AI product
OpenAI Codex is an AI coding agent from OpenAI available as a command-line tool (Codex CLI) that helps developers produce software. It can be used alongside Gemini for adversarial audits of software requirements and implementation plans, listed as a supported coding-agent or model option in several projects, and its logs can be joined with task and test evidence. The Codex CLI can also receive and answer requests from the Penako canvas.
45 uses taken from transcripts — each links to the moment in the video.
Used alongside Gemini to conduct adversarial audits of software requirements and implementation plans.
Provides an agent experience used for software development and for building a separate playable version of the Strata game.
Used by Nico as a vibe-coding tool to help build software.
Mentioned as another tool for creating browser-based linkable tools.
Handles local or desktop coding and general information-work tasks.
Coding agent used as an example of modifying files and determining test cases from English instructions.
Primary lead agent and locally connected harness used for business operations, coding, research, management, thumbnail creation, and deployment tasks.
Secondary AI coding plan used when the Claude Code subscription ran out.
Coding engine placed under IBM's software-development harness.
Received coding tasks on the floating computer environment.
Supports a similar workflow for running agent skills and scripts.
Used to build OpenClaw and its messaging relay with a coding agent.
Provides coding-agent logs that agentacct joins with tasks and test evidence.
Provides a supported coding-agent or model option in multiple projects.
Provides coding-agent sessions and is one of the model or agent environments integrated with projects in the transcript.
Can receive and answer requests from the Penako canvas.
Coding agent used in the shared agent workspace.
AI agent harness used for complex development work, software testing, verification, and higher-quality code generation.
Runs as a terminal-based coding agent option.
Used as a comparison coding harness and for automatic title generation in the T3 Code workflow.
Helps with deploying the model-serving setup.
A coding harness from OpenAI that is cited as part of the company's recent product progress.
Provides the coding-agent environment used to configure and run the pull-request audit.
An AI coding and work platform discussed as an increasingly common alternative to Claude Code. The video says its broader work capabilities may be more significant than its coding function alone.
An open-source coding agent from OpenAI that runs locally in the terminal. It reads, edits, and runs code in response to user tasks.
Provides coding-agent functionality for memorax-code, open-pstack, and Whip-related workflows.
An AI system the speakers use alongside Grokbot and Town to identify and carry out workplace automations.
Used for mathematical experimentation, coding projects, and a personal harness for assisting mathematical understanding.
Provided the coding agent environment used to build and modify applications and Lakebed.
An AI coding tool used by Speechify engineers, though less frequently than Claude Code and Cursor.
An AI coding agent and development workbench used for coding, refactoring, troubleshooting production bugs, analyzing metrics, data science, summarizing discussions, and preparing documents and presentations. It also automatically reviews pull requests and can support automated performance profiling, benchmarking, and optimization workflows.
Used by the Town engineering team for software development and coding tasks.
Runs coding-agent tasks and provides an alternative model and usage implementation for auditing pull requests and comparing skill behavior.
Runs the local project, installs Hyperframes and dependencies, interprets natural-language editing instructions, and drives the editing process.
Agent harness used to run Astra, operate the computer, manage coding tasks, use sub-agents, and apply changes to codebases.
Runs the I-have-ADHD skill and consumes OpenAI plugin bundles.
Computer-use coding agent run on a Mac Mini to automate the React Native-to-native app port and test it in a simulator.
An AI coding and computer-use tool used to penetration-test a static website, identify 13 findings, and apply the resulting security fixes.
Serves as an alternative coding-agent harness used alongside Claude Code.
Named as a coding-agent example intended to use Stack Overflow for Agents.
Computer-use and coding agent used to verify Fable's results, especially for computer-use tasks and on macOS.
Andrew Ng says OpenAI Codex made significant progress as an AI coding tool and can help developers produce software.
AI coding agent used to generate the YouTube-like homepage and provide implementation instructions.
Agent used in the demonstrations to register on the collaboration platform, send connection requests, invite another agent, exchange messages, and collaborate with other coding agents.
An agent-based review system that reviews its own changes, invokes other agents to review those reviews, runs a bootable copy of itself, and exposes logging to the agents.
53 in the library.