Honeycomb logo

Honeycomb + Memtro

Ask which Honeycomb triggers are firing, and when the last deploy marker went on.

Connect Honeycomb with a region and a Configuration key for one environment and Memtro reads its datasets and when each last received data, triggers and which are firing, SLOs, boards, and deploy or incident markers. Trigger recipients are never read. It reads on demand and there is no hourly sync. When you ask, and once an administrator has granted the action by name, it can add, change or delete markers, save and run queries, and create boards and SLOs. Markers notify nobody but show on everybody's charts. Deleting a trigger or SLO is permanent and stops its alerts.

In Memtro

What you can do with Honeycomb in Memtro

Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Honeycomb tool, reads what it needs, and answers with the source cited.

What it does

  1. 01Datasets in the environment with when each last received data, to spot a service that went quiet
  2. 02Triggers with dataset, threshold, check frequency and firing or disabled state, and how many recipients but never who
  3. 03SLOs with target, time window, the SLI column and the datasets they cover, and boards with a link
  4. 04When asked and granted, adds, changes or permanently deletes a deploy, incident or note marker, which notifies nobody but shows on everybody's charts
  5. 05When asked and granted, saves and names a query, runs it on the Enterprise plan using query capacity, and creates boards and SLOs
  6. 06When asked and granted, permanently deletes a trigger or an SLO, stopping its alerts without telling its recipients

Acts when asked

When you ask it to

These tools change something in Honeycomb. 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.

  1. 01Add a marker (a deploy, incident or note) to an environment's or a dataset's graphs
  2. 02Change a marker's message, type, link or times
  3. 03Delete a marker
  4. 04Save a query specification
  5. 05Run a saved query and read its results
  6. 06Name and describe a saved query
  7. 07Create a board
  8. 08Create an SLO
  9. 09Permanently delete a trigger
  10. 10Permanently delete an SLO

Events

When it happens

Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with Honeycomb for you. Each event can start a job, with the event as its input. Honeycomb sends a secret with every delivery, and one without it is refused.

Events and webhooks
  • 01A trigger fired
  • 02A trigger went back to normal
  • 03An SLO's budget is burning fast
  • 04An SLO's budget burn rate is back within limits
  • 05An SLO's budget will run out soon
  • 06An SLO's budget is no longer about to run out
  • 07An anomaly was detected
  • 08An anomaly ended
In practice

Ask it like you would a colleague

Once Honeycomb 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.

Honeycomb logoHoneycomb + Memtro
  • Which Honeycomb triggers are firing right now?

  • When did we last deploy the checkout service?

  • Has any dataset stopped receiving data today?

  • Add a deploy marker for release 4.12 to the api dataset

  • Count errors by endpoint on the api dataset over the last 2 hours

01

What is alerting

At the start of the on-call shift Dan Fletcher asks what is alerting. Memtro lists the two firing triggers, both on the payments dataset with their thresholds, and notes that the payments dataset last received data forty minutes ago.

02

Marking the incident

During an outage Priya Nair asks Memtro to mark when the Northwind integration started failing. Memtro adds an incident marker to the environment's graphs, which notifies nobody but shows on everybody's charts, and sets its end time when she says it is fixed.

Teams

Where it fits

The teams that lean on Honeycomb most, a question each of them asks, and what they connect beside it.

Better together

Works with

A record in Honeycomb 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.

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.

Setup

How to connect

Connect withRegion and Configuration key
  1. 1

    In Honeycomb open Environment settings → API Keys → Configuration and create a Configuration key, not an Ingest key. A key belongs to one environment, so connect each environment separately

  2. 2

    Tick Manage Triggers, Manage SLOs, Manage Public Boards and Send Events or Create Markers. Add Manage Queries and Columns to save queries, and Run Queries (Enterprise) to run them. Copy the key: it is shown only while you create it

  3. 3

    In Memtro open Connections → Honeycomb, set Region to us if you sign in at ui.honeycomb.io or eu if at ui.eu1.honeycomb.io, paste the Configuration key and connect

  4. 4

    Ask which triggers are firing right now

Also works from

Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Honeycomb tools are the same everywhere.

FAQ

Questions

Can Memtro change anything in Honeycomb?+

Only when you ask, and only what it has been granted: add a marker (a deploy, incident or note) to an environment's or a dataset's graphs; change a marker's message, type, link or times; delete a marker; save a query specification; run a saved query and read its results; name and describe a saved query; create a board; create an SLO; permanently delete a trigger; permanently delete an SLO. 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 Honeycomb 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 Honeycomb 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 Honeycomb?+

Region and Configuration key. In Honeycomb open Environment settings → API Keys → Configuration and create a Configuration key, not an Ingest key. A key belongs to one environment, so connect each environment separately.

Can Honeycomb start a job?+

Yes. Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with Honeycomb for you. 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 Honeycomb in a few minutes

Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.

Where agents remember your company

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