openai

openai

Explained projects

openai/math: The Repo That Turns Mathematics Into a Build Artifact
Research Agents
openai/math: The Repo That Turns Mathematics Into a Build Artifact
A deep dive into the Lean-backed pipeline where model output becomes papers, proofs, and formal checks, with the failures filed right alongside the wins.
12 min read · Oct 7, 2026
openai/NavierStokesAndEuler: How OpenAI Turned a Millennium-Scale Fluid Proof into a Lean Contract
Research Agents
openai/NavierStokesAndEuler: How OpenAI Turned a Millennium-Scale Fluid Proof into a Lean Contract
A deep dive into the Comparator pattern, the induction machinery behind singularity, and why this repo feels less like a paper and more like a verification pipeline.
10 min read · Sep 9, 2026
openai-agents-python: OpenAI Agents SDK: The Small Runtime That Makes Multi-Agent Systems Feel Native
Multi-Agent Frameworks
openai-agents-python: OpenAI Agents SDK: The Small Runtime That Makes Multi-Agent Systems Feel Native
A Python-first framework that turns handoffs, sessions, guardrails, tracing, and realtime voice into one coherent agent loop.
8 min read · Apr 16, 2026
openai/openai-python: The Generated SDK That Still Feels Hand-Built
Coding Agents
openai/openai-python: The Generated SDK That Still Feels Hand-Built
A deep dive into the Python client that turns a moving API into a typed, async-ready, production-friendly interface without sacrificing ergonomics or correctness.
10 min read · Apr 13, 2026
model_spec_evals: When an AI constitution becomes a passing score
Benchmarks & Eval
model_spec_evals: When an AI constitution becomes a passing score
openai/model_spec_evals turns OpenAI’s Model Spec into an executable test suite, where a judge model writes the critique, median sampling reduces noise, and 6 becomes the line between pass and fail.
8 min read · Apr 8, 2026
openai-mcpkit: OpenAI's MCP kit starts where most demos end: authentication
Security & Supply Chain
openai-mcpkit: OpenAI's MCP kit starts where most demos end: authentication
A blueprint for bringing proprietary data into ChatGPT without flattening the enterprise security model.
10 min read · Apr 8, 2026
openai/apps-sdk-ui: The design system that teaches apps how to feel native inside ChatGPT
Open-Source Replacements
openai/apps-sdk-ui: The design system that teaches apps how to feel native inside ChatGPT
A deep dive into the host-aware component layer, data-attribute styling, and responsive patterns that let third-party widgets disappear into a moving interface.
8 min read · Apr 8, 2026
openai/parameter-golf: The 16MB Weight Class for Language Models
Benchmarks & Eval
openai/parameter-golf: The 16MB Weight Class for Language Models
A leaderboard repo where every byte, every second, and every optimizer choice changes the result.
9 min read · Apr 8, 2026
Inside openai/openai-chatkit-starter-app: The Chat Starter That Makes the Backend a Boundary
Self-Hosted AI
Inside openai/openai-chatkit-starter-app: The Chat Starter That Makes the Backend a Boundary
A deep dive into OpenAI’s reference app, where one path hosts the whole conversation and the other turns the server into a secure session broker.
11 min read · Apr 8, 2026
openai/openai-apps-sdk-examples: The Repo That Turns ChatGPT Into a Widget Host
Workflow Automation
openai/openai-apps-sdk-examples: The Repo That Turns ChatGPT Into a Widget Host
A reference implementation for Apps SDK widgets, MCP servers, and the `window.openai` bridge that keeps UI alive inside the chat.
12 min read · Apr 8, 2026
openai/model_spec_dataset: case law for a model constitution
Benchmarks & Eval
openai/model_spec_dataset: case law for a model constitution
A benchmark where the payload is a rubric, not an answer key, and the real test is whether a model can follow instruction hierarchy, refuse safely, and stay objective.
9 min read · Apr 8, 2026
openai/circuit_sparsity: The Sparse Transformer That Comes with a Debugger
Benchmarks & Eval
openai/circuit_sparsity: The Sparse Transformer That Comes with a Debugger
A hermetic GPT, hook-first inference, and a Streamlit visualizer turn mechanistic interpretability into something you can inspect, patch, and compare.
11 min read · Apr 8, 2026
openai/gpt-oss-safeguard: The Moderation Model That Reads the Rulebook First
Security & Supply Chain
openai/gpt-oss-safeguard: The Moderation Model That Reads the Rulebook First
A new safety system treats policy as input, not an afterthought. That makes moderation more transparent, more adaptable, and much harder to mistake for a fixed classifier.
9 min read · Apr 7, 2026
openai/openai-sora-sample-app: What Happens After You Click Generate
3D Generative AI
openai/openai-sora-sample-app: What Happens After You Click Generate
A reference app that turns long-running video generation into a usable workflow with prompt optimization, starter images, polling, local persistence, and remix forks.
12 min read · Apr 7, 2026
hallucinations-paper-experiments: The notebook that measures how truth gets taxed
Benchmarks & Eval
hallucinations-paper-experiments: The notebook that measures how truth gets taxed
OpenAI's reproduction code for hallucination research shows how evaluation rules can push models toward guessing, and how a consistency check tries to pull them back.
10 min read · Apr 7, 2026
OpenAI teen-safety-policy-pack: The moderation layer written like code
Security & Supply Chain
OpenAI teen-safety-policy-pack: The moderation layer written like code
How Markdown policies, label ladders, and test datasets turn teen safety into a versioned enforcement spec.
7 min read · Apr 7, 2026
GABRIEL Turns LLMs Into a Measurement Stack
Benchmarks & Eval
GABRIEL Turns LLMs Into a Measurement Stack
OpenAI's toolkit treats ratings, rankings, extraction, and de-identification as repeatable research workflows instead of ad hoc prompts.
11 min read · Apr 7, 2026
openai/openai-chatkit-advanced-samples: ChatKit’s Headless GUI Blueprint
Voice & Multimodal AI
openai/openai-chatkit-advanced-samples: ChatKit’s Headless GUI Blueprint
A FastAPI and React reference repo where state, widgets, hidden context, and client effects do the work that plain prompting cannot.
9 min read · Apr 7, 2026
openai/skills: The Repository That Turns Prompts into Portable Agent Skills
Agent Memory & Skills
openai/skills: The Repository That Turns Prompts into Portable Agent Skills
OpenAI's skills system packages instructions, docs, scripts, and validation into reusable modules, so agents act more like disciplined software than freeform text generators.
8 min read · Apr 7, 2026
openai/chatkit-python: The SDK That Streams UI, Not Just Tokens
Voice & Multimodal AI
openai/chatkit-python: The SDK That Streams UI, Not Just Tokens
Inside the widget diff engine, typed protocol, and persistence layer that turn a Python backend into a living chat interface.
8 min read · Apr 7, 2026
openai/plugins: The File System Is the New App Store for Codex
Agent Memory & Skills
openai/plugins: The File System Is the New App Store for Codex
Manifests, skills, and MCP servers turn AI capability into installable, governable packages. The repo is a blueprint for how agents will be extended.
8 min read · Apr 7, 2026
codex: A Distributed System in CLI Clothing
Coding Agents
codex: A Distributed System in CLI Clothing
How openai/codex disguised a high-performance Rust orchestration server as a terminal tool, and accidentally created a cross-platform standard along the way.
8 min read · Mar 30, 2026
symphony: The Elixir Engine Managing OpenAI's Autonomous Workforce
Multi-Agent Frameworks
symphony: The Elixir Engine Managing OpenAI's Autonomous Workforce
How openai/symphony leverages the Erlang VM to turn fragile AI coding agents into reliable, background-running employees.
8 min read · Mar 30, 2026
Good Cop, Bad Cop: Unpacking openai/codex-plugin-cc
Coding Agents
Good Cop, Bad Cop: Unpacking openai/codex-plugin-cc
How an official OpenAI plugin turns Anthropic's terminal agent into an adversarial, multi-model workspace.
7 min read · Mar 30, 2026