---
id: "entity-codex-d3"
type: "entity"
entityType: "product"
canonicalName: "OpenAI Codex"
aliases: ["Codex"]
source_timestamps: ["00:00:01", "00:01:00"]
tags: ["product", "agent"]
related: ["entity-openai", "concept-computer-use", "concept-background-execution", "entity-chronicle"]
sources: ["s03-apps-no-api"]
sourceVaultSlug: "s03-apps-no-api"
originDay: 3
---
# OpenAI Codex

## Profile

Originally launched as a **command-line coding tool**, Codex has, per the speaker, been completely revamped by [[entity-openai-d3]] into a **full desktop agent** capable of universal [[concept-computer-use]] — driving the Mac GUI in the background without hijacking the user's cursor.

## Capabilities Highlighted

- [[concept-computer-use]] across legacy and modern apps
- [[concept-background-execution]] (non-hijacking parallel work)
- Ambient memory via [[entity-chronicle]]
- Implicit, mode-free interaction (see [[concept-implicit-vs-explicit-design]])
- Practical workflow targeting in [[action-automate-legacy-software]]

## Performance Claim

In the speaker's testing, Codex outperforms [[entity-claude-d3]] on speed and reliability — see [[claim-codex-outperforms-claude]].

## Canonical Reference

- The historical Codex: https://platform.openai.com/docs/models/codex (legacy code-generation model)
- The 'desktop agent' Codex described in this video reflects the speaker's framing of OpenAI's 2025 agent push and may overlap with current OpenAI agent/Operator-line products rather than a single SKU literally named 'Codex desktop agent'.