Memory

storage.memory Storage v0.1.0

Read/write durable cross-run memory (append/recall/get/set/clear) via the state engine. Append is the only array-native op: a list on the wire is N records, so appending a list of ten writes TEN entries — one per record, with Key and Value resolved against THAT record, so one key expression can address N conversations. That is a behaviour change: a list used to be stored as ONE entry, so wrap it in an object (e.g. { items: [...] }) before this node if you want the old single-entry shape. Set, clear, get and recall are whole-value operations on one key — a list is the value being stored, not N values — and never fan out.

The Memory step on the Studio canvas — The **Memory** step as it appears on the Studio canvas — input pins on the left, output ports on the right.

Finding it in the library

Search the builder's node library for Memory (it lives under Storage). A single click opens the in-editor docs panel shown here — description, ports, and every property, without leaving the canvas. Double-click (or drag) to add it to the workflow.

Memory in the node library, with the in-editor docs panel open — The library entry and the in-editor docs panel for **Memory** — the same reference this page is generated from.

Wired up in the builder

Memory in a real, runnable flow — captured live from the Studio editor, exactly as it looks on your canvas. This is the same workflow used for the example input & output below.

Memory wired into a runnable workflow in the Studio builder — **Memory** wired into a runnable flow — input on the left, output on the right.

How it’s configured

The node’s settings as the builder shows them — every field laid out with real values. In the Studio these are edited on the node: click the chevron on the divider under its ports to open them.

The Memory node's settings in the Studio builder — The settings for **Memory**, showing the values from the flow above.

Ports

Ports are the node’s contract with its neighbours. In the editor a port label renders bold when wired and italic when optional; ◈ ports accept attachment carriers rather than data wires.

Direction	Port	Label	What flows through it
Input	`input`	Input
Output	`output`	Output

How data flows through it

Memory consumes the content of the incoming envelope — when it is fed directly by a trigger, the trigger’s wrapper is unwrapped at the node boundary so the node sees the actual data, not the metadata shell. Its output becomes the payload for the next node, while the envelope (trace ids, correlation, binary refs) rides along untouched. In the Runs view you always see the whole envelope for both sides of this node.

Expressions in the config

String-typed properties accept {{ }} expressions evaluated against the incoming item at run time — e.g. {{ $json.customer.email }}. On this node that’s key. JSON- and code-typed fields never interpolate — they are passed through literally.

Build it with AI

Every node in this reference is reachable through Flowdrome’s AI Copilot and the MCP tools — say what you want, and the graph surgery happens server-side. Node types resolve fuzzily, so the catalog label (Memory) works as well as the exact type id (storage.memory).

In the Copilot panel (or any connected AI):

add a memory node after the trigger

As a step in a create_chain_workflow call:

{"type":"Memory","config":{}}

Raw MCP call — add this node to a workflow with add_node

curl -s -X POST http://localhost:4800/mcp -H "content-type: application/json" -d '{ "jsonrpc": "2.0", "id": "1", "method": "tools/call", "params": { "name": "add_node", "arguments": { "workflowId": "<id>", "type": "Memory" } } }'

Example input & output

Captured from a real test run of the workflow above — this is what the Runs view shows after pressing Test workflow.

Input — what the node received

The Memory node's input envelope in the run data viewer — The input envelope in the Runs view — Flowdrome always shows the whole envelope, with the payload inside `body`.

Output — what the node produced

The Memory node's output envelope in the run data viewer — The output envelope after the step ran.

Property reference

Every setting, with its type and default — the same fields shown configured above.

Property	Type	Default	Description
Operation `op`	`select`	`"recall"`	Memory operation to perform. append adds ONE ENTRY PER RECORD — a list of ten turns leaves ten entries (and counts as ten against Max items). recall/get/set/clear act once on the key, whatever arrives. `appendcleargetrecallset`
Key `key`	`string`	`"conversation"`	Memory key (namespace) to operate on. Supports {{ }}: on append it is resolved against EACH record, so {{ $json.chatId }} over a list of ten addresses ten conversations; the whole-value ops (recall/get/set/clear) resolve it once against the whole input. An expression that resolves to nothing fails with MEMORY_CONFIG_INVALID rather than writing to a literal key.
Value `value`	`json`	`—`	Value to append/set — on append it is resolved against THIS record, so one mapping stores N different entries. Use the ƒ button to pick a field from the incoming data ({{ $json.… }}). Leave it unset and each record stores itself; note that a LIST then appends one entry per element, so to keep a whole page of results as a SINGLE entry wrap it first ({ items: [...] } from a Set/Aggregate step is one record). Shown when `op === "append" \|\| op === "set"`
Recall limit `limit`	`int`	`20`	Max items returned by recall. Shown when `op === "recall"`
Max items `maxItems`	`int`	`—`	Optional cap on stored items.

Related nodes

The rest of the Storage group — the same folder you’d scan in the editor’s library.

This page is generated from the node registry by gen-node-docs.mjs on every site build — ports, properties, defaults and visibility rules cannot drift from the code. The screenshots and example data are captured from a live Flowdrome by npm run shots:nodes and npm run gen:examples.