Skip to content
Assistants/OpenAI Codex CLI

OpenAI Codex CLI

OpenAI · cli agent · paid

Lightweight coding agent that runs in your terminal (Codex CLI).

agentcliopenaicodex
Is this coverage useful?

Helps prioritize which assistants and sources we maintain. Anonymous · one vote per visitor.

Config files OpenAI Codex CLI has changed

Config you own — hooks, permission rules, MCP servers, settings — that releases below state a change to. Counted from the release notes we track, newest change first. How a harness is layered.

skills and plugins2 changes · 4 releases touched it · latest Sep 3, 2026 · rust-v0.153.0 ↗
MCP server config1 change · 8 releases touched it · latest Jul 29, 2026 · rust-v0.146.0 ↗
sandbox settings1 change · 5 releases touched it · latest Aug 7, 2026 · rust-v0.147.0 ↗
permission rules1 change · 4 releases touched it · latest Aug 26, 2026 · rust-v0.150.0 ↗
agent context files1 change · latest Aug 26, 2026 · rust-v0.150.0 ↗

Release signals

OpenAI Codex CLIrust-v0.154.0-alpha.8Sep 8, 2026

alpha.8

Release 0.154.0-alpha.8Primary source ↗
OpenAI Codex CLIrust-v0.154.0-alpha.7Sep 8, 2026

alpha.7

Release 0.154.0-alpha.7Primary source ↗
OpenAI Codex CLIrust-v0.154.0-alpha.6Sep 7, 2026

alpha.6

Release 0.154.0-alpha.6Primary source ↗
OpenAI Codex CLIrust-v0.153.4Sep 4, 2026

Fixed Astra’s visibility in the bundled model picker and made it the bundled default when no model is explicitly configured. (#42874)

  • Updated Astra’s guidance to use asynchronous questions only when the tool is available in the session. (#42878)
  • #42874 [0.153 hotfix] Show Astra in bundled model picker @rhan-oai
  • #42878 [0.153 hotfix] Qualify Astra async-question guidance by tool availability @rhan-oai
Primary source ↗
OpenAI Codex CLIrust-v0.153.3Sep 4, 2026

Added GPT-6-Astra to the Amazon Bedrock model picker for Mantle and Runtime global/US routes. (#42805)

  • Corrected GPT-6-Astra’s guidance for asynchronous clarification questions to use the supported tool and recognize that it accepts text only. (#42809)
  • #42805 [0.153 hotfix] Add GPT-6-Astra to Amazon Bedrock catalogs @celia-oai
  • #42809 [0.153 hotfix] Update Astra async-question guidance @rhan-oai
Read the full release note

New Features

  • Added GPT-6-Astra to the Amazon Bedrock model picker for Mantle and Runtime global/US routes. (#42805)

Bug Fixes

  • Corrected GPT-6-Astra’s guidance for asynchronous clarification questions to use the supported tool and recognize that it accepts text only. (#42809)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.153.2...rust-v0.153.3

  • #42805 [0.153 hotfix] Add GPT-6-Astra to Amazon Bedrock catalogs @celia-oai

  • #42809 [0.153 hotfix] Update Astra async-question guidance @rhan-oai

Primary source ↗
OpenAI Codex CLIrust-v0.154.0-alpha.3Sep 4, 2026

alpha.3

Release 0.154.0-alpha.3Primary source ↗
OpenAI Codex CLIrust-v0.153.2Sep 3, 2026

Corrected the GPT-6-Astra Fast tier description to say “2x speed, increased usage” instead of “1.5x.” This changes only the displayed text, not how requests run. (#42632)

  • #42632 Fix GPT-6-Astra Fast tier description for 0.153.2 @anp-oai
Primary source ↗
OpenAI Codex CLIrust-v0.154.0-alpha.2Sep 3, 2026

alpha.2

Release 0.154.0-alpha.2Primary source ↗
OpenAI Codex CLIrust-v0.153.1Sep 3, 2026

Added support for configuring GPT-6-Astra through the API without changing the default model or showing it in the model picker. (#42605)

  • #42605 Backport GPT-6-Astra model catalog to 0.153 @anp-oai
Read the full release note

New Features

  • Added support for configuring GPT-6-Astra through the API without changing the default model or showing it in the model picker. (#42605)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.153.0...rust-v0.153.1

  • #42605 Backport GPT-6-Astra model catalog to 0.153 @anp-oai
Primary source ↗
OpenAI Codex CLIrust-v0.154.0-alpha.1Sep 3, 2026

alpha.1

Release 0.154.0-alpha.1Primary source ↗
OpenAI Codex CLIrust-v0.153.0Sep 3, 2026

Vim mode now supports undo with `u` and redo with `Ctrl+R`, preserving complete drafts including pasted content and attachments. ([#41941](https://github.com/openai/codex/pull/41941), [#42140](https://github.com/openai/codex/pull/42140))

  • The plugin CLI can list, install, and remove plugins from remote marketplaces. ([#42150](https://github.com/openai/codex/pull/42150))
  • Set `tui.auto_recap = false` to disable automatic recaps while keeping manual `/recap` available. ([#42101](https://github.com/openai/codex/pull/42101))
  • +99 more changes
Read the full release note

New Features

  • Vim mode now supports undo with u and redo with Ctrl+R, preserving complete drafts including pasted content and attachments. (#41941, #42140)

  • The plugin CLI can list, install, and remove plugins from remote marketplaces. (#42150)

  • Set tui.auto_recap = false to disable automatic recaps while keeping manual /recap available. (#42101)

  • TUI history shows complete patches, input sent to background terminals, and individual completed commands. (#41893, #42107)

  • Plus and Team users receive an earlier warning when less than half of their allowance remains in an approximately five-hour usage window. (#42142)

Bug Fixes

  • TUI sessions reconnect after an external app-server connection drops, preserving drafts and transcripts while keeping uncertain or queued submissions paused for review.

Excerpt ends here — this release continues at the source ↗.

Primary source ↗
OpenAI Codex CLIrust-v0.153.0-alpha.5.1Sep 3, 2026

alpha.5.1

Release 0.153.0-alpha.5.1Primary source ↗
OpenAI Codex CLIrust-v0.153.0-alpha.6Sep 2, 2026

alpha.6

Release 0.153.0-alpha.6Primary source ↗
OpenAI Codex CLIrust-v0.153.0-alpha.5Sep 2, 2026

alpha.5

Release 0.153.0-alpha.5Primary source ↗
OpenAI Codex CLIrust-v0.152.1Sep 1, 2026

Guardian approval review now honors Node REPL policies provided through model metadata.

Primary source ↗

Polled sources

[openai-developers] OpenAI Developers Codex

html · every 720m

https://developers.openai.com/codex

[github-releases] GitHub Releases

github_releases · every 60m

https://github.com/openai/codex/releases