Tag
Codex
Codex is OpenAI’s coding agent and toolchain, spanning CLI workflows, plugins, sandboxed execution, and auth/network controls. This tag covers quota changes, MCP integration, and how teams use it to automate coding, PR review, and deployment.
29 articles

Public Sentry keys can hijack Claude Code and Cursor
Researchers showed a public Sentry key can be abused to feed malicious MCP data into Claude Code, Cursor, and Codex.

优刻得沙箱把远程开发环境搭建到几秒内
5个优刻得沙箱用法,帮你快速搭建可暂停、可恢复、可克隆的远程开发环境。

Codex日志bug把SSD写废了怎么办
我拆开这篇知乎,讲Codex日志写爆SSD的根因、风险和可直接套用的限流修复模板。

Sia’s OpenAI partnership is a sign enterprise AI is becoming a servic…
Sia’s OpenAI partnership shows enterprise AI is now won by implementation partners, not tool demos.

OpenAI’s June 2026 push spans agents, payments, and legal heat
OpenAI’s June 2026 news mix shows a company scaling agents, entering payments, and facing fresh legal and regulatory pressure.

OpenAI’s Ona buy adds more reach to Codex
1 acquisition could help OpenAI’s Codex handle longer tasks, as the assistant tops 5 million weekly active users.

Claude Code, Cursor, and Copilot set the 2026 bar
6 AI coding agents dominate 2026 reviews, with developers weighing cost, repo context, privacy, and real productivity gains.

Codex brings ChatGPT into work and code tasks
Codex in ChatGPT helps teams turn work data, code tasks, and follow-ups into faster drafts and summaries.

Codex 0.139.0 adds web search and cleaner tooling
Codex 0.139.0 adds standalone web search, richer tool schemas, and fewer TUI and sandbox bugs.

Opus 4.8 is the best model in the benchmark, not the default
Claude Opus 4.8 tops Nate’s benchmark, but it should stay a specialist, not the default model.

OpenAI’s latest moves now center on pricing, safety, and scale
4 OpenAI shifts to watch now: GPT-5.5 pricing, ChatGPT lockdown mode, Codex expansion, and a possible IPO push.

4 AWS变化 for OpenAI用户
4个AWS变化看OpenAI企业分发:模型与Codex上架、统一账单、合规采购、云渠道扩展。

5 steps to connect Codex with DeepSeek
5 steps to route Codex through DeepSeek with CCX and CC Switch, plus the setup details that make it work.

How to understand the Codex and ChatGPT merge
This guide explains how to evaluate the Codex and ChatGPT app merge as one workflow.

Codex’s workspace limits now tell you why
OpenAI Codex now shows workspace-specific usage-limit messages for credit and spend-cap failures.

ChatGPT updates turn into a June 2026 playbook
A developer-style breakdown of June 2026 ChatGPT updates, with a copy-ready template for release-note analysis.

Why Grok Build is not ready to replace Claude Code
Grok Build is a credible new coding tool, but it is not ready to replace Claude Code or Codex.

5 个 Codex 新功能看 OpenAI 方向
5 个 Codex 更新与一项 PowerPoint 测试,说明 OpenAI 正把 AI 变成能长期干活的工作伙伴。

AWS turns Bedrock into an OpenAI control plane
AWS folded OpenAI models, Codex, and managed agents into Bedrock so teams can ship AI work inside AWS controls.

Figma puts an AI agent inside its canvas
Figma added an AI agent to its canvas so designers can generate, edit, and iterate on layouts with text prompts.

3 routes for AI PPT creation
3 ways to make AI slides, from prompt-first tools to open-source skills and local workflows.

5 shifts in LLMs from the last six months
5 shifts explain why LLMs changed fast over six months: better coding agents, stronger open models, and new local workflows.

Why Docker’s microVM sandboxes are the right move for AI agents
Docker is right to use microVM sandboxes for autonomous AI agents because containers are too weak a boundary for root-level code execution.

OpenAI Codex Cuts Quota: When Pro Membership Pays Off
OpenAI 调整了 Codex 额度和 Pro 会员权益。本文教你怎么看最新额度、价格变化和实际影响。

OpenAI’s Codex Plugin Lands in Claude Code
OpenAI shipped a Codex plugin for Claude Code on March 30, putting its coding agent inside Anthropic’s terminal tool.

From Prompting to Harness Engineering
OpenAI says one team shipped a 1M-line product with 3 engineers and Codex, merging about 1,500 PRs in 5 months.

OpenAI’s April 2026 updates: Codex gets tighter
OpenAI’s latest Codex release adds proxy-only networking, device-code login, dynamic auth tokens, and more reliable sandbox behavior.

Figma Opens Its Canvas to AI Agents
Figma’s beta MCP server lets agents edit files directly, with skills and design-system context to keep AI output on brand.

OpenAI’s plan for an automated AI researcher
OpenAI wants an autonomous research intern by September and a multi-agent AI researcher by 2028, but errors still pile up fast.