Search, sort and keep the rows of your Baserow tables up to date when asked.
Connect Baserow with a database token and the ids of the tables it may see, and Memtro reads their rows keyed by field name, with link, select and file cells read as labels, searched or sorted by a field, and each table's fields with their type. It reads on demand and there is no hourly sync. When you ask, and once an administrator has granted the action by name, it can add rows, change cell values and permanently delete rows, one at a time or up to 100 at once. Deleted rows cannot be restored through the API.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Baserow tool, reads what it needs, and answers with the source cited.
These tools change something in Baserow. 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.
Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Baserow, choosing the same kinds; the tab shows Baserow's own steps. Each event can start a job, with the event as its input. Baserow sends a secret with every delivery, and one without it is refused.
Events and webhooksOnce Baserow 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.
Which rows in the leads table mention Northwind?
Show the ten newest suppliers sorted by date added
What fields does the inventory table have?
Add a row to the leads table for BigCo with Dan Fletcher as owner
Set the status of row 42 in the projects table to done
The operations lead at Acme asks what the supplier table holds on Brightwave Ltd. Memtro searches that table for the name and returns the matching row by field name, with its linked contacts and status read as labels rather than ids.
Priya Sharma asks Memtro to mark the Northwind rollout as done in the projects table. Memtro reads the row first, shows the old status, then changes only the status field, leaving every other cell and row as it was.
The teams that lean on Baserow most, a question each of them asks, and what they connect beside it.
A record in Baserow 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.
Clio Manage
YouTrack
Canny
Float
Productive
Smartsheet
Wrike
Financial Cents
Karbon
Scoro
Kanboard
Kimai
Leantime
Acuity Scheduling
Luma
Tito
Fellow
Samsara
ServiceM8
Cliniko
Fleetio
SavvyCal
Chili Piper
Humanitix
Circleback
Aha!
Tempo
Smoobu
Semble
Airmeet
Beds24
Bookeo
Commusoft
Fergus
Fixflo
Housecall Pro
Nookal
Paymo
ProductPlan
SimplyBook.me
TimeCamp
Workiz
Guesty
Buildium
Skilljar
Runn
ClockodoIn Baserow → Settings → Database tokens choose Create token and the workspace, give it Read on the tables Memtro should see and Create, Update or Delete on any it may change, and copy it
Note each table's id from its address (…/database/{database}/table/{table id}/), since a database token cannot list tables
In Memtro open Connections → Baserow, paste the Database token and the Table ids, separated by commas, fill in Baserow host only if self-hosted, such as baserow.example.com, and connect
Ask which rows in a table mention a company or a name
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Baserow tools are the same everywhere.
Only when you ask, and only what it has been granted: add a new row to one of the connection's tables, with values by field name; add up to 100 rows to one of the connection's tables at once; change cell values on a row; change cell values on up to 100 rows, by row id; delete a row (permanent); delete up to 100 rows by id (permanent). 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.
Database token and table ids. In Baserow → Settings → Database tokens choose Create token and the workspace, give it Read on the tables Memtro should see and Create, Update or Delete on any it may change, and copy it.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Baserow, choosing the same kinds; the tab shows Baserow's own steps. A job set to start "When an event arrives" then runs once for each matching event, with the event as its input. The run treats the event as outside data, never as instructions, and anything the run remembers is kept as unverified.
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