What went down in Better Stack, why, and who acknowledged and resolved it.
Connect Better Stack with an API token and Memtro reads incidents with what failed, the cause, status and who acknowledged and resolved them and when, and uptime monitors with the URL checked, current status, last check and check frequency. 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 comment on an incident, open one, acknowledge, resolve or escalate it, or permanently delete it. Opening or escalating an incident pages people by the channels you name, and pages cannot be recalled.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Better Stack tool, reads what it needs, and answers with the source cited.
These tools change something in Better Stack. 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 Better Stack 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.
What went down this week, and how long did each incident take to resolve?
Is anything ongoing in Better Stack right now?
Which monitors are down or paused?
Who acknowledged last night's API incident, and what was the cause?
Resolve the checkout incident and add a comment that the certificate was renewed at 09:40
At the Friday review the engineering lead asks what went down this week. Memtro lists Better Stack incidents with the failing monitor, cause, who acknowledged and resolved each and when, so the time to resolve for each outage is on the table.
After fixing a failing checkout monitor, Dan Fletcher asks Memtro to note the cause and resolve the incident. Memtro reads the incident, adds the comment he approved, then resolves it in Better Stack. Nobody is paged by either step.
The teams that lean on Better Stack most, a question each of them asks, and what they connect beside it.
A record in Better Stack 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 Better Stack → API tokens, create a global token, or open Team-based tokens, pick the team and create an Incidents API token. Copy it
In Memtro open Connections → Better Stack, paste the API token and connect
With a global token, also enter the Team name to keep lists to one team
Ask what went down this week and how long each incident took to resolve
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Better Stack tools are the same everywhere.
Only when you ask, and only what it has been granted: add a comment to an incident; open a new incident, alerting on-call by the channels chosen; acknowledge an ongoing incident, stopping further escalation; resolve an ongoing incident; escalate an ongoing incident to a person, team, schedule, policy or the whole organisation (pages them); delete an incident (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 Better Stack → API tokens, create a global token, or open Team-based tokens, pick the team and create an Incidents API token. Copy it.
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
