examples/.
The model and provider in each script are only there to make it run. Swap in
whatever your app already uses; nothing about the memory wiring depends on them.
What to look for
Every script asks two questions in a row, where the second is only answerable from what the first one stored. Run it twice: the second run starts with the first run’s memories already in the space, so it can answer the opening question too. They differ from each other on purpose, because the frameworks do:Automatic
LangChain and Microsoft Agent Framework: one middleware or one
context provider, and every turn is recalled and stored.
Model's choice
CrewAI and Strands expose memory as tools. Both scripts spend prompt
text telling the model when to call them; that wording is part of the
integration.
Wire it yourself
Google ADK automates neither direction:
load_memory gives the model a
search tool, an after_agent_callback stores the turn.Explicit capture
LlamaIndex only flushes a turn once its own buffer overflows, so the last
turn never lands by itself. That script calls
bridge.remember(...).Failure behaviour
Every adapter fails open. If Anona is unreachable, the recall or the store is logged and the agent runs on without memory. No exception reaches your code. To see it for yourself, run any script with a deliberately wrong API key: it still answers, it just remembers nothing.The scripts are executed by the SDK’s own test suite against each real
framework, so an example that stopped working would fail CI rather than reach
you broken.