add_node
Aggiunge un nodo alla memoria neurale
LABSCO SUMMARY
Confidence scores on recall are what let a model treat a weak match as weak instead of narrating it as fact.
An unscored memory search returns its best guess with the same presentation as a certain hit, and the model downstream cannot tell them apart. Attaching confidence gives it something to be uncertain with. The strict schema on skill registration is the same instinct at write time — a registry that accepts anything becomes unqueryable within a few dozen entries. An HTML memory report is an unusual inclusion and a practical one: being able to look at what the memory actually contains is how you find out it has been accumulating nonsense. Tool descriptions are in Italian.
What it is
A memory server combining three things: a searchable node graph, a registry of skills held to a mandatory schema, and saved working-context snapshots.
What you get
- search_nodes returns results with confidence scoring rather than a flat list, so weak matches are distinguishable from strong ones.
- register_skill enforces a strict mandatory schema — a name is required among the fields — which is what keeps a skill registry from becoming free-text notes.
- suggest_skills proposes relevant skills from the current context rather than waiting to be asked.
- save_context_snapshot stores a detailed working context and restore_context brings it back, which is session continuity as an explicit operation.
- get_memory_report generates a report of the memory as JSON or HTML — so the store is inspectable rather than opaque.
Requirements
Nothing to supply.
Setup effort
One command — npx -y @drakonkat/neural-memory@latest
USE CASES
01
Remembering something and finding it later
Add the node, then search by keywords with confidence scores so a weak match is visibly weak.
02
Keeping reusable skills usable
Register them against the mandatory schema rather than as free text, and let relevant ones be suggested from context.
03
Picking up where you left off
Snapshot the working context deliberately and restore it in the next session.
04
Checking the memory is not full of rubbish
Generate the report as HTML and actually look at what has accumulated.
8 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
delete_node
Elimina un nodo
get_memory_report
Genera report della memoria in formato JSON o HTML
register_skill
Registra una SKILL con schema rigido obbligatorio. Schema: name (obbligatorio), framework, language, filePattern, learnSteps[], useCases[].
restore_context
Recupera un contesto salvato
save_context_snapshot
Salva snapshot dettagliato del contesto di lavoro
search_nodes
Cerca nodi per keywords con confidence scoring
suggest_skills
Suggerisce skills rilevanti basate sul contesto corrente
BEFORE YOU INSTALL
What to know first
Tools you get
8 tools when we connected.
Requires
npx on PATH
CONTEXT COST
Light Standing cost
Rated by the size of the 8 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"neural-memory": {
"command": "npx",
"args": [
"-y",
"@drakonkat/neural-memory@latest"
]
}
}
}npx
TERMINAL
npx -y @drakonkat/neural-memory@latest
