After the release
Maya Okafor, backend engineer at Acme Ltd, asked whether the last deploy of the API service succeeded. Memtro found the service in production and showed the newest deployment as FAILED, with the one before it SUCCESS and its URL.
Railway + Memtro
Did the last Railway deploy of the API service succeed?
Railway hosts your apps and services. Memtro reads your projects with their services and environments, and the recent deployments of a service with status and URL. Deployment logs are never read. When asked, and once an administrator has granted the action by name, it can deploy a service or a chosen commit, which starts a build and billable compute, redeploy, restart, roll back, stop or cancel deployments, create services and projects, change service settings, which can change what is billed, and permanently delete a service with its deployments. Railway tokens have no scopes, so use one made for Memtro.
In Memtro
What you can do with Railway in Memtro
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Railway tool, reads what it needs, and answers with the source cited.
What it does
- 01List the projects the token can see, with description and created and updated dates, and each project's services and environments.
- 02List a service's recent deployments in one environment, newest first, with status such as BUILDING, SUCCESS, FAILED or CRASHED.
- 03Give the URL of each deployment, and check one deployment's status and dates and the service, environment and project it belongs to.
- 04When asked and granted, deploys a service or a named commit, redeploys or rolls back, which starts a build and billable compute and replaces what is running once healthy.
- 05When asked and granted, restarts a deployment, stops one so the service goes offline, cancels a build, and creates services and projects or changes their names and build and deploy settings.
- 06When asked and granted, permanently deletes a service and all its deployments in every environment.
Acts when asked
When you ask it to
These tools change something in Railway. 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.
- 01Deploy a service in an environment, optionally at a given commit (starts a build and billable compute)
- 02Redeploy a service's latest deployment with its existing commit
- 03Restart a running deployment without rebuilding (brief downtime)
- 04Roll a service back to an earlier deployment
- 05Stop a running deployment (the service goes offline)
- 06Cancel a deployment that is building or queued
- 07Redeploy one specific earlier deployment
- 08Create a service in a project, empty or from a GitHub repo or Docker image
- 09Change a service's build and deploy settings in one environment (commands, replicas, region, cron, healthcheck)
- 10Rename a service or change its icon
- 11Delete a service and all its deployments (permanent)
- 12Create an empty project
- 13Rename or re-describe a project
Events
When it happens
Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Railway, choosing the same kinds; the tab shows Railway's own steps. Each event can start a job, with the event as its input. Railway sends a secret with every delivery, and one without it is refused.
Events and webhooks- 01A deployment failed
In practice
Ask it like you would a colleague
Once Railway 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.
Railway + Memtro
Did the last deploy of the API service succeed?
Which services are in the billing project?
Has the worker service crashed in production this week?
What URL is the staging web service on?
Roll the API service in production back to the previous deployment
Rolling back a bad deploy
Dan Fletcher, CTO at Northwind, saw the worker service crashing after a release and asked Memtro to roll it back. Memtro found the last SUCCESS deployment in production and rolled the service back to it on Railway, where it became the running deployment again.
Teams
Where it fits
The teams that lean on Railway most, a question each of them asks, and what they connect beside it.
- EngineeringKeep decisions from evaporatingEngineer, Tech lead, On call, New joiner“Who owns the billing migration, and what did we decide about retries?”Used alongside GitHub, Linear, Jira, Confluence, Slack and 5 more.
- ProductHear what customers actually ask forProduct manager, Researcher, Designer, Head of product“Which customers asked for SSO this quarter, and what is their combined ARR?”Used alongside Help Scout, HubSpot, Linear, Jira, Slack and 6 more.
- Agent buildersMemory and tools for the agents you buildSolo builder, Platform team, Automation engineer, Whoever signs it off“Search memtro for what we know about Acme before drafting the proposal”Used alongside GitHub, Linear and Slack.
Better together
Works with
A record in Railway 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.
- Work managementRailway with JiraJQL search, issue details and projects from Jira Cloud.
- Work managementRailway with Clio ManageAsk the matter: its client, its fee earner, the time on it and what is still unbilled.
- Work managementRailway with LinearIssues, projects and teams, synced hourly into memory.
- SupportRailway with Help ScoutAI that reads your support conversations and cross-references the customer everywhere else.
- SupportRailway with ZendeskEvery ticket, reply and internal note, ready to be asked about.
- SupportRailway with IntercomCustomer conversations and the people behind them, in your company memory.
- Documents and wikisRailway with NotionSearch pages and query databases, and write to them when you ask.
- Documents and wikisRailway with Google DriveSearch Drive and read Docs, Sheets and Slides as text, and write a Doc when you ask.
- Documents and wikisRailway with ConfluenceSearch and read wiki pages, and write them when you ask.
Also in Engineering and operations
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
- GitHub
- AWS CloudWatch
- Sentry
- ServiceNow
- Okta
- Twilio
- AWS CloudTrail
- GitLab
- Bitbucket
- Vercel
- PagerDuty
- Datadog
- Grafana
- incident.io
- Azure DevOps
- CircleCI
- Cloudflare
- LaunchDarkly
- New Relic
- Rollbar
- Snyk
- Better Stack
- Buildkite
- DigitalOcean
- Heroku
- Netlify
- SonarQube Cloud
- Statuspage
UptimeRobot- Axiom
- BugSnag
- Checkly
- Hetzner Cloud
Honeycomb- Pingdom
- Render
- Statsig
- Sumo Logic
- Supabase
- HCP Terraform
- Vultr
- Airbrake
- Codecov
Cronitor- Dynatrace
FireHydrant- Fly.io
- Honeybadger
- Akamai Linode
- Octopus Deploy
- Pulumi
- Rootly
- Semgrep
- Splunk
StatusCake- Tailscale
- Argo CD
- authentik
- Coolify
- Gitea
GlitchTip
GLPI- Jenkins
Langfuse
LibreNMS- n8n
NetBox- Portainer
- Prefect
Snipe-IT
Woodpecker CI
Zabbix
LangSmith
Helicone- OpenAI (usage and cost)
- Anthropic (usage and cost)
- Algolia
- Flagsmith
- Unleash
GrowthBook
Drata
Intruder
GitGuardian
Secureframe
ilert- KnowBe4
JumpCloud
ConfigCat- Fastly
- Postman
- Make
- Braintrust
- OpenRouter
- ElevenLabs
Split- Scaleway
Aikido Security- AssemblyAI
Astronomer- Bamboo
- Baseten
- Bitrise
- Bitwarden
- BrowserStack
- bunny.net
- Cachet
- Checkmk
- Civo
- Cloudsmith
- Codacy
- Codemagic
Comet Opik- Coralogix
CrowdStrike Falcon- Dagster+
- DeepSource
Detectify- Docker Hub
Domotz- Grafana OnCall
- Harness
- Hugging Face
- Instatus
- Koyeb
- Lambda Cloud
LambdaTest
LangWatch
LlamaCloud
Logz.io
Lunary- Mezmo
NinjaOne- Nomad
Northflank- Oh Dear
- OVHcloud
Portkey- Probely (Snyk API & Web)
PromptLayer- Proxmox VE
PRTG Network Monitor- Qase
Raygun
Retell AI- Retool
Runpod- SecurityScorecard
- Semaphore CI
Shodan- SigNoz
- Socket
Spike.sh
Squadcast- SwaggerHub
- TeamCity
Tenable- Together AI
- Travis CI
UpGuard
Uptime.com
Vanta- Vapi
- Windmill
Zenduty- OpsLevel
Cortex- Auth0
- Clerk
WorkOS
Kandji
Automox
Huntress- HackerOne
SimpleMDM- AppSignal
Healthchecks.io
Rapid7 InsightVM- 1Password Events
- JFrog Artifactory
- Sauce Labs
Zenhub- Deepgram
- Replicate
Setup
How to connect
Connect withWorkspace or account token and optional workspace ID
- 1
In railway.com, open Account settings → Tokens and create a token made for Memtro. Tokens have no scopes and can do anything their owner can. Project tokens are not supported.
- 2
Choose a workspace in the dropdown for a workspace token, or No workspace for an account token, then create and copy it.
- 3
In Memtro, open Connections → Railway and paste it as Workspace or account token. For a workspace token, add the Workspace ID from its settings page.
- 4
Ask: did the last deploy of the API service succeed?
Also works from
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Railway tools are the same everywhere.
FAQ
Questions
Can Memtro change anything in Railway?+
Only when you ask, and only what it has been granted: deploy a service in an environment, optionally at a given commit (starts a build and billable compute); redeploy a service's latest deployment with its existing commit; restart a running deployment without rebuilding (brief downtime); roll a service back to an earlier deployment; stop a running deployment (the service goes offline); cancel a deployment that is building or queued; redeploy one specific earlier deployment; create a service in a project, empty or from a GitHub repo or Docker image; change a service's build and deploy settings in one environment (commands, replicas, region, cron, healthcheck); rename a service or change its icon; delete a service and all its deployments (permanent); create an empty project; rename or re-describe a project. 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.
Who can use a Railway connection?+
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.
Does Memtro store my Railway data?+
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.
How do I connect Railway?+
Workspace or account token and optional workspace ID. In railway.com, open Account settings → Tokens and create a token made for Memtro. Tokens have no scopes and can do anything their owner can. Project tokens are not supported.
Can Railway start a job?+
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Railway, choosing the same kinds; the tab shows Railway'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.
Connect Railway in a few minutes
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.