{"id":140462,"date":"2026-08-14T21:30:23","date_gmt":"2026-08-14T21:30:23","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/140462\/"},"modified":"2026-08-14T21:30:23","modified_gmt":"2026-08-14T21:30:23","slug":"hands-on-with-computer-history-openais-take-on-agent-memory","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/140462\/","title":{"rendered":"Hands-On with Computer History: OpenAI’s Take on Agent Memory"},"content":{"rendered":"

Late yesterday, OpenAI revealed<\/a> the sort of automation catnip I love: Computer History<\/a>. It\u2019s a new feature for Pro, Business, and Enterprise subscribers that creates continuity for ChatGPT and Codex by converting the actions you take on your Mac into Markdown memory files that serve as context for subsequent interactions. The idea is that with the additional context, ChatGPT and Codex will better understand your requests, requiring you to provide less detail up front while getting better results. Anyone familiar with OpenClaw<\/a>, Hermes Agent<\/a>, and similar projects will know where this is going.<\/p>\n

Here\u2019s how it works.<\/p>\n

Computer History is currently a Mac-only feature that is turned off by default, so if you want to try it, head to the Integrations section of the desktop app\u2019s settings and toggle it on. History entries can be cleared individually, too. Before you get started, ChatGPT explains that you can pause or clear your history and manage the apps and websites that Computer History accesses at any time. I excluded Passwords, 1Password, and Keychain Access to start and may add to that list as I use the feature more and get a better sense for the sort of information that it collects.<\/p>\n

That opening alert also says you agree to pause Computer History during video and audio calls with others to avoid recording them without their consent. I appreciate the reminder that recording people without consent is something you shouldn\u2019t do and is even illegal in some places, but as with the many meeting summarization tools on the market, I doubt that very many people will heed the warning and comply even though doing so is just a click of the menu bar away.<\/p>\n

Still, I appreciate the alert up front, because turning Computer History on requires trust that the information won\u2019t be misused by OpenAI. I\u2019m sure that\u2019s a bridge too far for some, but one of the most frustrating parts of using a tool like Codex is explaining yourself over and over. Every thread is like Groundhog Day<\/a> for an agent, and while there are techniques that help provide continuity, making it automatic with Computer History is an exciting prospect.<\/p>\n

If you\u2019re intrigued by the potential, it pays to read OpenAI\u2019s documentation and understand how the feature works. First of all, Computer History is not the same as Chronicle<\/a>, a retired research preview feature that relied on taking screenshots as you worked. In contrast, Computer History records interaction events but not screenshots, audio, or private web browsing sessions, according to OpenAI\u2019s documentation<\/a>. In practice, what that means is that as you work, ChatGPT will record your switches from app to app and what you\u2019re doing in apps. Here\u2019s what it\u2019s captured as I started work on this story:<\/p>\n

As you can see, every 10 minutes, ChatGPT creates a brief, timestamped summary of what I\u2019ve been doing and lists the apps I\u2019ve used by their icons. If I hover over an entry, I can immediately delete it or open the source file in the Finder for more detail on the information that ChatGPT is collecting.<\/p>\n

Each entry in Computer History is a Markdown file with YAML front matter that includes a title, description, and list of the apps you\u2019ve used followed by a structured memory document. Here, you\u2019ll see a summary of what you\u2019ve done:<\/p>\n

\n The user continued writing computer history.md in Obsidian\u2019s MacStories Vault, refining the section that explains how Computer History differs from the earlier Chronicle preview and adding a practical description of what the feature records while the user works. The user referenced the OpenAI Learn Computer History documentation in Safari, briefly exchanged messages with Federico Viticci, checked ChatGPT\/Codex settings, and then opened MacStories Images to queue a screenshot named CleanShot 2026-08-14 at [email\u00a0protected]<\/a> for upload. The upload was queued by the end of the segment, but no completed upload or copied Markdown image link was observed.\n<\/p>\n

You\u2019ll also find details that ChatGPT deems important and non-obvious, such as the following:<\/p>\n

Important non-obvious context about the user
\nMacStories Vault – Obsidian vault where the Computer History article draft was active.
\ncomputer history.md – active note being drafted for the Computer History article.
\nCleanShot 2026-08-14 at [email\u00a0protected]<\/a> – screenshot selected from @ Screenshots and queued in MacStories Images near the end of the window.
\nMacStories Images – internal Safari image uploader used for the screenshot; the page showed one queued item and an Upload 1 control.
\nFederico Viticci – Messages conversation briefly active during the writing session.
\nChatGPT\/Codex settings – ChatGPT app showed settings around 10:08Z, likely related to the same Computer History article context.<\/p>\n

That\u2019s followed by a more detailed blow-by-blow accounting of what I did over the course of the 10 minutes covered by the report. In all, it\u2019s just shy of 700 words, which, by the end of the day, will be just one short journal entry among dozens tucked away in a folder on my Mac.<\/p>\n

Those files are used as context for ChatGPT and Codex. I haven\u2019t used the feature long enough to thoroughly test it, but as you can see from the screenshot above, it provided concise, correct answers when asked about what I\u2019ve been working on today and my conversation with Federico.<\/p>\n

That\u2019s not too different from what the new Siri app can do on macOS Golden Gate<\/a>, but as I suspected, the seams start to show when you move beyond questions to tool use. When I asked Codex to send a draft of my story to Federico, it called on Computer Use to find the Markdown file and drop it in my Messages thread with him, which is exactly what I wanted. By contrast, the Siri app pasted the text of the draft into the message itself as a wall of raw Markdown text with \\n characters for line breaks. Spoiler: that\u2019s not what I wanted.<\/p>\n

Siri comparisons aside, Computer History is the sort of feature that deserves a check-in down the road because its true value and limitations aren\u2019t going to reveal themselves from a few contrived examples. OpenAI\u2019s documentation explains that it can be used to jog your memory when resuming a project, find things you recently worked on, and create workflows, which is the most interesting bit.<\/p>\n

So many potential automations die before they\u2019re ever created because we all have deadlines and too many things to get done. Stopping to build a skill or other automation for a task breaks your flow. Computer History promises to reduce that to a simple request like, \u201cI just did X. Turn it into a skill.\u201d Again, how well that works in practice remains to be seen, but it\u2019s exactly what I want from an agent.<\/p>\n

I\u2019ve already touched on some of the privacy implications of Computer History, but it\u2019s worth digging into how these memories are generated before you use the feature. The Markdown files I described are built from the interaction events that Computer History records locally as you use your Mac. OpenAI says the event files are deleted after 48 hours and are used by Codex in an ephemeral session to generate the Markdown memory files that are also stored locally. Then, when you ask a question in ChatGPT or Codex that calls on your local Markdown memory files, they are used as context for the prompt, transmitting the data as part of the request to OpenAI. So if you\u2019re not comfortable with letting Codex use your Mac interactions to generate memories and then sending those memories to ChatGPT or Codex as context, you shouldn\u2019t turn on Computer History.<\/p>\n

Me, I\u2019m excited by the prospect of Computer History. I work across a huge number of apps every day on multiple projects, and it\u2019s too easy to lose track of it all. But most of all, I\u2019m intrigued by the possibility of reducing the friction of creating repeatable skills to automate everyday tasks. I\u2019m just a few hours into my Computer History experiment, and I will report back after I\u2019ve had time to live with it for a while.<\/p>\n","protected":false},"excerpt":{"rendered":"Late yesterday, OpenAI revealed the sort of automation catnip I love: Computer History. It\u2019s a new feature for…\n","protected":false},"author":2,"featured_media":140463,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[24,25,580,2317,157],"class_list":["post-140462","post","type-post","status-publish","format-standard","has-post-thumbnail","category-openai","tag-ai","tag-artificial-intelligence","tag-chatgpt","tag-codex","tag-openai"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/140462","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=140462"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/140462\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/140463"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=140462"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=140462"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=140462"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}