Morning check
The data lead at Acme asks whether the nightly build passed. Memtro reads the production job: the 02:00 run ended in error after 14 minutes, on the dbt build step, and the end of its log names the failing model and the missing column.
Ask whether last night's dbt build passed, and which step failed if it did not.
Connect dbt Cloud with a token, your access URL and account ID, and Memtro reads projects, environments and scheduled jobs with their next run and last result, job runs with message, duration and branch, and one run's steps with the end of each log when asked. The sync writes each finished job run into memory. When you ask, and once an administrator has granted the action by name, it can run a job now, retry or re-run a failed one, or cancel a run. Each run spends warehouse compute and rebuilds tables. Deleting a job is permanent.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right dbt Cloud tool, reads what it needs, and answers with the source cited.
These tools change something in dbt Cloud. 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, choose the kinds you want, and Memtro registers its address with dbt Cloud for you. Each event can start a job, with the event as its input. dbt Cloud signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce dbt Cloud 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.
Did last night's dbt build pass?
Which dbt runs failed today, and why?
Show me the steps and logs of the last failed nightly run
When is the production job next scheduled to run?
Retry last night's failed production run from where it stopped
The data lead at Acme asks whether the nightly build passed. Memtro reads the production job: the 02:00 run ended in error after 14 minutes, on the dbt build step, and the end of its log names the failing model and the missing column.
Dan Fletcher pushes a fix for the missing orders column and asks Memtro to finish the Northwind nightly build. Memtro retries the failed run from its point of failure, which rebuilds only the remaining models in the warehouse, and reports it passed 6 minutes later.
The teams that lean on dbt Cloud most, a question each of them asks, and what they connect beside it.
A record in dbt Cloud 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.
dbt Cloud's API is available on the Starter, Enterprise and Enterprise+ plans, not on the free Developer plan
In dbt open Account settings → Service tokens and create a token with the Read-only permission set, or Job Admin if Memtro should run, cancel or delete jobs when asked. On Starter use a personal access token from Account settings → API tokens instead
In Memtro open Connections → dbt Cloud and paste the Service token or personal access token, the Access URL host from Account settings → Account information, and the Account ID after /accounts/ in the address bar
Ask whether last night's production build passed
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The dbt Cloud tools are the same everywhere.
Only when you ask, and only what it has been granted: trigger a run of a dbt Cloud job now (runs dbt against the warehouse); cancel a queued or running dbt Cloud run; retry a failed dbt Cloud run from its point of failure; re-run a job: from the failure point if its last run failed, otherwise afresh; delete a dbt Cloud job and its schedule (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. An hourly sync anchors recently changed dbt Cloud records into memory as entities.
Service token or personal access token, Access URL and Account ID. dbt Cloud's API is available on the Starter, Enterprise and Enterprise+ plans, not on the free Developer plan.
Yes. Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with dbt Cloud for you. 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