Who flipped the flag
Tom Reilly, on-call engineer at BigCo, saw checkout errors and asked who had enabled a flag in production yesterday. Memtro read the event log for production over that day. It named the person who enabled new-checkout and when.
Is new-checkout on in production, and who enabled it?
From Unleash, Memtro reads projects with their health and stale flag counts, environments, flags with on or off per environment, rollout strategies, segments and the event log. Constraint values and other strategy parameters are never returned. When asked and once an administrator has granted the action by name, it can turn a flag on or off, create, edit, tag, archive or revive flags, mark them stale, add or remove rollout strategies and create segments. A change in production reaches your users at the applications' next poll. Removing a strategy is permanent.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Unleash tool, reads what it needs, and answers with the source cited.
These tools change something in Unleash. 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 Unleash 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 new-checkout on in production?
Who enabled a flag yesterday?
Which flags are stale in the payments project?
What rollout percentage does new-checkout have in production?
Roll new-checkout out to 10% of users in production.
Tom Reilly, on-call engineer at BigCo, saw checkout errors and asked who had enabled a flag in production yesterday. Memtro read the event log for production over that day. It named the person who enabled new-checkout and when.
Sarah Chen, platform lead at Northwind, asked Memtro to start new-checkout for 10% of users in production. Memtro added a flexible rollout strategy at 10% and turned the flag on there. Applications picked it up at their next poll, and the change appeared in the flag's event history under the token's user.
The teams that lean on Unleash most, a question each of them asks, and what they connect beside it.
A record in Unleash 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 Unleash, sign in as a dedicated user. A token made from a user with the read-only Viewer root role keeps Memtro to reading. The actions you grant need a user who can make those changes.
Open the profile menu → View profile settings → Personal API tokens → New token, and copy it. It carries every permission of that user.
In Memtro, open Connections → Unleash and enter Host and Personal access token. Fill Base path only if Unleash is served under a path.
Ask: is new-checkout on in production?
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Unleash tools are the same everywhere.
Only when you ask, and only what it has been granted: turn a feature flag on or off in one environment; create a feature flag in a project; edit a flag's description, type, stale or impression-data setting; archive a feature flag, which removes it from SDKs, or revive an archived one; mark named flags stale or not stale; add a tag to a flag; add a rollout strategy to a flag in one environment, or remove one; create a segment. 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 Unleash, sign in as a dedicated user. A token made from a user with the read-only Viewer root role keeps Memtro to reading. The actions you grant need a user who can make those changes.
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