GPU spend check
Tom Reilly, ML lead at BigCo, asked which GPU instances were running and their hourly price. Memtro listed each with its type, region and price. He spotted an idle one from last week and asked the team about it.
Which Lambda GPU instances are running, and what do they cost per hour?
Lambda Cloud connects Memtro to your GPU cloud account. It reads running instances with type, GPUs, region, hourly price and status, and instance types with prices and which regions have capacity now. It also reads images, persistent filesystems, support tickets and the account's audit log. When asked and granted, it can launch, restart, terminate, rename or retag instances, create or delete filesystems, and open, comment on or close support tickets. Lambda can also tell Memtro when a support ticket is created, changes status or is solved, and a job can start on it. Lambda support must set those events up.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Lambda Cloud tool, reads what it needs, and answers with the source cited.
These tools change something in Lambda Cloud. 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 Lambda Cloud, choosing the same kinds; the tab shows Lambda Cloud's own steps. Each event can start a job, with the event as its input. Lambda Cloud sends a secret with every delivery, and one without it is refused.
Events and webhooksOnce Lambda Cloud 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.
Which instances are running, and what do they cost per hour?
Which instance types can be launched right now, and in which regions?
Which support tickets with Lambda are still open?
Which instances were launched or terminated this week, according to the audit log?
Restart the training-02 instance.
Tom Reilly, ML lead at BigCo, asked which GPU instances were running and their hourly price. Memtro listed each with its type, region and price. He spotted an idle one from last week and asked the team about it.
When Lambda marked Northwind's support ticket about an unhealthy host solved, Lambda told Memtro and a job started. It read the ticket and the instance it named, then reported the instance's current status to Maya Okafor, the infrastructure engineer.
The teams that lean on Lambda Cloud most, a question each of them asks, and what they connect beside it.
A record in Lambda Cloud 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 Lambda Cloud, open API keys and generate an API key. It carries the roles of whoever created it and is shown once.
In Memtro, open Connections → Lambda Cloud and paste the API key.
An administrator grants the actions by name, such as Terminate instances, to the teams that may use them. Events are turned on from the connection's Events tab, then Lambda support is asked to send ticket webhooks to the address.
Ask "Which instances are running, and what do they cost per hour?"
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Lambda Cloud tools are the same everywhere.
Only when you ask, and only what it has been granted: launch a GPU instance (billed per hour); restart instances; terminate instances; rename or retag an instance; create a persistent filesystem; delete a filesystem; open a support ticket with Lambda; comment on, re-prioritise or close a support ticket. 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 key. In Lambda Cloud, open API keys and generate an API key. It carries the roles of whoever created it and is shown once.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Lambda Cloud, choosing the same kinds; the tab shows Lambda Cloud'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