Source: Mastra docs: Memory overview
Mastra memory: message history, working memory, semantic recall and Observational Memory, scoped by resource and thread, backed by a storage adapter.
Contents
- What: official documentation page
- Author: Mastra
- Date: read 2026-11-14
- Original: https://mastra.ai/docs/memory/overview
Summary
Mastra’s Memory combines four mechanisms behind one object attached to an agent, scoped by a resource (user/entity) and a thread (conversation). It requires a storage provider, and optionally a vector store and embedder for retrieval.
Key claims
- Message history: last N messages (
lastMessages). - Working memory: persistent structured data about user/task, injected as a system message (or a state signal).
- Semantic recall: vector-retrieved past messages; same-thread hits are interleaved by timestamp, cross-thread hits go into a system message.
- Observational Memory (
observationalMemory: true): background agents compress older messages into observations and reflections; only unobserved messages remain verbatim; an optionalrecalltool (retrieval: true). - Default scopes: working memory and semantic recall are resource-scoped (shared across a user’s threads); Observational Memory is thread-scoped.
- A thread’s owner
resourceIdcannot change; reusing a thread ID across owners causes errors. - Subagents get a fresh thread per delegation and resource
{parentResourceId}-{agentName}. - Observational Memory silently turns off on unsupported storage adapters; its mutex is per process, so multi-process deployments need a shared PubSub with leases; with async buffering call
await memory.settled()before shutdown.