{"slug": "codex-chronicle", "title": "Codex Chronicle", "summary": "OpenAI launched Chronicle, an opt-in research preview for ChatGPT Pro subscribers on macOS, that augments Codex memories with screen context to reduce the need for users to restate context. The feature requires Screen Recording and Accessibility permissions, stores memories unencrypted on the device, and carries risks including prompt injection and rapid rate limit consumption.", "body_md": "Chronicle is in an **opt-in research preview**. It is only available for\nChatGPT Pro subscribers on macOS. Please review the [Privacy and\nSecurity](#privacy-and-security) section for details and to understand the\ncurrent risks before enabling.\n\nChronicle augments Codex memories with context from your screen. When you prompt Codex, those memories can help it understand what you’ve been working on with less need for you to restate context.\n\nChronicle is available as an opt-in research preview in the ChatGPT desktop app on macOS. It requires macOS Screen Recording and Accessibility permissions. Before enabling, be aware that Chronicle uses rate limits quickly, increases risk of prompt injection, and stores memories unencrypted on your device.\n\n## How Chronicle helps\n\nWe’ve designed Chronicle to reduce the amount of context you have to restate when you work with Codex. By using recent screen context to improve memory building, Chronicle can help Codex understand what you’re referring to, identify the right source to use, and pick up on the tools and workflows you rely on.\n\n### Use what’s on screen\n\nWith Chronicle Codex can understand what you are currently looking at, saving you time and context switching.\n\n### Fill in missing context\n\nNo need to carefully craft your context and start from zero. Chronicle lets Codex fill in the gaps in your context.\n\n### Remember tools and workflows\n\nNo need to explain to Codex which tools to use to perform your work. Codex learns as you work to save you time in the long run.\n\nIn these cases, Codex uses Chronicle to provide additional context. When another source is better for the job, such as reading the specific file, Slack thread, Google Doc, dashboard, or pull request, Codex uses Chronicle to identify the source and then use that source directly.\n\n## Enable Chronicle\n\n- Open Settings in the ChatGPT desktop app.\n- Go to\n**Personalization** and make sure**Memories** is enabled. - Turn on\n**Chronicle** below the Memories setting. - Review the consent dialog and choose\n**Continue**. - Grant macOS Screen Recording and Accessibility permissions when prompted.\n- When setup completes, choose\n**Try it out** or start a new task.\n\nIf macOS reports that Screen Recording or Accessibility permission is denied, open System Settings > Privacy & Security > Screen Recording or Accessibility and enable ChatGPT. If a permission is restricted by macOS or your organization, Chronicle will start after the restriction is removed and ChatGPT receives the required permission.\n\n## Pause or disable Chronicle at any time\n\nYou control when Chronicle generates memories using screen context. Use the\nChatGPT menu bar icon to choose **Pause Chronicle** or **Resume Chronicle**. Pause\nChronicle before meetings or when viewing sensitive content that you do not want\nCodex to use as context. To disable Chronicle, return to **Settings >\nPersonalization > Memories** and turn off **Chronicle**.\n\nYou can also control whether memories are used in a given task. [Learn\nmore](/codex/customization/memories#control-memories-per-task).\n\n## Rate limits\n\nChronicle works by running sandboxed agents in the background to generate memories from captured screen images. These agents currently consume rate limits quickly.\n\n## Privacy and security\n\nChronicle uses screen captures, which can include sensitive information visible on your screen. It does not have access to your microphone or system audio. Don’t use Chronicle to record meetings or communications with others without their consent. Pause Chronicle when viewing content you do not want remembered in memories.\n\n### Where does Chronicle store my data?\n\nScreen captures are ephemeral and will only be saved temporarily on your\ncomputer. Temporary screen capture files may appear under\n`$TMPDIR/chronicle/screen_recording/`\n\nwhile Chronicle is running. Screen captures\nthat are older than 6 hours will be deleted while Chronicle is running.\n\nThe memories that Chronicle generates are just like other Codex memories:\nunencrypted markdown files that you can read and modify if needed. You can also\nask Codex to search them. If you want to have Codex forget something you can\ndelete the respective file inside the folder or selectively edit the markdown\nfiles to remove the information you’d like to remove. You should not manually\nadd new information. The generated Chronicle memories are stored locally on your\ncomputer under `$CODEX_HOME/memories_extensions/chronicle/`\n\n(typically\n`~/.codex/memories_extensions/chronicle`\n\n).\n\n### What data gets shared with OpenAI?\n\nChronicle captures screen context locally, then periodically uses Codex to summarize recent activity into memories. To generate those memories, Chronicle starts an ephemeral Codex session with access to this screen context. That session may process selected screenshot frames, OCR text extracted from screenshots, timing information, and local file paths for the relevant time window.\n\nScreen captures used for memory generation are stored temporarily on your device. They are processed on our servers to generate memories, which are then stored locally on device. We do not store the screenshots on our servers after processing unless required by law, and do not use them for training.\n\nThe generated memories are Markdown files stored locally under\n`$CODEX_HOME/memories_extensions/chronicle/`\n\n. When Codex uses memories in a\nfuture session, relevant memory contents may be included as context for that\nsession, and may be used to improve our models if allowed in your ChatGPT\nsettings. [Learn more](https://help.openai.com/en/articles/7730893-data-controls-faq).\n\n## Prompt injection risk\n\nUsing Chronicle increases risk to prompt injection attacks from screen content. For instance, if you browse a site with malicious agent instructions, Codex may follow those instructions.\n\n## Troubleshooting\n\n### How do I enable Chronicle?\n\nIf you do not see the Chronicle setting, make sure you are using a ChatGPT desktop app build that includes Chronicle and that you have Memories enabled inside Settings > Personalization.\n\nChronicle is currently only available for ChatGPT Pro subscribers on macOS.\n\nIf setup does not complete:\n\n- Confirm that ChatGPT has Screen Recording and Accessibility permissions.\n- Quit and reopen the ChatGPT desktop app.\n- Open\n**Settings > Personalization** and check the Chronicle status.\n\n### Which model is used for generating the Chronicle memories?\n\nChronicle uses the same model as your other [Memories](/codex/customization/memories). If you\ndid not configure a specific model it uses your default Codex model. To choose a\nspecific model, update the `consolidation_model`\n\nin your\n[configuration](/codex/config-file/config-basic).\n\n```\n[memories]\nconsolidation_model = \"gpt-5.4-mini\"\n```\n\n", "url": "https://wpnews.pro/news/codex-chronicle", "canonical_source": "https://learn.chatgpt.com/docs/customization/chronicle", "published_at": "2026-07-10 11:58:53+00:00", "updated_at": "2026-07-10 12:05:26.582994+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "ai-research", "ai-safety", "ai-ethics"], "entities": ["OpenAI", "ChatGPT", "Codex", "Chronicle", "macOS"], "alternates": {"html": "https://wpnews.pro/news/codex-chronicle", "markdown": "https://wpnews.pro/news/codex-chronicle.md", "text": "https://wpnews.pro/news/codex-chronicle.txt", "jsonld": "https://wpnews.pro/news/codex-chronicle.jsonld"}}