Memory
Also: persistent memory
A feature that saves facts between conversations so you do not have to repeat them. It is a saved note, not the model learning.
The fuller definition
In an AI application, memory is a mechanism for retaining and later supplying information across interactions. It may use files, summaries, databases, or product-specific features.
2,000
8,000
4,000
2,000
A hypothetical 16,000-token budget. Real limits and token accounting depend on the model. Saving a file outside this budget does not mean it is present in the current context, and a passage inside it is not guaranteed equal attention.
A concrete example
A project saves approved drafting preferences and retrieves them for a later task.
The distinction that matters
Saved memory is not identical to model training, and information stored somewhere may not be loaded for a particular answer.
Related terms
Context window
How much text the model can hold in mind at once: your question, the documents you added, and the conversation so far. Anything outside it is invisible to the model.
Prompting & contextCompaction
Squeezing a long conversation into a short summary so there is room to keep going. Details can be lost in the squeeze.
Prompting & contextCLAUDE.md
A file named CLAUDE.md that gives Claude Code project guidance. Which files it reads depends on the setup.
Where it is taught
Give AI a brief it can actually followSource and further reading
Anthropic · Context engineeringThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.