How is the pricing experiment doing, and is new-checkout on in production?
GrowthBook holds your feature flags and the experiments that test them. Memtro reads flags with their environments, rules and change history, experiments with status, phases and results, and projects, metrics and segments, never metric or segment SQL. When asked and once an administrator has granted the action by name, it can turn flags on or off, create, edit, revert, archive or delete flags, create, start and stop experiments, comment on them, and refresh results, which runs queries on your data warehouse. Flag changes and started experiments reach live users at once. Deleting a flag is permanent.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right GrowthBook tool, reads what it needs, and answers with the source cited.
These tools change something in GrowthBook. 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 GrowthBook, choosing the same kinds; the tab shows GrowthBook's own steps. Each event can start a job, with the event as its input. GrowthBook signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce GrowthBook 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.
GrowthBook + MemtroIs new-checkout on in production?
How is the pricing experiment doing?
Who changed the checkout flag last week?
Which experiments are running in the web project?
Stop the pricing experiment and record variation B as the winner.
Maya Okafor, growth product manager at Acme Ltd, asked how the pricing experiment was doing. Memtro read the latest analysed results. It reported users per variation, each variation's percent change against control with its confidence interval, and the sample-ratio check.
After two more weeks of data, Maya asked Memtro to stop the pricing experiment and record it as won. Memtro stopped the experiment with that result, so live users stopped getting the variations, and posted her approved summary to its discussion, where watchers may be notified.
The teams that lean on GrowthBook most, a question each of them asks, and what they connect beside it.
A record in GrowthBook 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
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 GrowthBook, open Settings → API Keys and create a Secret Key with the narrowest role that covers what you will ask Memtro to do, read-only if you only want answers. It starts secret_.
A personal access token from the user menu → Personal Access Tokens also works, and acts as you, with your access.
In Memtro, open Connections → GrowthBook and paste it into Secret Key or personal access token. Fill API host and Port only if you self-host, and Requested by only for a Secret Key in User mode.
Ask: how is the pricing experiment doing?
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The GrowthBook tools are the same everywhere.
Only when you ask, and only what it has been granted: add a comment to an experiment's discussion; turn a feature flag on or off in named environments, publishing at once; create a feature flag, off in every environment; edit a flag's description, owner, default value, tags or project; archive or unarchive a feature flag; revert a flag to an earlier revision, or publish a draft revision; delete a feature flag and all its revisions permanently; create a draft experiment, or edit its name, hypothesis, description, owner, tags or metrics; start an experiment, or stop it and record the result; archive or unarchive an experiment; run a fresh results analysis for an experiment (queries the data warehouse). 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.
Secret Key or personal access token. In GrowthBook, open Settings → API Keys and create a Secret Key with the narrowest role that covers what you will ask Memtro to do, read-only if you only want answers. It starts secret_.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in GrowthBook, choosing the same kinds; the tab shows GrowthBook'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
