Long-session memory (Railroad)
Optional structured memory extracted over time and re-injected into prompts so follow-up turns stay coherent (user-facing: “remembers details within your session/product limits”).
What this is
Session memory (product nickname “Railroad”) stores structured facts the assistant extracts across turns so long chats stay coherent—within privacy and retention rules for your plan.
How to use it
- You do not manage memory manually; it updates as you chat.
- Ask the assistant to “forget” sensitive details if the product exposes that control in your build.
- Start a New chat for a clean memory scope.
Notes and limits
Memory is not a full backup of pages; it is distilled text used to steer replies.
Related topics
Related Documentation
Performance and resource usage
Is Oasis too heavy? How CPU, memory, disk, and network are used—for browsing, the assistant, and optional on-device features.
Training and bonus tokens
How Oasis training works, whether anonymous training leaves the device, privacy-first trainable browser, personalized vs anonymous modes, and daily bonus tokens.
Import data from other browsers
How Oasis imports bookmarks, passwords, history, extensions, and autofill from Chrome, Edge, Safari, Brave, and more—and where that data lives relative to the cloud assistant.
About the Author
I'm the CEO of Kahana, bringing a unique perspective from my management consulting experience at Clarkston Consulting and biomedical engineering background from Duke University. I'm focused on making the future of work more elegant through innovative technology solutions that prioritize user well-being and productivity.