Is anything down on our status page right now, and what maintenance is coming up?
Cachet shows you your self-hosted status page's overall status, then incidents with their status, message and updates. Memtro also reads components and groups with their status, scheduled maintenance, and metrics with their points. When asked and granted, it can create, update or delete incidents and post incident updates. It can create, update or delete components and set their status, and schedule, update or delete maintenance. It can also record metric points and add or remove subscribers. Cachet can tell Memtro when an incident or a component's status changes, and a job can start. Cachet v3 is supported.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Cachet tool, reads what it needs, and answers with the source cited.
These tools change something in Cachet. 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 Cachet, choosing the same kinds; the tab shows Cachet's own steps. Each event can start a job, with the event as its input. Cachet signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Cachet 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.
Is anything down on the status page right now?
What updates were posted on last week's API incident?
What maintenance is scheduled for this month?
Which components are in the payments group?
Post an update on the login incident saying a fix is rolling out.
Dan Fletcher, support lead at BigCo, asked whether anything was down before replying to a customer. Memtro read the overall status and listed the component showing a partial outage, with the open incident and its latest update.
Priya Sharma, site reliability engineer at Acme Ltd, asked Memtro to post that a fix was rolling out for the login incident. With the action granted, Memtro posted the update, which showed on the public status page at once.
The teams that lean on Cachet most, a question each of them asks, and what they connect beside it.
A record in Cachet 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.
UptimeRobot
Honeycomb
Cronitor
FireHydrant
StatusCake
GlitchTip
GLPI
Langfuse
LibreNMS
NetBox
Snipe-IT
Woodpecker CI
Zabbix
LangSmith
Helicone
GrowthBook
Drata
Intruder
GitGuardian
Secureframe
ilert
JumpCloud
ConfigCat
Split
Aikido Security
Astronomer
Comet Opik
CrowdStrike Falcon
Detectify
Domotz
LambdaTest
LangWatch
LlamaCloud
Logz.io
Lunary
NinjaOne
Northflank
Portkey
PromptLayer
PRTG Network Monitor
Raygun
Retell AI
Runpod
Shodan
Spike.sh
Squadcast
Tenable
UpGuard
Uptime.com
Vanta
Zenduty
Cortex
WorkOS
Kandji
Automox
Huntress
SimpleMDM
Healthchecks.io
Rapid7 InsightVM
ZenhubIn the Cachet dashboard, open Settings → Manage API Keys → New API Key. Leave the abilities empty for full access, or tick manage and delete for what Memtro may change.
Open Connections → Cachet in Memtro and paste the Status page host, with no https:// or path, and the API key.
An administrator grants actions such as create an incident by name, only to the teams that may speak on the status page. Events are turned on from the connection's Events tab, and the address is then added in Cachet's Manage Webhooks.
Ask whether anything is down on the status page right now.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Cachet tools are the same everywhere.
Only when you ask, and only what it has been granted: create an incident on the status page (can notify subscribers); change an incident's name, message, status or visibility; post an update to an incident; delete an incident (permanent); add a component to the status page; change a component, including its public status; delete a component (permanent); schedule maintenance (can notify subscribers); change scheduled maintenance; post an update to scheduled maintenance, or mark it complete; delete scheduled maintenance (permanent); record a metric point; subscribe an email address to status updates; remove a subscriber. 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.
Status page host and API key. In the Cachet dashboard, open Settings → Manage API Keys → New API Key. Leave the abilities empty for full access, or tick manage and delete for what Memtro may change.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Cachet, choosing the same kinds; the tab shows Cachet'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
