"Memory"- is- a- friendly- word- for- a- set- of- storage- and- retrieval- choices.- The- friendly- word- can- hide- an- ugly- amount- of- plumbing.- If- you- do- not- know- where- the- remembered- fact- lives,- you- do- not- really- know- how- the- product- behaves.- Start- every- memory- feature- design- by- naming- the- storage- system,- the- retention- rule,- and- the- deletion- path.

##- TL;DR

If- you- are- building- or- using- an- LLM- app,- do- not- assume- chat- history- equals- memory.

The- safe- starting- point- is- to- separate- four- buckets:

• conversation- history:- recent- messages- replayed- into- the- model;
• profile- memory:- explicit- stored- preferences- or- facts- about- a- user;
• application- data:- records- kept- in- your- own- database- or- vector- store;
• training- or- analytics- data:- material- kept- for- model- improvement,- reporting- or- debugging.

Each- bucket- needs- a- different- explanation,- retention- rule- and- access- control.

##- What- “memory”- can- mean

###- Conversation- history

This- is- the- easiest- kind- of- “memory”- to- understand:- the- app- sends- older- messages- back- into- the- next- request- so- the- model- can- respond- in- context.

That- is- not- the- same- as- the- model- permanently- learning- the- user.

###- Profile- memory

Some- apps- store- explicit- facts- or- preferences,- like- a- preferred- tone,- product- preference- or- time- zone.

That- can- be- useful,- but- only- if- the- user- can- see,- edit- and- delete- what- is- stored.

###- Application- data

Some- systems- store- a- summary,- a- note,- a- file- or- a- retrieved- passage- in- a- database- or- vector- store.

That- is- useful- for- search- and- continuity,- but- it- is- still- storage.- Calling- it- “memory”- does- not- make- it- less- sensitive.

###- Training- or- analytics- data

Some- providers- or- products- retain- prompts- and- outputs- for- quality,- abuse- detection- or- training.

That- can- be- legitimate,- but- it- must- be- explained- clearly- and- configured- carefully.

##- What- can- go- wrong

The- main- risks- are- predictable:

1.- the- app- keeps- more- than- the- user- expected; 2.- old- or- stale- facts- get- replayed- into- future- answers; 3.- private- data- is- stored- where- too- many- people- can- see- it; 4.- retrieval- returns- the- wrong- memory- to- the- wrong- user; 5.- a- memory- feature- becomes- a- hidden- source- of- legal- or- trust- risk; 6.- users- cannot- tell- what- is- kept,- for- how- long,- or- why.

A- memory- feature- that- feels- helpful- in- a- demo- can- become- a- privacy- problem- in- production- if- the- retention- story- is- vague.