Since the deploy
Half an hour after a release, Dan Fletcher asks whether errors are up. Memtro runs one APL query over the app dataset, which costs query compute, and reports 5xx responses by hour: 12 an hour before the deploy, 140 since.
Ask Axiom how many errors the API logged since the deploy, and which monitors fired.
Connect Axiom with an API token and Memtro runs APL queries over your datasets, each costing query compute, and reads datasets, monitors with their query and last evaluation error, what each monitor notified, and chart annotations. Notifier settings such as webhook URLs and keys are never read. 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, edit or delete annotations, create, change or delete monitors, and create, trim or delete datasets. Trimming or deleting a dataset permanently removes its events.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Axiom tool, reads what it needs, and answers with the source cited.
These tools change something in Axiom. 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 Axiom, choosing the same kinds; the tab shows Axiom's own steps. Each event can start a job, with the event as its input. Axiom sends a secret with every delivery, and one without it is refused.
Events and webhooksOnce Axiom 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.
How many errors did the API log in the last hour?
Show the recent failures for the billing service since the deploy
Which monitors triggered this week, and when did they resolve?
Add a deploy annotation for release 4.12 to the app dataset
Disable the checkout latency monitor until Monday
Half an hour after a release, Dan Fletcher asks whether errors are up. Memtro runs one APL query over the app dataset, which costs query compute, and reports 5xx responses by hour: 12 an hour before the deploy, 140 since.
Priya Nair asks Memtro to stop the Globex queue-depth monitor paging the team during a planned migration. Memtro disables that one monitor in Axiom, which stops it alerting its notifiers, and re-enables it when she asks the next morning.
The teams that lean on Axiom most, a question each of them asks, and what they connect beside it.
A record in Axiom 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 app.axiom.co open Settings → API tokens → New API token and choose Advanced permissions. A basic token can only ingest data, so it connects but cannot query
Grant query on the datasets Memtro should read and read on monitors and annotations. Grant create, update or delete on annotations, monitors and datasets, and update on trim, only for what Memtro may change. Copy the token: it is shown once
In Memtro open Connections → Axiom, paste the API token and connect, leaving Org ID blank unless it is a personal access token
Ask how many errors the API logged in the last hour
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Axiom tools are the same everywhere.
Only when you ask, and only what it has been granted: add an annotation to one or more datasets' charts; edit an annotation; delete an annotation (permanent); create a monitor that alerts named notifiers; change, disable or re-enable a monitor; delete a monitor (permanent); create a dataset; change a dataset's description or retention (shorter retention removes older data); trim a dataset's events older than a number of days (permanent); delete a dataset and all its data (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.
API token. In app.axiom.co open Settings → API tokens → New API token and choose Advanced permissions. A basic token can only ingest data, so it connects but cannot query.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Axiom, choosing the same kinds; the tab shows Axiom'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