GoodMem

Store documents as memories with vector embeddings and perform similarity-based semantic retrieval using GoodMem
Connect it
In Keystile Automations → Connections → New connection, choose GoodMem and sign in. Your AI tools and workflows then use it through Keystile; they never see the password or key.How connecting works.
Try it from your AI tool
Using Keystile, in GoodMem: delete memory (Permanently delete a memory and its associated chunks and vector embeddings).What it can do (5 actions)
| Action | What it does | Changes data |
|---|---|---|
| Create Memory | Store a document as a new memory in a space. The memory is processed asynchronously - chunked into searchable pieces and embedded into vectors. Accepts a file or plain text. | Yes |
| Create Space | Create a new space or reuse an existing one. A space is a logical container for organizing related memories, configured with embedders that convert text to vector embeddings | Yes |
| Delete Memory | Permanently delete a memory and its associated chunks and vector embeddings. | |
| Get Memory | Fetch a specific memory record by its ID, including metadata, processing status, and optionally the original content. | |
| Retrieve Memories | Perform similarity-based semantic retrieval across one or more spaces. Returns matching chunks ranked by relevance, with optional full memory definitions. |
How Keystile protects it
Every GoodMem action is checked before it runs, whether it comes from an AI tool or a workflow. 2 of its actions change data; your rules, limits and budgets decide whether each is allowed, held for a person or stopped, and it all goes into the signed record.
Use GoodMem with your AI assistant — safelyClaude, Cursor or ChatGPT do the work; Keystile checks every action first.
Get early access