Skip to main content
Glama

remember

Persist important decisions, preferences, facts, and project context into searchable cognitive memory with importance, domain, and metadata for later recall.

Instructions

Store one or more memories in persistent cognitive memory.

WHEN TO USE: Call proactively whenever the conversation reveals something worth remembering — decisions, preferences, facts about people, project context. Do NOT store ephemeral task details, code snippets, or git-derivable info.

SINGLE: remember(text="User prefers dark mode", domain="preference", importance=0.7) BATCH: remember(memories=[{"text": "Alice is DevOps lead", "domain": "people"}, ...]) DRAFT: remember(summary="...long end-of-session summary...") — v0.8.0+ engine atomizes the summary into linked semantic facts; useful for the end-of-session auto-capture pattern.

IMPORTANCE: 0.8-1.0 critical decisions | 0.5-0.7 useful context | 0.3-0.5 background

Args: text: Memory text (for single memory). Be specific and searchable. memory_type: "semantic" (facts), "episodic" (events), "procedural" (how-to). importance: 0.0-1.0. Higher = remembered longer. domain: "work", "preference", "architecture", "people", "infrastructure", "health", "finance", "general". source: "user", "inference", "document", "system". valence: Emotional tone (-1.0 to 1.0). 0.0 neutral. metadata: Optional key-value pairs. namespace: For per-project isolation. certainty: Confidence 0.0-1.0. emotional_state: joy, frustration, excitement, concern, neutral. memories: List of memory dicts for batch. summary: For draft mode — long summary that the engine atomizes. idempotency_key: v0.10 engine — makes the write exactly-once: retrying with the same key + same text returns the SAME rid with no second write; same key + different text is an error. Engine-embedder (bundled) backend only. On batch, the key scopes per item as "{key}:{index}" if the atomic batch path is unavailable. created_at: v0.14 engine — BACKDATE the memory to when it was actually true, not when you imported it. Use for backfill (chat logs, migrations). Without it every imported memory stamps "now", which makes temporal(action="as_of") report history that never happened and flattens staleness/decay. Same formats as as_of: "2026-08-01", "2026-08-01T14:30:00Z", "7d" (ago), or unix seconds. Omit for anything learned in the present conversation. claims: v0.19 engine — facts this memory states, as [{"subject", "relation", "object"}]; state one for any fact you want tracked (contradiction, succession, multi-hop). Subject and object must occur in the text, relation is snake_case; ungrounded ones are reported back, not stored. Batch items take their own "claims". A claim may carry "valid_from"/"valid_to" (created_at formats). event_time: when the memory is ABOUT, not when written (created_at formats). Time-travel recall reads it and every claim on the memory inherits it as valid_from, so an older fact is the predecessor of a newer one, not its contradiction.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textNo
claimsNo
domainNogeneral
sourceNouser
summaryNo
valenceNo
memoriesNo
metadataNo
certaintyNo
namespaceNodefault
created_atNo
event_timeNo
importanceNo
memory_typeNosemantic
emotional_stateNo
idempotency_keyNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.21.0
    • addedInput schema / properties / claims
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "additionalProperties": true,
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Claims"
      +}
    • addedInput schema / properties / event_time
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Event Time"
      +}
  2. Changed1 schema field changedv0.19.2
    • addedInput schema / properties / created_at
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Created At"
      +}
  3. Changed1 schema field changedv0.10.0
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Idempotency Key"
      +}
  4. First observedv0.9.0

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, it discloses rich behavioral detail: three call modes (SINGLE/BATCH/DRAFT), importance/decay semantics, exact-once idempotency behavior and its backend limitations, created_at backdating effects on temporal queries, grounded claims behavior ('ungrounded ones are reported back, not stored'), and event_time claim inheritance. This gives an agent a strong model of side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but appropriately so for a 16-parameter write tool with no schema descriptions. It is front-loaded with the core purpose and WHEN TO USE, uses clear headers, compact examples, and keeps each param annotation targeted. No filler is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, the description covers all call patterns, param semantics, engine-version caveats, and temporal/idempotency edge cases. An output schema exists so return-value details are not required; nothing an agent needs to decide whether and how to invoke remember is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden for 16 parameters, and it succeeds: every parameter is explained, with default values, allowed domain values, importance ranges, created_at formats, claims structure, and examples. It adds substantial meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Store one or more memories in persistent cognitive memory.' It clearly identifies the tool's function and is distinct from sibling tools like recall, forget, and graph; no part of it restates the tool name or title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit WHEN TO USE guidance ('Call proactively whenever...') and explicit exclusions ('Do NOT store ephemeral task details, code snippets, or git-derivable info'). However, it does not name a sibling tool or alternative condition for cases where storage is not appropriate, so it falls just short of the full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.