Which of our Baseten deployments are serving production, and how many replicas are running?
Baseten shows you your models with their deployments, environments and active replica counts, and metrics for any deployment. Memtro also reads training projects and jobs, and the workspace audit log of who did what to which model. When asked and granted, it can activate, deactivate, retry or rescale a deployment, promote one to production or another environment, and cancel a promotion. It can also delete a deployment, rename a model, and stop or recreate a training job. Activating a deployment or recreating a job is billed. The audit log needs a personal API key, because team keys cannot read it.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Baseten tool, reads what it needs, and answers with the source cited.
These tools change something in Baseten. 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 Baseten 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 deployment is serving production for the summariser model?
How many replicas is the staging deployment running now?
Which training jobs failed this week, and with what error?
Who changed the production environment of the ranking model yesterday?
Deactivate the old development deployment of the vision model.
Tom Reilly, ML platform lead at BigCo, asked who had changed the ranking model's production environment overnight. Memtro read the audit log and showed that an API key had promoted a new deployment from the API, with the time it happened.
Maya Okafor, ML engineer at Northwind, asked Memtro to cancel the promotion still ramping up on staging. With the action granted, Memtro cancelled it, and traffic returned to the environment's current deployment.
The teams that lean on Baseten most, a question each of them asks, and what they connect beside it.
A record in Baseten 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 app.baseten.co, open Settings → API keys and create a personal key, or a team key with Full access. Inference-only and Metrics-only keys cannot read models.
Open Connections → Baseten in Memtro and paste the API key.
An administrator grants actions such as activate a deployment or promote to production by name to the teams that may use them.
Ask which deployment is serving production for your main model.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Baseten tools are the same everywhere.
Only when you ask, and only what it has been granted: activate a deployment (starts billed GPU replicas); deactivate a deployment (takes it offline); retry a failed deployment (rebuilds it); change a deployment's autoscaling (replica counts and targets); promote a deployment to production; promote a deployment to an environment; cancel an in-progress promotion; delete a deployment (permanent); rename a model; stop a training job; recreate a training job (starts a new billed job). 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 app.baseten.co, open Settings → API keys and create a personal key, or a team key with Full access. Inference-only and Metrics-only keys cannot read models.
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
