What changed this week
Priya Sharma, head of data at Northwind, asked which dashboards changed this week. Memtro searched across projects sorted by last update and listed each dashboard with who created it, its space and its views.
Which Lightdash dashboards changed this week, and what charts are in the Finance space?
Memtro reads your Lightdash projects. It searches charts, dashboards and spaces by name, with who created each, when it last changed and its views, and lists explores, including which have compile errors. When asked and once an administrator has granted the action by name, it can create or rename spaces, create or duplicate dashboards, roll back a chart, comment on a tile, pause, resume or send a scheduled delivery now, and refresh a project's dbt build. A send may email people outside the company and cannot be recalled. Deleting a space, dashboard, chart or schedule is permanent.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Lightdash tool, reads what it needs, and answers with the source cited.
These tools change something in Lightdash. 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 Lightdash 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 dashboards changed this week?
What charts are in the Finance space?
Which explores have compile errors?
Who created the churn dashboard, and how many views does it have?
Refresh the analytics project so the new orders model shows up.
Priya Sharma, head of data at Northwind, asked which dashboards changed this week. Memtro searched across projects sorted by last update and listed each dashboard with who created it, its space and its views.
Tom Reilly, an analytics engineer at Acme Ltd, merged a new orders model and asked Memtro to refresh the project. Memtro started the dbt refresh as a background job, then listed the explores once it finished and confirmed none had compile errors.
The teams that lean on Lightdash most, a question each of them asks, and what they connect beside it.
A record in Lightdash 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.
In Lightdash, sign in as a dedicated user and open Settings → Personal access tokens → Generate new token. The viewer role keeps Memtro read-only, editor lets it change content and schedules, developer lets it refresh a project.
Copy the token. It acts with every permission of that user and stops working if they leave the organisation.
In Memtro, open Connections → Lightdash and paste Host (host name only, such as <name>.lightdash.cloud) and Personal access token.
Ask: "Which dashboards changed this week?"
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Lightdash tools are the same everywhere.
Only when you ask, and only what it has been granted: create a space in a project; rename a space; delete a space and what is in it, permanently; create an empty dashboard, or duplicate an existing one; delete a dashboard, permanently; delete a saved chart, permanently, which removes it from dashboards; roll a saved chart back to an earlier version; send a scheduled delivery now to all of its recipients; pause or resume a scheduled delivery; delete a scheduled delivery, permanently; refresh a project's dbt build so explores pick up model changes; comment on a dashboard tile, optionally mentioning people. 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 Personal access token. In Lightdash, sign in as a dedicated user and open Settings → Personal access tokens → Generate new token. The viewer role keeps Memtro read-only, editor lets it change content and schedules, developer lets it refresh a project.
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