前沿

OpenAI · 11-08 03:36

Release 0.169.0-alpha.3

OpenAI · 11-07 06:17

Release 0.169.0-alpha.2

OpenAI · 11-06 11:02

Release 0.169.0-alpha.1

OpenAI · 11-06 09:42

New Features Open the agent command center with codex agents --no-daemon . The command center and session picker now mark unread results ( #58238 , #58239 , #58263 , #58264 ). Swit

OpenAI · 11-06 07:00

Release 0.168.0-alpha.7

OpenAI · 11-06 04:00

Cult.fit is using Codex to help teams across functions build tools, move faster, and change how work gets done.

OpenAI · 11-06 03:57

Release 0.168.0-alpha.6

OpenAI · 11-06 01:06

Release 0.168.0-alpha.5

OpenAI · 11-05 21:21

Release 0.167.0-alpha.3.2

OpenAI · 11-05 19:20

Release 0.168.0-alpha.4

OpenAI · 11-05 16:00

Merge uses GPT-6 Astra, ChatGPT, and Codex to review product code and support marketing. Its teams also use AI to plan executive dinners and prepare sales updates.

OpenAI · 11-05 10:38

Release 0.168.0-alpha.3

OpenAI · 11-05 08:45

Flipsnack focused its ChatGPT Ads campaigns on getting people to try its product, growing registrations while lowering the cost per signup.

OpenAI · 11-05 04:53

Release 0.168.0-alpha.2

OpenAI · 11-05 03:10

Release 0.167.0-alpha.3.1

OpenAI · 11-04 22:30

OpenAI will acquire Pierre Computer Company, expanding Codex’s tools for building, understanding, and reviewing code.

OpenAI · 11-04 08:45

Release 0.167.0-alpha.5

OpenAI · 11-04 08:44

Release 0.168.0-alpha.1

Anthropic · 11-04 08:01

What's changed Added a record of your answer when Claude Code asks to turn on the mods it writes in a session Added assume_role on mantle upstreams of the Claude apps gateway, for

OpenAI · 11-04 08:00

Images 2.6 brings faster image generation, GIF creation, more precise editing, and new API controls across ChatGPT, Codex, and the API.

OpenAI · 11-04 07:04

Mirror of the unmodified libcap 2.75 source archive used to build Bubblewrap for Codex's Linux musl packages. Upstream archive SHA-256 for libcap-2.75.tar.xz is de4e7e064c9ba451d52

OpenAI · 11-03 20:00

Discover how ChatGPT and Codex are helping engineers accelerate CAD, PCB design, simulation, and other workflows across the physical world.

OpenAI · 11-03 16:00

Discover how Heimstaden uses OpenAI’s ChatGPT Enterprise and Codex to transform property management, cut costs, and empower employees across Europe.

OpenAI · 11-03 10:29

Release 0.167.0-alpha.4

Anthropic · 11-03 09:25

What's changed Added a warning to /schedule when a new cloud scheduled task gets connectors you did not ask for, with how to remove them Added a check that asks before a web or she

OpenAI · 11-02 23:30

How OpenAI built Pando, a Git-compatible backend designed for the scale of development that Codex makes possible.

OpenAI · 11-02 08:00

Qodo brings company knowledge and coding standards into Codex, helping developers catch P0 issues across repositories before opening a pull request.

OpenAI · 11-02 06:30

Release 0.167.0-alpha.3

OpenAI · 11-02 03:05

Release 0.167.0-alpha.2

s1dashu · 11-01 22:22

Blazing-fast native notes app for macOS & Windows. Rust + GPUI, local-first, compatible with Feishu/Lark DocxXML.

Anthropic · 10-31 09:01

What's changed Added CLAUDE_CODE_DISABLE_ULTRATHINK , which turns the ultrathink keyword off Added pooled group budgets to the Claude apps gateway: one monthly budget that a group'

OpenAI · 10-31 05:47

Release 0.167.0-alpha.1

Anthropic · 10-30 09:06

What's changed Added permissions.blockWritesOutsideWorkingDirectories : Write, Edit and NotebookEdit refuse paths outside the working directories in every permission mode Added an

OpenAI · 10-30 03:50

New Features Added keyboard-driven transcript selection with word, line, and page motions, integrated search, and configurable shortcuts. ( #57221 , #57222 , #57223 , #57224 ) Rend

OpenAI · 10-29 06:10

Release 0.166.0-alpha.6

OpenAI · 10-29 03:40

Evernote used ChatGPT Ads to introduce its note-taking app to people working with AI. The team tracked how often free trials led to paid subscriptions.

OpenAI · 10-29 03:25

Release 0.166.0-alpha.5.1

OpenAI · 10-28 21:15

OpenAI and ServiceNow expand their partnership to bring OpenAI models and agents into ServiceNow and ServiceNow workflows into ChatGPT and Codex.

OpenAI · 10-28 12:49

Release 0.166.0-alpha.5

OpenAI · 10-28 07:31

Release 0.166.0-alpha.4

Anthropic · 10-28 04:24

What's changed Added oidc.user_id_claim to the Claude apps gateway, to identify people by an id_token claim other than sub , such as Microsoft Entra ID's oid Added click to send: i

OpenAI · 10-28 03:32

Release 0.166.0-alpha.3

OpenAI · 10-27 20:03

Release 0.166.0-alpha.2

OpenAI · 10-27 13:04

Release 0.165.0-alpha.1.2

OpenAI · 10-27 08:40

Release 0.165.0-alpha.1.1

OpenAI · 10-27 08:01

Release 0.166.0-alpha.1

OpenAI · 10-27 05:58

Release 0.165.0-alpha.3

blakeandersonw · 10-27 00:07

How to build useful, profitable apps in 2026. Clone it and point your coding agent at AGENTS.md.

OpenAI · 10-26 23:40

Release 0.165.0-alpha.2

OpenAI · 10-26 15:00

See how OpenAI engineers use Codex Ultrafast to investigate incidents in minutes. Explore faster security analysis, code refactoring, and daily workflows.

andyhuo520 · 10-26 12:34

AI digital-human talking-head videos from one photo: Renoise MCP generation + 5 editing styles + 48 creator-grade packaging components. Agent skill for Claude Code / Codex / OpenCl

t3dotgg · 10-24 13:00

The agent skills I use every day. Works with Claude Code and Codex.

Anthropic · 10-24 07:39

What's changed Added the Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, and when telemetry or nonessential traffic is disabled; long foreground sleeps are now bl

OpenAI · 10-23 22:18

Release 0.165.0-alpha.1

OpenAI · 10-23 12:50

New Features Save reusable prompts and slash commands in ten numbered /presets slots, with a keyboard menu for quick access. ( #54380 , #54381 ) Set model, reasoning effort, speed,

OpenAI · 10-23 06:54

Release 0.164.0-alpha.11.1

OpenAI · 10-22 19:27

Release 0.164.0-alpha.12

OpenAI · 10-22 14:47

Release 0.163.0-alpha.11.2

Anthropic · 10-22 12:34

What's changed Bug fixes and reliability improvements

OpenAI · 10-22 12:31

Release 0.164.0-alpha.11

OpenAI · 10-22 08:13

Release 0.164.0-alpha.10

OpenAI · 10-22 06:23

Release 0.163.0-alpha.11.1

OpenAI · 10-21 22:19

Release 0.164.0-alpha.9

udhaykumarbala · 10-21 20:42

A community-built phone app for Clean Your TV: clean up an Android TV from your phone. No laptop, no coding agent, nothing uninstalled.

Anthropic · 10-21 11:16

What's changed Fixed claude -p inside cloud sessions reporting "Not logged in" when started without the session's environment variables Fixed an API error being replaced by "prompt

OpenAI · 10-21 08:00

Cloudflare uses OpenAI Daybreak to investigate vulnerabilities and propose fixes for review. Its developers use Codex to build faster and improve code quality.

OpenAI · 10-21 06:35

Release 0.164.0-alpha.8

Anthropic · 10-21 04:46

What's changed Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox'

OpenAI · 10-20 21:52

Release 0.164.0-alpha.7

OpenAI · 10-20 06:58

Release 0.164.0-alpha.6

Anthropic · 10-20 05:34

What's changed Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin Added decider: "person" to a mod's tool.check an

OpenAI · 10-19 22:33

Release 0.164.0-alpha.5

OpenAI · 10-19 18:48

Release 0.164.0-alpha.4

Anthropic · 10-19 06:26

What's changed Bug fixes and reliability improvements

OpenAI · 10-17 12:12

Release 0.164.0-alpha.3

Noniv · 10-17 07:49

Real-time WebGPU ocean renderer written from scratch, no engine. FFT waves, whitecaps, sun glitter, physically based sunset sky with clouds, free camera. Built with Claude Code (Op

Anthropic · 10-17 04:53

What's changed Added CLAUDE_CODE_AUTO_MODE_MODEL to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode Added an Idle

OpenAI · 10-17 01:39

Release 0.164.0-alpha.2

OpenAI · 10-16 23:00

Release 0.164.0-alpha.1

OpenAI · 10-16 08:00

Anant Kumar builds tools to compare loan valuations and analyze credit agreements, using Codex for code review and faster follow-ups.

OpenAI · 10-16 05:33

New Features Open /config to search preferences across categories, change supported settings immediately, and see which changes require a restart. ( #52990 , #53429 ) Send a follow

Anthropic · 10-16 03:22

What's changed Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS so unattended retry mode ( CLAUDE_CODE_RETRY_WATCHDOG ) ends a request at a usage limit that resets too far

OpenAI · 10-16 02:33

Release 0.163.0-alpha.10.2

OpenAI · 10-15 04:55

Release 0.163.0-alpha.10.1

Anthropic · 10-15 02:24

What's changed Added virtualText to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt Added cache_creation_5m_tokens and

OpenAI · 10-14 22:46

Release 0.163.0-alpha.13

OpenAI · 10-14 17:38

Release 0.163.0-alpha.12

OpenAI · 10-14 11:34

Release 0.163.0-alpha.11

Anthropic · 10-14 10:49

What's changed Added CLAUDE_CODE_DISABLE_FILE_MENTIONS environment variable: Claude gets the paths of @ file mentions to read with its file tools, not the files' contents Added idl

OpenAI · 10-14 03:12

Release 0.163.0-alpha.10

OpenAI · 10-13 23:52

Release 0.163.0-alpha.9

OpenAI · 10-13 21:44

Release 0.163.0-alpha.8

NVIDIA · 10-13 20:00

NVIDIA RTX Spark is a new beginning for the PC — a reinvention combining the capabilities of a gaming PC, a creative studio and a personal AI supercomputer into a single superchip.

OpenAI · 10-10 09:27

Release 0.163.0-alpha.6

OpenAI · 10-10 08:43

Release 0.163.0-alpha.5

OpenAI · 10-10 03:47

Bug Fixes Fixed a TUI crash when asynchronous questions contain multiple lines, preserving line breaks and complete hyperlink destinations. ( #51866 ) Fixed startup failures caused

Anthropic · 10-10 03:28

What's changed Added a code key to the Claude apps gateway's managed.policies[] : the same settings as cli , also applied in Claude Desktop's Code tab; beside desktop , it turns on

OpenAI · 10-09 21:45

Release 0.163.0-alpha.4

OpenAI · 10-09 08:18

Release 0.163.0-alpha.2

OpenAI · 10-09 05:24

Release 0.163.0-alpha.1

Anthropic · 10-09 03:48

What's changed Added onFailure: "block" for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it thr

OpenAI · 10-09 02:58

New Features Add tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled. ( #50148 ) Pin tasks in the agent Command C

OpenAI · 10-09

Across recruiting, engineering, and operations, Oracle turns specialist knowledge into fast, repeatable workflows with ChatGPT Work and Codex.

OpenAI · 10-08 20:00

LegalOn cut estimated daily Codex costs by 65% while maintaining development speed. It matched Astra, Sol, and Luna to tasks and managed budgets strategically.

OpenAI · 10-08 15:43

Release 0.162.0-alpha.17.2

Anthropic · 10-08 13:03

What's changed Fixed prompt and agent hooks written as instructions (such as "Block commands that...") allowing what they should block Improved how prompt hooks on Stop and Subagen

OpenAI · 10-08 10:58

Release 0.162.0-alpha.18.1

OpenAI · 10-08 08:51

Release 0.162.0-alpha.20

OpenAI · 10-08 08:13

Release 0.162.0-alpha.19

OpenAI · 10-08 08:07

Release 0.162.0-alpha.17.1

Anthropic · 10-08 02:10

What's changed Added Claude Haiku 5.5 ( claude-haiku-5-5 ), now the default Haiku model on the Anthropic API — 1M context, $0.10/$0.50 per Mtok ($0.50/$2.50 for prompts over 100K)

OpenAI · 10-07 10:16

Release 0.162.0-alpha.18

OpenAI · 10-07 06:09

Release 0.162.0-alpha.17

Anthropic · 10-07 02:59

What's changed Added --marketplace <source> to claude plugin install : adds the marketplace if needed, under the same policy checks as claude plugin marketplace add , then in

OpenAI · 10-06 13:38

Release 0.161.0-alpha.13.1

Anthropic · 10-06 11:55

What's changed Fixed a regression in 2.1.290 where cloud sessions could drop answers to permission prompts Fixed a regression in 2.1.288 where the last messages of a session could

Anthropic · 10-06 07:33

What's changed Added serverToolUses to the result of a mod's turn.step hook: the tool calls the API ran itself (the advisor), each with its id, name, input, start and end Added age

OpenAI · 10-06 05:50

Release 0.162.0-alpha.16

OpenAI · 10-05 21:23

Release 0.162.0-alpha.15

OpenAI · 10-05 10:17

Release 0.162.0-alpha.14

OpenAI · 10-04 23:51

Release 0.162.0-alpha.13

OpenAI · 10-04 13:58

Release 0.162.0-alpha.12

Anthropic · 10-04 07:07

What's changed Fixed a deny or ask rule on a nested part of a compound shell command not holding over a user-installed mod's approval on managed machines Fixed the terminal freezin

OpenAI · 10-04 04:21

Release 0.162.0-alpha.11

OpenAI · 10-03 18:08

Release 0.162.0-alpha.10

OpenAI · 10-03 08:23

Release 0.162.0-alpha.9

OpenAI · 10-03 06:51

Release 0.162.0-alpha.8

OpenAI · 10-03 01:06

Release 0.162.0-alpha.7

OpenAI · 10-02 19:55

Release 0.162.0-alpha.6

OpenAI · 10-02 16:22

Release 0.162.0-alpha.5

OpenAI · 10-02 13:54

Release 0.162.0-alpha.4

OpenAI · 10-02 11:50

Release 0.162.0-alpha.3

OpenAI · 10-02 08:51

Release 0.162.0-alpha.2

OpenAI · 10-02 08:00

Chatham Financial uses Codex and GPT-5.6 to build technology and redesign workflows, cutting trade validation from 30 minutes to under 4.

OpenAI · 10-02 07:13

Release 0.162.0-alpha.1

OpenAI · 10-02 00:47

Release 0.161.0-alpha.13

OpenAI · 10-01 22:54

Release 0.161.0-alpha.12

OpenAI · 10-01 20:32

Release 0.161.0-alpha.11

OpenAI · 10-01 18:40

Release 0.161.0-alpha.10

OpenAI · 10-01 16:46

Release 0.161.0-alpha.9

OpenAI · 10-01 14:36

Release 0.161.0-alpha.8

OpenAI · 10-01 12:03

Release 0.161.0-alpha.7

OpenAI · 10-01 10:43

Release 0.161.0-alpha.6

OpenAI · 10-01 08:20

Release 0.160.0-alpha.6.2

OpenAI · 10-01 06:59

New Features Eligible local sessions signed in with ChatGPT can now show optional reminders to complete account security setup. ( #49744 ) Changelog Full Changelog: rust-v0.159.2..

OpenAI · 10-01 04:11

Release 0.161.0-alpha.5

Anthropic · 10-01 03:10

What's changed Added a count such as "2 of 5" to the permission prompt when several permission requests stack up Added mouse support for the "N more" rows of lists in fullscreen mo

OpenAI · 09-30 19:58

Release 0.161.0-alpha.4

rehan-remade · 09-30 13:00

Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing

OpenAI · 09-30 10:39

Release 0.161.0-alpha.3

OpenAI · 09-30 08:07

Release 0.160.0-alpha.6.1

OpenAI · 09-30 08:00

Bug Fixes Suppressed console windows flashing on Windows when Codex launches background processes and sandboxed commands. ( #49385 ) Changelog Full Changelog: rust-v0.159.1...rust-

OpenAI · 09-30 04:34

New Features Added GPT-6.1 Sol as the default model in the bundled catalog and Amazon Bedrock Mantle and Runtime catalogs. ( #49323 , #49342 ) Changelog Full Changelog: rust-v0.159

OpenAI · 09-30 02:41

Release 0.161.0-alpha.2

OpenAI · 09-30 00:33

Release 0.161.0-alpha.1

OpenAI · 09-29 18:00

Explore more than 20 announcements from OpenAI DevDay 2026, including GPT-6 Astra, ChatGPT, Codex, APIs, security, and new tools for builders.

OpenAI · 09-29 16:07

New Features Opt-in instant_interrupt lets new input steer Codex during model responses or long-running code-mode calls. ( #48135 , #48141 ) New sessions get a compact welcome scre

OpenAI · 09-29 14:39

Release 0.160.0-alpha.6

OpenAI · 09-29 13:03

Release 0.160.0-alpha.5

OpenAI · 09-29 12:31

Release 0.160.0-alpha.4

OpenAI · 09-29 06:33

Release 0.160.0-alpha.3

OpenAI · 09-29 04:04

Release 0.160.0-alpha.2

Anthropic · 09-29 02:02

What's changed Added Claude Sonnet 5.5 ( claude-sonnet-5-5 ), now the default Sonnet model on the Anthropic API — 1M context, $2/$10 per Mtok with $0.20/Mtok cache reads Added a "Y

OpenAI · 09-28 23:32

Release 0.159.0-alpha.13

OpenAI · 09-28 13:10

New Features Configure copy-on-select and right-click paste in the fullscreen TUI. Copied transcript selections now preserve Markdown formatting. ( #47639 , #47896 , #48118 ) Conne

OpenAI · 09-28 12:01

Release 0.160.0-alpha.1

OpenAI · 09-28 11:27

Release 0.159.0-alpha.12

OpenAI · 09-28 09:58

Release 0.158.0-alpha.15.4

OpenAI · 09-28 08:29

Release 0.159.0-alpha.11

OpenAI · 09-28 08:00

We’re collecting real stories of builders, tinkerers, researchers, and creators who are using Codex to do incredible things. If you want to be a part of the next chapter of the Cod

OpenAI · 09-28 05:18

Release 0.159.0-alpha.10

OpenAI · 09-28 03:30

Release 0.158.0-alpha.15.3

OpenAI · 09-27 14:48

Release 0.159.0-alpha.9

OpenAI · 09-27 12:58

Release 0.159.0-alpha.8

OpenAI · 09-27 08:33

Release 0.159.0-alpha.7

OpenAI · 09-27 08:12

Release 0.158.0-alpha.15.2

OpenAI · 09-27 04:19

Release 0.159.0-alpha.6

OpenAI · 09-27 01:42

Release 0.159.0-alpha.5

OpenAI · 09-26 14:31

Release 0.159.0-alpha.4

OpenAI · 09-26 13:01

Release 0.158.0-alpha.2.1

OpenAI · 09-26 11:09

Release 0.158.0-alpha.15.1

OpenAI · 09-26 05:52

Release 0.159.0-alpha.3

Anthropic · 09-26 05:50

What's changed Added x-claude-code-prompt-id to the gateway hint headers so LLM gateways can group the requests that serve one user prompt; opt in with CLAUDE_CODE_GATEWAY_HINT_HEA

OpenAI · 09-26 04:30

Release 0.159.0-alpha.2

OpenAI · 09-26 03:00

With Codex, GPT-Live-1, and GPT-6 Astra, Proaction builds, operates, and sells modern fleet management faster.

OpenAI · 09-26 02:58

Release 0.159.0-alpha.1

OpenAI · 09-26 01:42

Release 0.158.0-alpha.15

OpenAI · 09-25 21:02

Release 0.158.0-alpha.14

Microsoft · 09-25 20:03

We’re reimagining Microsoft Copilot to enable work as it evolves and to help expand what every individual and every organization can accomplish in the flow of human ambition. Today

OpenAI · 09-25 12:38

Release 0.158.0-alpha.13

OpenAI · 09-25 10:32

New Features Added GPT-6 Sol and Luna, including Amazon Bedrock support and migration prompts for older models. ( #47332 , #47347 ) Enabled fullscreen transcripts by default and ad

OpenAI · 09-25 07:53

Release 0.158.0-alpha.12

OpenAI · 09-25 07:32

Release 0.158.0-alpha.11

OpenAI · 09-25 06:03

Release 0.157.0-alpha.11.1

OpenAI · 09-25 05:09

Release 0.158.0-alpha.10

Anthropic · 09-25 02:38

What's changed Added a maxProseWidth setting that caps the width of Claude's prose in wide terminals while tables and code blocks keep the full width Added a startup notice, and /s

OpenAI · 09-25 02:02

Release 0.158.0-alpha.9

OpenAI · 09-24 15:20

Release 0.158.0-alpha.8

OpenAI · 09-24 13:37

Release 0.158.0-alpha.7

OpenAI · 09-24 07:51

Release 0.158.0-alpha.6

OpenAI · 09-24 06:25

Release 0.158.0-alpha.5

OpenAI · 09-24 03:58

Release 0.155.0-alpha.16.4

Anthropic · 09-24 03:19

What's changed Added Claude apps gateway support for newer Claude Desktop keys in desktop policy blocks, including blockReadsOutsideWorkingDirectories and disableBypassPermissionsM

OpenAI · 09-24 02:49

Release 0.158.0-alpha.4

OpenAI · 09-24 01:21

Release 0.158.0-alpha.3

OpenAI · 09-23 21:19

Release 0.158.0-alpha.2

OpenAI · 09-23 18:48

Release 0.158.0-alpha.1

OpenAI · 09-23 12:59

Release 0.157.0-alpha.11

OpenAI · 09-23 11:45

Release 0.155.0-alpha.16.3

OpenAI · 09-23 10:43

New Features Choose GPT-6 Sol or GPT-6 Luna from the model picker. The rate-limit switch prompt now recommends GPT-6 Luna. ( #47405 ) Changelog Full Changelog: rust-v0.156.0...rust

OpenAI · 09-23 06:16

Release 0.157.0-alpha.10

OpenAI · 09-23 03:53

New Features Choose an optional fullscreen UI with /tui for your next launch, including transcript search, mouse selection, and right-click copying. ( #46732 , #46734 , #46883 , #4

OpenAI · 09-23 02:13

Release 0.157.0-alpha.9

Anthropic · 09-23 00:38

What's changed Added Claude Opus 5.5 ( claude-opus-5-5 ), now the default Opus model — 1M context, $4/$20 per Mtok with $0.20/Mtok cache reads Added mouse support to more lists in

OpenAI · 09-22 20:45

Release 0.157.0-alpha.8

OpenAI · 09-22 15:08

Release 0.157.0-alpha.7

OpenAI · 09-22 14:00

Release 0.157.0-alpha.6

OpenAI · 09-22 12:38

Release 0.157.0-alpha.5

OpenAI · 09-22 11:12

Release 0.157.0-alpha.4

OpenAI · 09-22 08:39

Release 0.157.0-alpha.3

OpenAI · 09-22 08:24

Release 0.155.0-alpha.16.1

OpenAI · 09-22 07:14

Release 0.157.0-alpha.2

OpenAI · 09-22 05:49

Release 0.156.0-alpha.17

OpenAI · 09-22 02:21

Release 0.157.0-alpha.1

OpenAI · 09-22 01:02

Release 0.156.0-alpha.16

OpenAI · 09-21 21:32

Release 0.156.0-alpha.15

OpenAI · 09-21 12:20

Release 0.156.0-alpha.14

OpenAI · 09-21 08:29

Release 0.156.0-alpha.13

OpenAI · 09-21 08:17

Release 0.156.0-alpha.12

OpenAI · 09-21 06:58

Release 0.156.0-alpha.11

OpenAI · 09-21 05:29

Release 0.156.0-alpha.10

OpenAI · 09-20 08:25

Release 0.156.0-alpha.9

OpenAI · 09-20 01:31

Release 0.156.0-alpha.8

OpenAI · 09-19 12:19

Release 0.156.0-alpha.7

Anthropic · 09-19 11:10

What's changed Changed auto mode for Claude API and Enterprise users, and on Bedrock, Vertex, Foundry and gateways, to default to the server-side classifier, which does not charge

OpenAI · 09-19 10:30

Release 0.156.0-alpha.6

OpenAI · 09-19 08:31

Release 0.156.0-alpha.5

OpenAI · 09-19 05:29

Release 0.156.0-alpha.4

OpenAI · 09-19 04:05

Bug Fixes New local TUI sessions now leave reasoning summaries disabled by default, fixing request rejection by providers that do not support them. Explicit reasoning-summary setti

OpenAI · 09-19 02:31

Release 0.156.0-alpha.3

Anthropic · 09-19 02:06

What's changed Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead; change it under "Project instructions" in /config (not yet on Bedrock,

OpenAI · 09-18 13:04

Release 0.156.0-alpha.2

OpenAI · 09-18 11:13

Release 0.155.0-alpha.9.2

Anthropic · 09-18 10:12

What's changed Fixed every request failing with 400 … Input tag 'advisor_20260301' when ANTHROPIC_BASE_URL points at a proxy or gateway (2.1.275 regression)

OpenAI · 09-18 08:31

Release 0.156.0-alpha.1

OpenAI · 09-18 07:16

New Features Added experimental /voice conversations with live transcripts and microphone controls on supported builds, enabled through /experimental . ( #43581 , #43651 , #44331 )

OpenAI · 09-18 06:49

Release 0.155.0-alpha.18

Anthropic · 09-18 06:33

What's changed Added the signed-in account to Claude apps gateway sign-in: when the gateway names it, you confirm it before the credential is saved, and /status shows it Added a se

OpenAI · 09-18 05:19

Release 0.155.0-alpha.17

OpenAI · 09-17 12:37

Release 0.155.0-alpha.16

OpenAI · 09-17 08:33

Release 0.155.0-alpha.15

Anthropic · 09-17 08:12

What's changed Added a visible warning when memory usage is critical, with steps to free memory or restart safely Added CLAUDE_CODE_MCP_STARTUP_WAIT_MS to bound how long the first

OpenAI · 09-17 07:09

Release 0.155.0-alpha.14

OpenAI · 09-17 05:46

Release 0.155.0-alpha.13

OpenAI · 09-17 04:06

Release 0.155.0-alpha.2.6

OpenAI · 09-17 02:29

Release 0.155.0-alpha.12

OpenAI · 09-17 01:16

Release 0.155.0-alpha.11

OpenAI · 09-16 21:19

Release 0.155.0-alpha.2.5

OpenAI · 09-16 20:00

Learn how ChatGPT Work and Codex analytics help teams understand AI usage and spend, identify training needs, and connect adoption to business outcomes.

OpenAI · 09-16 12:23

Release 0.155.0-alpha.10

OpenAI · 09-16 08:37

Release 0.155.0-alpha.9

OpenAI · 09-16 06:29

Release 0.155.0-alpha.8

OpenAI · 09-16 05:12

Release 0.155.0-alpha.7

Anthropic · 09-16 04:23

What's changed Added x-claude-code-request-class , x-claude-code-agent-type , x-claude-code-prev-tool-durations , x-claude-code-compaction and x-claude-code-context-compacted reque

OpenAI · 09-15 10:02

Release 0.155.0-alpha.6

Anthropic · 09-15 08:42

What's changed Bug fixes and reliability improvements

OpenAI · 09-15 08:33

Release 0.155.0-alpha.5

OpenAI · 09-15 07:05

Release 0.155.0-alpha.2.4

Anthropic · 09-15 06:12

What's changed Added fast mode in Claude Code Remote sessions (cloud and self-hosted runners): the host's fast-mode setting or /fast typed in the session applies where your organiz

OpenAI · 09-14 19:49

Release 0.155.0-alpha.4

Anthropic · 09-13 03:45

What's changed Fixed read-only git commands in Bash unexpectedly asking for permission after a session had been running for a while (regression in 2.1.269)

Anthropic · 09-12 03:17

What's changed Added claude plugin eval : run a plugin's eval suite against Claude Code and get scored, reproducible results (JSON + HTML report); see claude plugin eval --help Add

OpenAI · 09-11 23:56

Release 0.155.0-alpha.3.10

OpenAI · 09-11 20:01

Release 0.155.0-alpha.3.9

OpenAI · 09-11 18:30

Release 0.155.0-alpha.3.8

OpenAI · 09-11 16:17

Release 0.155.0-alpha.3.7

OpenAI · 09-11 14:08

Release 0.155.0-alpha.3.6

OpenAI · 09-11 13:07

Release 0.155.0-alpha.3.5

OpenAI · 09-11 12:44

Release 0.155.0-alpha.3.4

OpenAI · 09-11 12:23

Release 0.155.0-alpha.3.3

OpenAI · 09-11 12:11

Release 0.155.0-alpha.3.2

OpenAI · 09-11 11:17

Release 0.155.0-alpha.3.1

OpenAI · 09-11 08:35

Release 0.154.0-alpha.6.2

OpenAI · 09-11 08:31

Release 0.155.0-alpha.2.3

Anthropic · 09-11 04:30

What's changed Added to the Claude apps gateway: with pricing: set in gateway.yaml , signed-in Claude Code clients receive the same rates through managed settings, so /cost and tel

OpenAI · 09-11 04:23

Release 0.155.0-alpha.2.2

OpenAI · 09-11 04:19

CI-only build tools for native Windows voice releases. These archives are not included in Codex user packages. cygwin-build-inputs.tar.gz : 103 pinned Cygwin binary packages and th

OpenAI · 09-11 02:51

Release 0.155.0-alpha.2.1

OpenAI · 09-11 02:06

Release 0.155.0-alpha.2

OpenAI · 09-11

César de la Fuente’s lab uses Codex and ChatGPT to search living and extinct genomes for antimicrobial candidates to fight drug-resistant infections.

OpenAI · 09-10 19:56

Release 0.155.0-alpha.1

OpenAI · 09-10 06:37

New Features GPT-6-Astra is now available in the model picker and Amazon Bedrock catalogs. ( #42879 , #42619 ) Experimental worktree support lets you create isolated checkouts for

Anthropic · 09-10 03:58

What's changed Added maxEffortLevel setting (top-level or per model under modelSettings ): caps the effort level on every provider, including Bedrock, Vertex and Foundry; users can

OpenAI · 09-09 19:54

Release 0.154.0-alpha.6.1

OpenAI · 09-09 17:17

Release 0.154.0-alpha.11

OpenAI · 09-09 15:58

Release 0.154.0-alpha.10.2

OpenAI · 09-09 14:08

Release 0.154.0-alpha.10.1

OpenAI · 09-09 13:23

Release 0.154.0-alpha.10

OpenAI · 09-09 13:06

Release 0.154.0-alpha.8.1

OpenAI · 09-09 10:21

Release 0.154.0-alpha.9

Anthropic · 09-09 07:55

What's changed Fixed a 2.1.265 regression affecting LLM-gateway and proxy setups: the undocumented CLAUDE_CODE_USE_GATEWAY environment variable, previously ignored unless ANTHROPIC

OpenAI · 09-09 07:19

Release 0.154.0-alpha.8

Anthropic · 09-09 04:37

What's changed Added user.email and user.groups to the telemetry Claude Desktop and Cowork send through a Claude apps gateway, matching terminal sessions Added support for pointing

OpenAI · 09-09 01:47

Release 0.154.0-alpha.7

OpenAI · 09-08 08:00

Engineers at 1Password use Codex to rapidly build new features and internal tools, reaching production-readiness while maintaining rigorous security policies.

OpenAI · 09-08 02:06

Release 0.154.0-alpha.6

Anthropic · 09-06 10:54

What's changed Bug fixes and reliability improvements

OpenAI · 09-05 08:59

Release 0.154.0-alpha.4

OpenAI · 09-05 07:27

Bug Fixes 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 as

Anthropic · 09-05 03:58

What's changed Added an "Organization policy" line to /status and claude doctor that says why your organization's policy could not be loaded, such as a proxy not passing the endpoi

OpenAI · 09-05 03:02

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 cl

OpenAI · 09-04 09:01

Release 0.154.0-alpha.3

OpenAI · 09-04 07:54

Bug Fixes 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

Anthropic · 09-04 07:48

What's changed Added a diff panel that opens beside the conversation in fullscreen mode and shows your uncommitted changes as Claude edits; toggle it with /diff Added a likely caus

OpenAI · 09-04 06:01

Release 0.154.0-alpha.2

OpenAI · 09-04 05:05

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: ru

OpenAI · 09-03 17:33

Release 0.154.0-alpha.1

OpenAI · 09-03 09:39

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 li

Anthropic · 09-03 06:33

What's changed Added managedMcpServers managed setting: organizations can provide HTTP/SSE MCP servers to every user (same entry shape as .mcp.json ); entries that name a command t

OpenAI · 09-02 19:29

Release 0.153.0-alpha.6

Anthropic · 09-02 06:33

What's changed Fixed Claude Code failing to launch on macOS 12 (Monterey), a regression introduced in 2.1.255 Fixed remote and scheduled sessions failing with "user messages must h

Anthropic · 09-02 01:53

What's changed Added Claude Fable 5.1 ( claude-fable-5-1 ), now the default Fable model — 1M context, $10/$50 per Mtok with $0.25/Mtok cache reads Added "Time format" ( timeFormat

Google · 09-02

Built on our latest Nano Banana model, Google Pics — our image creation and editing tool — is now available.

OpenAI · 09-01 09:00

See how Gilbert + Tobin combines CEO-led commitment, rigorous governance, and human accountability to scale ChatGPT Enterprise and Codex across the firm.

Anthropic · 09-01 03:46

What's changed Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs Fixed "always allow" not saving in a project that has no .claude

OpenAI · 08-31 15:00

Polimill uses OpenAI GPT models and Codex to help municipalities search and use administrative knowledge while accelerating development.

Anthropic · 08-29 02:19

What's changed Added PreModelSwitch and PostModelSwitch hook events (block, confirm, or annotate a model switch); SessionStart resume hooks now receive session staleness and the es