GoodMem

Quick answers

What is GoodMem?

GoodMem is memory infrastructure for AI agents that sits between your agents and your data. It ingests documents, embeds and indexes them, and serves governed, permission-checked context back to any model. Your application calls GoodMem to store content and retrieve relevant passages at inference time; GoodMem manages the ingestion pipeline, embedding orchestration, retrieval pipeline, and access-control layer.

When do I need a memory layer?

You need a memory layer when the context your agents require outlives a single request and when more than one agent, user, or team must share that context under different permissions. Concrete symptoms are agents that re-read the same source material on every run, context windows that grow until they become the dominant cost, knowledge that must be scoped per customer or per team, and retrieval behavior you cannot audit after the fact.

When should I not use GoodMem?

A plain vector database is enough when you have one corpus, one embedding model, one trust boundary, and a document pipeline you are happy to own. If you are embedding clean text you already have, filtering it in SQL, and serving it to a single application, pgvector or a dedicated vector store will do the job with less to run.

Which languages have official SDKs?

GoodMem publishes first-party SDKs for Python, TypeScript, Java, Go, and .NET, plus an MCP server. All are generated from a single shared API description and published under the Apache-2.0 license to their language's standard registry.

What is a "memory" in GoodMem?

A memory is a document, not an extracted fact. When you create one you submit the original content along with its content type and an optional metadata object. GoodMem stores that original content, extracts text from it, splits it into chunks according to the space's chunking configuration, and embeds each chunk. Retrieval returns chunks, each of which cites the memory and the position it came from. One memory therefore produces many indexed chunks, and chunk count — not memory count — is what drives storage.