_system_design/receipt_inspection): Cookbook for eval-driven design of a receipt parsing automation workflow. - [Evals API Use-case - Responses Evaluation](https://developers.openai.com/cookbook/examples/evaluation/use-cases/responses-evaluation): Cookbook to evaluate new models against stored Responses API logs. - [Exploring Model Graders for Reinforcement Fine-Tuning](https://developers.openai.com/cookbook/examples/reinforcement_fine_tuning): Cookbook to use model graders for reinforcement fine-tuning in expert tasks. - [Fine-tuning with gpt-oss and Hugging Face Transformers](https://developers.openai.com/cookbook/articles/gpt-oss/fine-tune-transfomers): Authored by: Edward Beeching, Quentin Gallouédec, and Lewis Tunstall Large reasoning models like OpenAI o3 generate a chain-of-thought to improve the accuracy a - [Generate images with GPT Image](https://developers.openai.com/cookbook/examples/generate_images_with_gpt_image): Cookbook to generate and edit images with GPT Image capabilities. - [Generate images with high input fidelity](https://developers.openai.com/cookbook/examples/generate_images_with_high_input_fidelity): Cookbook to preserve image details using high input fidelity in Image API. - [GPT-5.2 Prompting Guide](https://developers.openai.com/cookbook/examples/gpt-5/gpt-5-2_prompting_guide): Cookbook to prompt GPT-5.2 for accurate, concise enterprise workflows. - [Gpt-image-1.5 Prompting Guide](https://developers.openai.com/cookbook/examples/multimodal/image-gen-1.5-prompting_guide): Cookbook to prompt gpt-image-1.5 for reliable image generation results. - [Guide to Using the Responses API's MCP Tool](https://developers.openai.com/cookbook/examples/mcp/mcp_tool_guide): Cookbook to connect external services using the Responses API MCP tool. - [How to run gpt-oss locally with LM Studio](https://developers.openai.com/cookbook/articles/gpt-oss/run-locally-lmstudio): LM Studio is a performant and friendly desktop application for running large language models (LLMs) on local hardware. This guide will walk you through how to s - [How to run gpt-oss locally with Ollama](https://developers.openai.com/cookbook/articles/gpt-oss/run-locally-ollama): Want to get OpenAI gpt-oss running on your own hardware? This guide will walk you through how to use Ollama to set up gpt-oss-20b or gpt-oss-120b locally, to ch - [How to use the Usage API and Cost API to monitor your OpenAI usage](https://developers.openai.com/cookbook/examples/completions_usage_api): Cookbook to fetch and visualize Completions Usage and cost data via API. - [Leveraging model distillation to fine-tune a model](https://developers.openai.com/cookbook/examples/leveraging_model_distillation_to_fine-tune_a_model): Cookbook to distill a larger model into a smaller fine-tuned model. - [Modernizing your Codebase with Codex](https://developers.openai.com/cookbook/examples/codex/code_modernization): Cookbook to modernize legacy codebases using the OpenAI Codex CLI. - [Multi-Agent Portfolio Collaboration with OpenAI Agents SDK](https://developers.openai.com/cookbook/examples/agents_sdk/multi-agent-portfolio-collaboration/multi_agent_portfolio_collaboration): Cookbook for multi-agent portfolio analysis workflows using the OpenAI Agents SDK. - [Multi-Language One-Way Translation with the Realtime API](https://developers.openai.com/cookbook/examples/voice_solutions/one_way_translation_using_realtime_api): Cookbook to build one-way speech translation with the Realtime API. - [Multi-Tool Orchestration with RAG approach using OpenAI's Responses API](https://developers.openai.com/cookbook/examples/responses_api/responses_api_tool_orchestration): Cookbook to route queries across tools with RAG using the Responses API. - [o3/o4-mini Function Calling Guide](https://developers.openai.com/cookbook/examples/o-series/o3o4-mini_prompting_guide): Cookbook to improve o3/o4-mini function calling with prompt best practices. - [Orchestrating Agents: Routines and Handoffs](https://developers.openai.com/cookbook/examples/orchestrating_agents): Cookbook for orchestrating agent workflows with routines and handoffs. - [Prompt Caching 101](https://developers.openai.com/cookbook/examples/prompt_caching101): Cookbook to reduce latency and cost using OpenAI prompt caching. - [Reinforcement Fine-Tuning for Conversational Reasoning with the OpenAI API](https://developers.openai.com/cookbook/examples/fine-tuned_qa/reinforcement_finetuning_healthbench): Cookbook for reinforcement fine-tuning conversational reasoning using HealthBench evaluations. - [Sora 2 Prompting Guide](https://developers.openai.com/cookbook/examples/sora/sora2_prompting_guide): Cookbook to craft effective video prompts for Sora 2 generation. - [Transcribing User Audio with a Separate Realtime Request](https://developers.openai.com/cookbook/examples/realtime_out_of_band_transcription): Cookbook to transcribe user audio using out-of-band Realtime sessions. - [Verifying gpt-oss implementations](https://developers.openai.com/cookbook/articles/gpt-oss/verifying-implementations): The OpenAI gpt-oss models are introducing a lot of new concepts to the open-model ecosystem and getting them to perform as expected might take some time. This g ## Docs - [Docs MCP](https://developers.openai.com/learn/docs-mcp.md): Search and read OpenAI developer docs from your editor using MCP. - [OpenAI Developers plugin](https://developers.openai.com/learn/developers-codex-plugin.md): Install the OpenAI Developers plugin in ChatGPT, Codex, Claude Code, or Cursor to build, troubleshoot, and ship experiences with the OpenAI API. ## Guide - [Agentic Commerce Protocol](https://developers.openai.com/commerce): Design flows for embedded commerce in ChatGPT. - [Agents SDK quickstart](https://openai.github.io/openai-agents-python/quickstart/): Step-by-step guide to quickly build agents with the OpenAI Agents SDK. - [API deployment checklist](https://developers.openai.com/api/docs/guides/deployment-checklist): Checklist for tuning Responses API applications before launch. - [Audio & speech guide](https://platform.openai.com/docs/guides/audio): Overview of approaches for audio processing and speech in applications. - [Background mode guide](https://platform.openai.com/docs/guides/background): Guide to running tasks in the background with Responses. - [Batch API guide](https://platform.openai.com/docs/guides/batch): Guide on how to use the Batch API to reduce costs - [Building agents guide](https://platform.openai.com/docs/guides/agents): Official guide to building agents using the OpenAI platform. - [Building guardrails for agents](https://openai.github.io/openai-agents-python/guardrails/): Guide to implementing safeguards and guardrails in agent applications. - [Built-in tools guide](https://platform.openai.com/docs/guides/tools?api-mode=responses): Guide to using OpenAI's built-in tools with the Responses API. - [Code interpreter guide](https://platform.openai.com/docs/guides/tools-code-interpreter): Guide to using the built-in code interpreter tool. - [Computer Use API guide](https://platform.openai.com/docs/guides/tools-computer-use): Guide to using the Computer Use API (CUA). - [Conversation state guide](https://platform.openai.com/docs/guides/conversation-state?api-mode=responses): Guide for managing conversation state with the Responses API. - [Docs MCP](https://developers.openai.com/learn/docs-mcp): Search and read OpenAI developer docs from your editor using MCP. - [Evals Best Practices](https://platform.openai.com/docs/guides/evaluation-best-practices): Best practices for designing and running evals. - [File search guide](https://platform.openai.com/docs/guides/tools-file-search): Guide to retrieving context from files using the Responses API. - [Fine-tuning best practices](https://platform.openai.com/docs/guides/fine-tuning-best-practices#page-top): Recommendations for effective and efficient model fine-tuning. - [Fine-tuning guide](https://platform.openai.com/docs/guides/fine-tuning): Comprehensive guide to fine-tuning OpenAI models. - [Flex processing guide](https://platform.openai.com/docs/guides/flex-processing): Guide on how to reduce costs with flex processing - [Function calling guide](https://platform.openai.com/docs/guides/function-calling): Introduction to function calling with OpenAI models. - [Getting Started with Evals](https://platform.openai.com/docs/guides/evaluation-getting-started): Step-by-step guide to setting up your first eval. - [Graders](https://platform.openai.com/docs/guides/graders): Guide to using graders for evaluations. - [Image generation guide](https://platform.openai.com/docs/guides/image-generation): Guide to generating images using OpenAI models. - [Keep costs low & accuracy high](https://platform.openai.com/docs/guides/reasoning-best-practices#how-to-keep-costs-low-and-accuracy-high): Guide on balancing cost efficiency with model accuracy. - [Latency optimization guide](https://platform.openai.com/docs/guides/latency-optimization): Best practices for reducing model response latency. - [LLM correctness and consistency](https://platform.openai.com/docs/guides/optimizing-llm-accuracy): Best practices for achieving accurate and consistent model outputs. - [MCP guide](https://platform.openai.com/docs/guides/tools-remote-mcp): Guide to using the Model Context Protocol for portable tools. - [Model distillation overview](https://platform.openai.com/docs/guides/distillation#page-top): Overview of distillation techniques for creating efficient models. - [Model optimization guide](https://platform.openai.com/docs/guides/model-optimization): Guide on optimizing OpenAI models for performance and cost. - [OpenAI Developers plugin](https://developers.openai.com/learn/developers-codex-plugin): Install and use the OpenAI Developers plugin in Codex, Claude Code, or Cursor. - [OpenAI models page](https://platform.openai.com/docs/models): Overview of the models available on the OpenAI platform. - [Orchestrating multiple agents](https://openai.github.io/openai-agents-python/multi_agent/): Guide to coordinating multiple agents with shared context. - [Predicted outputs guide](https://platform.openai.com/docs/guides/predicted-outputs): Guide to understanding and using predicted outputs. - [Production best practices](https://platform.openai.com/docs/guides/production-best-practices): Guide on best practices for running AI applications in production - [Prompt engineering guide](https://platform.openai.com/docs/guides/realtime-transcription): Detailed guide on prompt engineering strategies. - [Prompt Optimizer](https://platform.openai.com/docs/guides/prompt-optimizer): Guide to refining prompts with the Prompt Optimizer. - [RAG technique overview](https://platform.openai.com/docs/guides/optimizing-llm-accuracy#retrieval-augmented-generation-rag): Overview of retrieval-augmented generation techniques. - [Rate limits guide](https://platform.openai.com/docs/guides/rate-limits): Guide to understanding and managing rate limits - [Realtime and audio guide](https://platform.openai.com/docs/guides/realtime): Guide to choosing realtime and audio build paths. - [Realtime intro](https://platform.openai.com/docs/guides/realtime-conversations): Introduction to building realtime voice applications. - [Realtime prompting guide](https://platform.openai.com/docs/guides/realtime-models-prompting): Guide to prompting and tuning realtime voice models. - [Realtime tool delegation guide](https://openai.github.io/openai-agents-js/guides/voice-agents/build/#delegation-through-tools): Guide on delegating tasks through tools in realtime agents. - [Realtime transcription guide](https://platform.openai.com/docs/guides/realtime-transcription): Guide for implementing streaming realtime speech transcription. - [Realtime translation guide](https://platform.openai.com/docs/guides/realtime-translation): Guide to performing realtime speech translation. - [Reasoning best practices](https://platform.openai.com/docs/guides/reasoning-best-practices): Prompting and optimization tips for reasoning models - [Reasoning guide](https://platform.openai.com/docs/guides/reasoning?api-mode=responses): Overview of what reasoning is and how to prompt reasoning models - [Reinforcement fine-tuning overview](https://platform.openai.com/docs/guides/reinforcement-fine-tuning): Guide on reinforcement learning-based fine-tuning techniques. - [Responses guide](https://platform.openai.com/docs/api-reference/responses): Introduction to the Responses API and its endpoints. - [Responses vs. chat completions guide](https://platform.openai.com/docs/guides/responses-vs-chat-completions): Comparison of the Responses API and Chat Completions. - [Speech-to-text guide](https://platform.openai.com/docs/guides/speech-to-text): Guide for building speech recognition pipelines. - [Speech-to-text intro](https://platform.openai.com/docs/guides/speech-to-text): Introduction to speech recognition with OpenAI. - [Structured outputs guide](https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses): Guide for producing structured outputs with the Responses API. - [Supervised fine-tuning overview](https://platform.openai.com/docs/guides/supervised-fine-tuning): Guide to supervised fine-tuning for customizing model behavior. - [Tools overview guide](https://openai.github.io/openai-agents-js/guides/voice-agents/build/#delegation-through-tools): Guide covering realtime delegation through tools. - [Tracing module](https://openai.github.io/openai-agents-python/tracing/): Guide to monitoring and debugging agents with tracing. - [Transcription guide](https://platform.openai.com/docs/guides/realtime-transcription): Detailed guide for building transcription pipelines. - [Transcription intro](https://platform.openai.com/docs/guides/speech-to-text#transcriptions): Introduction to converting speech to text with OpenAI APIs. - [Translation use case](https://platform.openai.com/docs/guides/speech-to-text#translations): Overview of building multilingual voice applications. - [Vision fine-tuning overview](https://platform.openai.com/docs/guides/vision-fine-tuning): Guide to fine-tuning models on vision tasks. - [Voice agents guide](https://platform.openai.com/docs/guides/voice-agents): Guide to building voice agents using speech-to-speech API. - [Voice applications intro](https://platform.openai.com/docs/guides/voice-agents?voice-agent-architecture=speech-to-speech#speech-to-speech-realtime-architecture): Introduction to building voice-enabled applications with OpenAI. - [Web search guide](https://platform.openai.com/docs/guides/tools-web-search): Guide to using web search with the Responses API. - [Working with the Evals API](https://platform.openai.com/docs/guides/evals): Guide to building evaluations with the Evals API. ## Video - [4o image generation intro](https://www.youtube.com/watch?v=2f3K43FHRKo): Video introduction to 4o model image generation capabilities. - [Balance accuracy, latency, and cost](https://www.youtube.com/watch?v=Bx6sUDRMx-8): Talk on optimizing AI systems for accuracy, speed, and cost. - [Build beautiful frontends with OpenAI Codex](https://www.youtube.com/watch?v=fK_bm84N7bs): Learn how OpenAI Codex's multimodal abilities accelerate frontend development. - [Build hour — agentic tool calling](https://webinar.openai.com/on-demand/d1a99ac5-8de8-43c5-b209-21903d76b5b2): Build hour giving an overview of agentic tool calling. - [Build hour — built-in tools](https://webinar.openai.com/on-demand/c17a0484-d32c-4359-b5ee-d318dad51586): Build hour giving an overview of built-in tools available in the Responses API. - [Building with Open Models](https://www.youtube.com/watch?v=1HL2YHRj270): Talk covering how developers customize and deploy OpenAI’s open models. - [Codex code review](https://www.youtube.com/watch?v=HwbSWVg5Ln4): Walkthrough of how Codex drives end-to-end pull request reviews with the new onboarding flow. - [Codex for (almost) everything](https://www.youtube.com/watch?v=Lm7-yFZ5fZQ): See the latest Codex app updates for working across more of the software development lifecycle. - [Codex in JetBrains IDEs](https://www.youtube.com/watch?v=1XkVsE9-ZK4): How to use Codex inside JetBrains IDEs like Rider, IntelliJ, PyCharm, and WebStorm. - [Codex intro](https://www.youtube.com/watch?v=hhdpnbfH6NU): Introductory video introducing Codex and its capabilities. - [Context Engineering & Coding Agents with Cursor](https://www.youtube.com/watch?v=3KAI__5dUn0): Session on structuring context for agent workflows inside the Cursor editor. - [DevDay — distillation breakout](https://www.youtube.com/watch?v=CqWpJFK-hOo): DevDay session on model distillation techniques. - [DevDay — optimization breakout](https://www.youtube.com/watch?v=Bx6sUDRMx-8): DevDay session discussing optimization of models and prompts. - [DevDay — realtime breakout](https://www.youtube.com/watch?v=mM8KhTxwPgs): DevDay session focused on realtime agent capabilities. - [DevDay — structured outputs breakout](https://www.youtube.com/watch?v=kE4BkATIl9c): Session covering structured outputs from DevDay. - [Introducing the Codex app](https://www.youtube.com/watch?v=HFM3se4lNiw): See the Codex app in action and how it helps you build and ship faster. - [Launch apps with evaluations](https://vimeo.com/1105244173): Video on incorporating evals when deploying AI products. - [Live Demo Showcase: Tools That 10x Your Codebase](https://www.youtube.com/watch?v=-l0OqapibAA): Live walkthrough of Codex-powered tooling that accelerates software delivery. - [MCP intro](https://vimeo.com/1105243308): Introduction video to Model Customization Platform (MCP). - [New audio models intro](https://www.youtube.com/watch?v=lXb0L16ISAc): Overview video of new audio models for speech and transcription. - [OpenAI Codex in your code editor](https://www.youtube.com/watch?v=sd21Igx4HtA): Walkthrough of the Codex IDE extension for VS Code, Cursor, and other forks. - [Realtime agent demo](https://vimeo.com/1105243382): Video introduction to the TypeScript Agents SDK. - [Responses API — tools and features](https://vimeo.com/1105245596): Overview video of available tools and capabilities in the Responses API. - [Shipping with Codex](https://www.youtube.com/watch?v=Gr41tYOzE20): DevDay talk on building, testing, and delivering products with Codex. - [Sora, ImageGen, and Codex: The Next Wave of Creative Production](https://www.youtube.com/watch?v=70ush8Vknx8): Panel discussion on combining Sora, ImageGen, and Codex for media creation. - [Unlock agentic power — Agents SDK](https://vimeo.com/1105245234): Video demonstrating advanced capabilities of the Agents SDK. - [Using OpenAI Codex CLI with GPT-5-Codex](https://www.youtube.com/watch?v=iqNzfK4_meQ): Overview of running the Codex CLI locally with GPT-5-Codex.