[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-codex-openai-coding-agent-real-work-en":3,"article-related-codex-openai-coding-agent-real-work-en":32,"series-industry-18bc1f11-955c-4b08-aca6-0b3d19d7a3f0":79},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":24,"views":28,"created_at":29,"published_at":30,"topic_cluster_id":31},"18bc1f11-955c-4b08-aca6-0b3d19d7a3f0","codex-openai-coding-agent-real-work-en","Codex is OpenAI’s coding agent for real work","\u003Cp data-speakable=\"summary\">\u003Ca href=\"\u002Ftag\u002Fcodex\">Codex\u003C\u002Fa> is \u003Ca href=\"\u002Ftag\u002Fopenai\">OpenAI\u003C\u002Fa>’s coding \u003Ca href=\"\u002Ftag\u002Fagent\">agent\u003C\u002Fa> for editing repos, running tests, and reviewing changes in cloud sandboxes.\u003C\u002Fp>\u003Cp>OpenAI’s Codex is not just another chat tool: it runs tasks in isolated cloud environments, and by March 2026 it had passed 2 million weekly active users. Here are the five parts that matter most if you want to understand what it does, where it runs, and how it differs from a normal assistant.\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>Item\u003C\u002Fth>\u003Cth>What it does\u003C\u002Fth>\u003Cth>Notable detail\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>Codex Cloud\u003C\u002Ftd>\u003Ctd>Web-based coding agent\u003C\u002Ftd>\u003Ctd>Launched in May 2025\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Codex CLI\u003C\u002Ftd>\u003Ctd>Terminal workflow\u003C\u002Ftd>\u003Ctd>Open source, released in April 2025\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Desktop app\u003C\u002Ftd>\u003Ctd>Long-running agent control\u003C\u002Ftd>\u003Ctd>Windows and macOS support\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>GPT-5.3-Codex-Spark\u003C\u002Ftd>\u003Ctd>Low-latency model\u003C\u002Ftd>\u003Ctd>About 15x faster than earlier versions\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Codex Security\u003C\u002Ftd>\u003Ctd>App security scanning\u003C\u002Ftd>\u003Ctd>Announced in March 2026\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>1. Codex Cloud\u003C\u002Fh2>\u003Cp>\u003Ca href=\"https:\u002F\u002Fchatgpt.com\u002Fcodex\">Codex Cloud\u003C\u002Fa> is the core experience most people mean when they talk about Codex. Each task gets its own cloud environment with the user’s repository already loaded, so the agent can read files, edit code, run tests, and call other code-checking tools without waiting on \u003Ca href=\"\u002Fnews\u002Fkimi-k2-5-local-setup-ollama-docker-en\">local setup\u003C\u002Fa>.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782900170418-bnnh.png\" alt=\"Codex is OpenAI’s coding agent for real work\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>That design makes it feel less like a chat window and more like a worker assigned to a repo. It can handle a task on its own, then return command logs and test results for review, which is useful when you want proof of \u003Ca href=\"\u002Fnews\u002Fandroid-june-2026-google-system-updates-en\">what changed\u003C\u002Fa> and why.\u003C\u002Fp>\u003Cul>\u003Cli>Best for bug fixes, feature work, and code review prep\u003C\u002Fli>\u003Cli>Most tasks take 1 to 30 minutes\u003C\u002Fli>\u003Cli>Initially launched with no general internet access\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>2. Codex CLI\u003C\u002Fh2>\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex\">Codex CLI\u003C\u002Fa> brought the agent into the terminal in April 2025. OpenAI released it as an open-source tool for developers who prefer command-line workflows and want the agent close to their local projects and scripts.\u003C\u002Fp>\u003Cp>The CLI matters because it is the most direct path for power users. Instead of moving between browser tabs, you can stay in your shell, hand off coding tasks, and inspect outputs in the same place you already build and test software.\u003C\u002Fp>\u003Cul>\u003Cli>Open source on GitHub\u003C\u002Fli>\u003Cli>Fits terminal-first workflows\u003C\u002Fli>\u003Cli>Useful for quick repo-level edits and checks\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>3. Desktop app for Windows and macOS\u003C\u002Fh2>\u003Cp>The desktop app, released in February 2026, was built for longer sessions and for managing multiple coding agents at once. OpenAI made it available on \u003Ca href=\"https:\u002F\u002Fwww.microsoft.com\u002Fwindows\">Windows\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fwww.apple.com\u002Fmacos\u002F\">macOS\u003C\u002Fa>, with the stated goal of helping users use code to gather or analyze information as well as write software.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782900173585-2fbe.png\" alt=\"Codex is OpenAI’s coding agent for real work\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>It also marked a shift toward a more unified workflow. By March 2026, OpenAI was folding the \u003Ca href=\"\u002Ftag\u002Fchatgpt\">ChatGPT\u003C\u002Fa> computer app, Codex, and ChatGPT Atlas into a single desktop product plan, which showed that the company wanted one place for agent work instead of separate tools.\u003C\u002Fp>\u003Cul>\u003Cli>Supports longer-running agent sessions\u003C\u002Fli>\u003Cli>Built for multiple concurrent coding tasks\u003C\u002Fli>\u003Cli>Includes native Windows PowerShell support\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>4. GPT-5.3-Codex-Spark\u003C\u002Fh2>\u003Cp>OpenAI updated the Codex model stack in February 2026 with GPT-5.3-Codex, then GPT-5.3-Codex-Spark a week later. Spark was the lower-latency option for interactive coding, and InfoQ reported that it ran about 15 times faster than earlier Codex versions.\u003C\u002Fp>\u003Cp>For many users, this is the most important performance change in the whole product line. Faster response times make the agent easier to use in live coding sessions, where waiting around can break the flow of debugging, pair programming, or rapid iteration.\u003C\u002Fp>\u003Cul>\u003Cli>Lower latency than earlier Codex models\u003C\u002Fli>\u003Cli>First production model OpenAI deployed on Cerebras hardware\u003C\u002Fli>\u003Cli>Better fit for real-time coding than batch tasks\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>5. Codex Security\u003C\u002Fh2>\u003Cp>\u003Ca href=\"https:\u002F\u002Fopenai.com\u002Findex\u002Fcodex-security\u002F\">Codex Security\u003C\u002Fa> arrived in March 2026 as a separate application-security agent. Instead of writing features, it builds a threat model for a repository, looks for vulnerabilities, validates suspected issues in sandboxed environments, and proposes fixes.\u003C\u002Fp>\u003Cp>OpenAI said it tested the tool on 1.2 million commits over 30 days and found nearly 800 critical vulnerabilities plus more than 10,000 high-severity issues. That puts the product in a different category from the main coding agent: it is aimed at security review, not just implementation work.\u003C\u002Fp>\u003Cul>\u003Cli>Designed to find and fix software vulnerabilities\u003C\u002Fli>\u003Cli>Reported to cut false positives by more than 50 percent in beta\u003C\u002Fli>\u003Cli>Found issues in projects including Chromium, OpenSSL, and PHP\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>How to decide\u003C\u002Fh2>\u003Cp>If you want the broadest day-to-day coding assistant, start with Codex Cloud. If you live in the terminal, the CLI is the cleaner fit. If you manage long projects or multiple agents, the desktop app is the better control center.\u003C\u002Fp>\u003Cp>If speed matters most, GPT-5.3-Codex-Spark is the key model to watch. If your job is security review rather than feature work, Codex Security is the version built for that use case.\u003C\u002Fp>","Codex is OpenAI’s coding agent, built to edit repos, run tests, and review changes in cloud sandboxes.","en.wikipedia.org","https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FCodex_(AI_agent)",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782900170418-bnnh.png","industry","en","3fa754ae-c223-4e32-b8ed-f1f922ab60a4",[17,18,19,20,21,22,23],"Codex","OpenAI","AI coding agent","Codex CLI","Codex Cloud","Codex Security","GPT-5.3-Codex-Spark",[25,26,27],"Codex runs code tasks in isolated cloud environments with logs and test results.","The product spans web, CLI, desktop, and IDE workflows across Windows and macOS.","Codex Security adds vulnerability scanning, while Spark focuses on faster interactive coding.",0,"2026-07-01T10:02:23.007076+00:00","2026-07-01T10:02:23+00:00","d19fc184-5852-4c4d-9ec0-db0c4841ac17",{"tags":33,"relatedLang":38,"relatedPosts":42},[34,36],{"name":18,"slug":35},"openai",{"name":17,"slug":37},"codex",{"id":15,"slug":39,"title":40,"language":41},"codex-openai-coding-agent-real-work-zh","Codex 的 5 個關鍵模組，先看用途再選入口","zh",[43,49,55,61,67,73],{"id":44,"slug":45,"title":46,"cover_image":47,"image_url":47,"created_at":48,"category":13},"777fb6b4-cb95-4faf-8ba2-c915ec340a22","bootdev-go-course-turns-syntax-into-services-en","Boot.dev’s Go course turns syntax into services","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782908267986-zkta.png","2026-07-01T12:17:23.153094+00:00",{"id":50,"slug":51,"title":52,"cover_image":53,"image_url":53,"created_at":54,"category":13},"17d21a9f-2d64-49c0-8a04-fa24d2fab8c6","suse-openchip-risc-v-eu-sovereign-stack-en","SUSE and Openchip turn RISC-V into an EU stack","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782907407926-u3lb.png","2026-07-01T12:02:56.604284+00:00",{"id":56,"slug":57,"title":58,"cover_image":59,"image_url":59,"created_at":60,"category":13},"5040a23c-22d0-47ab-94a5-e10ca77708cb","risc-v-hobbyists-open-hardware-obsession-en","RISC-V hobbyists are proving open hardware still rewards obsession","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782906473059-5j1x.png","2026-07-01T11:47:21.943456+00:00",{"id":62,"slug":63,"title":64,"cover_image":65,"image_url":65,"created_at":66,"category":13},"2a50a3e6-3552-4dc4-9774-a062f0593447","microsoft-build-2026-securing-code-agents-models-en","Microsoft Build 2026: Securing code, agents, and models","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782903775971-4vnt.png","2026-07-01T11:02:29.750881+00:00",{"id":68,"slug":69,"title":70,"cover_image":71,"image_url":71,"created_at":72,"category":13},"2556ac13-b8df-462c-be84-5329736ef75e","pentagon-agent-network-ai-battle-decisions-en","Pentagon’s Agent Network speeds AI battle decisions","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782902875963-uxp2.png","2026-07-01T10:47:22.497964+00:00",{"id":74,"slug":75,"title":76,"cover_image":77,"image_url":77,"created_at":78,"category":13},"f42a2e7a-4d28-4211-94ab-570e53975969","vcs-fund-ai-coding-security-first-en","VCs Should Fund AI Coding, But Only If Security Comes First","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782897466736-cavr.png","2026-07-01T09:17:21.927016+00:00",[80,85,90,95,100,105,110,115,120,125],{"id":81,"slug":82,"title":83,"created_at":84},"d35a1bd9-e709-412e-a2df-392df1dc572a","ai-impact-2026-developments-market-en","AI's Impact in 2026: Key Developments and Market Shifts","2026-03-25T16:20:33.205823+00:00",{"id":86,"slug":87,"title":88,"created_at":89},"5ed27921-5fd6-492e-8c59-78393bf37710","trumps-ai-legislative-framework-en","Trump's AI Legislative Framework: What's Inside?","2026-03-25T16:22:20.005325+00:00",{"id":91,"slug":92,"title":93,"created_at":94},"e454a642-f03c-4794-b185-5f651aebbaca","nvidia-gtc-2026-key-highlights-innovations-en","NVIDIA GTC 2026: Key Highlights and Innovations","2026-03-25T16:22:47.882615+00:00",{"id":96,"slug":97,"title":98,"created_at":99},"0ebb5b16-774a-4922-945d-5f2ce1df5a6d","claude-usage-diversifies-learning-curves-en","Claude Usage Diversifies, Learning Curves Emerge","2026-03-25T16:25:50.770376+00:00",{"id":101,"slug":102,"title":103,"created_at":104},"69934e86-2fc5-4280-8223-7b917a48ace8","openclaw-ai-commoditization-concerns-en","OpenClaw's Rise Raises Concerns of AI Model Commoditization","2026-03-25T16:26:30.582047+00:00",{"id":106,"slug":107,"title":108,"created_at":109},"b4b2575b-2ac8-46b2-b90e-ab1d7c060797","google-gemini-ai-rollout-2026-en","Google's Gemini AI Rollout Extended to 2026","2026-03-25T16:28:14.808842+00:00",{"id":111,"slug":112,"title":113,"created_at":114},"6e18bc65-42ae-4ad0-b564-67d7f66b979e","meta-llama4-fabricated-results-scandal-en","Meta's Llama 4 Scandal: Fabricated AI Test Results Unveiled","2026-03-25T16:29:15.482836+00:00",{"id":116,"slug":117,"title":118,"created_at":119},"bf888e9d-08be-4f47-996c-7b24b5ab3500","accenture-mistral-ai-deployment-en","Accenture and Mistral AI Team Up for AI Deployment","2026-03-25T16:31:01.894655+00:00",{"id":121,"slug":122,"title":123,"created_at":124},"5382b536-fad2-49c6-ac85-9eb2bae49f35","mistral-ai-high-stakes-2026-en","Mistral AI: Facing High Stakes in 2026","2026-03-25T16:31:39.941974+00:00",{"id":126,"slug":127,"title":128,"created_at":129},"9da3d2d6-b669-4971-ba1d-17fdb3548ed5","cursors-meteoric-rise-pressures-en","Cursor's Meteoric Rise Faces Industry Pressures","2026-03-25T16:32:21.899217+00:00"]