Keep the thread when Codex compacts.
Seamless Context is a plugin for Codex Desktop on Windows. Before each compaction it saves a bounded summary of your whole conversation, and after it, gives that summary back once.
What it does
- Remembers the whole thread, summarised, not just the last few messages. Before each compaction it builds a bounded summary of your goal, your instructions and corrections, what the assistant decided and found, and the commands it ran and what came back.
- Handles repeated compactions. In our tests on GPT-5.6 Sol the summary brought back every planted fact after six compactions, where the same chat without the plugin kept none of eleven.
- Gives it back once. After the compaction the summary is offered to Codex exactly one time, so it is never replayed or stale.
- Stays on your computer. No outgoing connections and no online licence check.
- Keeps Codex working. If anything goes wrong, Codex carries on normally and you see a short notice.
What is saved, and where
The summary can include short excerpts of your messages and of the assistant's replies, the commands it ran with short results, and your own instructions. It is built by code, not rewritten by a model. It is stored only on your computer, in your Codex data folder and your user profile, and is replaced at the next compaction. A licence key you paste into a chat is checked and removed from what is saved.
Install in a few minutes
- Buy. Your licence key and a personal download link appear on screen and arrive by e-mail within minutes.
- Install. In Codex open Plugins, choose Add, then Upload plugin archive, pick the ZIP, and click Install plugin. If the hooks icon turns yellow, open Settings, then Hooks, and choose Trust all.
- Activate. Paste your licence key into any Codex chat and send it. Seamless Context replies that it is activated. Your key is not sent to the AI.
Requirements: Windows 64-bit and Codex Desktop. No administrator access and no Python needed. A licence works offline on up to three computers you own.
What it does not do
- It does not change Codex and it does not make compaction invisible.
- It is a help, not a guarantee. Very long threads with more than about 100 distinct facts can lose the oldest, least specific ones.
- It works inside a Codex conversation after a compaction. It does not carry a conversation into a brand-new chat.
- It works only with Codex Desktop on Windows, not with ChatGPT, Claude or Cursor.
One price. No subscription.
Introductory price. One-time payment. No subscription.
- 30-day refund, no questions asked
- All 1.x updates included
- Licence for up to 3 of your own computers
- Windows 64-bit and Codex Desktop; no administrator access and no Python needed
- Licence key and personal download link on screen and by e-mail within minutes
By buying you agree to the Terms of Sale and Licence and the Privacy Policy.
Questions people ask
Is it a subscription?
No. One payment covers all 1.x updates.
How do updates work?
Every 1.x update is included at no extra cost. When a new version is released we e-mail it to buyers, and your personal download link always serves the latest version. The customer guide inside the download has the short steps to swap it in.
Which models does it help with?
We measured a large improvement on GPT-5.6 Sol, where Codex on its own keeps almost nothing after a compaction. On GPT-5.6 Terra and GPT-5.6 Luna, Codex already keeps most of a conversation, so there is little for Seamless Context to add. The GPT-6 models have not been measured yet.
Does it send my conversations anywhere?
No. Summaries and memory stay on your computer. The plugin makes no outgoing connections and does not check your licence online.
What exactly is saved?
A bounded summary of the conversation: your goal, your instructions and corrections, short excerpts of what the assistant decided and found, and the commands it ran with short results. It is stored only on your computer and is replaced at the next compaction. Your licence key is stripped from it.
Does it work with ChatGPT, Claude or Cursor?
No. Seamless Context is a plugin for Codex Desktop on Windows. The guides on this site explain AI memory in general, but the product only works with Codex.
What if I lose my key?
Use the resend my key page with the e-mail address you bought with.
What if it is not for me?
Ask for a refund within 30 days and you get your money back, no questions asked. See the refund policy.
Who do I contact?
support@actuallyintelligent-ai.com. We aim to reply within 3 business days.