Learning the schema
A new engineer at Brightwave Ltd asks what the search cluster stores. Memtro lists four collections with their properties and data types, says which use a vectoriser, and counts the objects in each.
Ask what a Weaviate collection holds, its properties, and how many objects it has.
Connect Weaviate with your cluster's host and an API key and Memtro reads collections with their properties and vectoriser, objects by id, tenants, aliases and object counts per node. Vectors are never fetched. When you ask, and once an administrator has granted them by name, it can create, update and delete objects, create collections and tenants, add properties and references, change tenant status and repoint aliases. New text may go to a vectoriser that is a paid third-party API. Deleting objects, tenants or a collection is permanent. A read-only key keeps these out of reach.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Weaviate tool, reads what it needs, and answers with the source cited.
These tools change something in Weaviate. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Once Weaviate is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
What collections do we have, and which vectoriser does each use?
How many objects are in the Article collection?
Show me the properties of object 7c1e in Product
Which nodes are in the cluster, and what version are they on?
Delete that duplicate object from the Article collection
A new engineer at Brightwave Ltd asks what the search cluster stores. Memtro lists four collections with their properties and data types, says which use a vectoriser, and counts the objects in each.
Priya Nair finds an Acme product with the wrong price property and asks Memtro to correct it. Memtro reads the object, then overwrites that one property, leaving the others as they were, and says the old value cannot be brought back from Memtro.
The teams that lean on Weaviate most, a question each of them asks, and what they connect beside it.
A record in Weaviate is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
On Weaviate Cloud copy one of the cluster's API keys. A read-only key is safer and enough for everything but the writes. Self-hosted, use a key from AUTHENTICATION_APIKEY_ALLOWED_KEYS, mapped to a read-only user unless Memtro may write
Type the cluster's name in Host only (on Weaviate Cloud, its REST endpoint), no https://, path or port: a public DNS name with a publicly trusted certificate. IP addresses, private names and plain http are refused
Paste the API key and the Host into Connections → Weaviate in Memtro and connect
Ask what properties each collection has
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Weaviate tools are the same everywhere.
Only when you ask, and only what it has been granted: create an object in a collection; update properties of an object (overwrites the properties given); delete an object; create up to 100 objects in a collection in one call; delete up to 100 listed objects by id (permanent); create a collection with its properties; add a property to a collection (cannot be removed afterwards); delete a collection and every object in it (permanent); add or remove a cross-reference between two objects; create tenants in a multi-tenant collection; activate, deactivate or offload tenants; delete tenants and all their data (permanent); create an alias for a collection, or repoint an alias to another collection. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
Host and API key. On Weaviate Cloud copy one of the cluster's API keys. A read-only key is safer and enough for everything but the writes. Self-hosted, use a key from AUTHENTICATION_APIKEY_ALLOWED_KEYS, mapped to a read-only user unless Memtro may write.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time