01
Morning triage
An on-call engineer asks Memtro what alerted overnight. It lists the monitors that fired and recovered, pulls the matching logs for the noisiest one, and links the Datadog incident that was opened.
Datadog + Memtro
Ask what is alerting, what the logs say and how a metric moved, without opening Datadog.
Memtro connects to Datadog read-only with an API key and a read-scoped application key. It can list and inspect monitors, search logs and count them by facet, pull metric time series, read the event stream, and summarise incidents and SLO status. Every hour it notes which monitors started or stopped alerting and which incidents were declared or resolved, so that history stays in your company memory.
What you can do with Datadog in Memtro
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Datadog tool, reads what it needs, and answers with the source cited.
02
Post-incident write-up
A team lead writing a retrospective asks for the timeline. Memtro combines the incident's detection and resolution times, the monitors that triggered, and the events in the window into a draft narrative with links back to Datadog.
- Monitors by state, tag or name, with per-group alert state and thresholds
- Log search in Datadog syntax, or counts per service, status, host or any facet
- Metric queries summarised to min/avg/max/latest with downsampled points
- Event stream: alerts, recoveries and deployments in a window
- Incident Management: severity, commander, impact, time to resolve
- SLO list and SLI / error-budget status over a window
- Hourly memory of monitors that start or stop alerting and incidents declared or resolved
Ask it like this
Questions people ask once Datadog is connected. In agent mode each one also checks the other systems that know about the same people, companies or identifiers.
- ›What is alerting in Datadog right now?
- ›Show error logs for the checkout service in the last 30 minutes
- ›How many 5xx responses per service in the last hour?
- ›Plot p99 latency for the api service over the last 6 hours
- ›Which incidents were resolved this week and how long did they take?
- ›Is the payments SLO within its error budget?
Where it fits
Teams that get the most from Datadog in Memtro, with the rest of their stack attached.
- EngineeringKeep decisions from evaporatingDecisions, owners and deadlines are extracted from conversations and tool results into a typed, time-aware memory. Corrections supersede old facts instead of piling up next to them.
- ProductHear what customers actually ask forFeature requests are scattered across tickets, call notes, Slack threads and issues. Memtro reads them where they live, links them to the customers who raised them, and remembers which decision closed each one.
- Agent buildersMemory and tools for the agents you buildPoint your own agent at Memtro over the OpenAI-compatible API or MCP and it gets long-term memory, connectors that read by default and act where you grant it, and model routing without you building any of it.
Better together
A record in Datadog is rarely the whole story. Connect the systems that hold the rest and the agent cross-references them by default, then remembers what it learned so the next question starts further along.
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.
How to connect
- 01In Datadog go to Organization Settings → API Keys and copy or create an API key
- 02Go to Application Keys, create one and scope it to monitors_read, logs_read_data, metrics_read, events_read, incident_read and slos_read
- 03In Memtro choose Datadog, paste both keys and set the site (datadoghq.com, datadoghq.eu, us3, us5, ap1)
- 04Click Test and connect
Also works from
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Datadog tools are the same everywhere.
Set it up as an MCP server →Clients and agents →Questions
- Can Memtro change anything in Datadog?
- Not yet. Today every Datadog tool reads, searches or lists. When the connector gains actions, each is marked, granted by name per team and used only when a person asks for exactly that, so nothing is created, sent, updated or deleted until you say so.
- Who can use a Datadog 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 Datadog 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. An hourly sync anchors recently changed Datadog records into memory as entities.
- How do I connect Datadog?
- API key + application key. In Datadog go to Organization Settings → API Keys and copy or create an API key.
Connect Datadog in a few minutes
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.