Skip to main content
Glama
slowave

slowave

Official
by slowave-ai

slowave_remember

Store durable facts, preferences, and decisions as persistent memory so future tasks reuse verified knowledge instead of rework or repeated questions.

Instructions

Record newly discovered knowledge worth retaining for future tasks in this scope. Scalar and batch forms inherit one explicitly verified session and scope. Proactively call this when you discover new knowledge worth retaining as durable memory because it could help you with future tasks: pursue a goal, avoid rework or a wrong assumption, or avoid asking the user again. Do not wait for the user to say “remember”. Good candidates are confirmed facts, user preferences, decisions, constraints, lessons, warnings, and open questions that affect future goals. Save the claim when it becomes clear; review for missed claims before commit. Use concise, standalone wording with enough context for a later session, and batch independent claims. Check activated memories and task context for duplicates; a matched claim is acceptable. Skip speculation, progress notes, pending steps, temporary task state, and details unlikely to matter again. A fact recorded elsewhere can still be worth saving when rediscovery would cost meaningful work.

Write for later retrieval: use one independent claim per entry and name its subject explicitly instead of "this" or "that approach". Preserve conditions, exceptions, and negation; include the reason for a decision when it explains when to apply it. Keep meaningful exact names, identifiers, commands, and error text alongside natural-language context. Retrieval considers meaning and specific terms, so avoid keyword lists, repeated synonyms, and unrelated claims in one entry. For example, prefer "Atlas authentication credentials expire after 45 minutes" to "Tokens: timeout, expiry, login, auth; same as discussed above." Include source/time context when it affects applicability, and use occurred_at only for the source-event time described below.

Args: scope: required scope matching the active session. session_id: required active session returned by slowave_activate. content: one standalone durable claim; mutually exclusive with memories. type: required scalar type. Reusable directions use instruction; only verified commit procedures are execution-backed procedures. occurred_at: optional RFC 3339 source-event time, such as 2026-08-26T09:30:00Z. Use only when the claim records an event that happened at a different time from this MCP call. Slowave always sets internal raw-event ts itself to the write time; occurred_at never changes event order. memories: strict batch of {content, type, occurred_at?, always?} objects inheriting the outer scope and session. always: optional true marks a standing rule that must reach every task in this scope (for example "never add Co-Authored-By lines").

Returns: stored: true when the scalar claim was accepted. memory_id: canonical identifier for a scalar stored or matched memory. disposition: created or matched for a scalar claim. type: confirmed scalar memory type. scope: confirmed scalar memory scope. source_event_id: source provenance event for a scalar claim. results: for batch input, ordered item envelopes with index and independent ok/data or ok/error results.

Input Schema

NameRequiredDescriptionDefault
typeNo
scopeYes
alwaysNo
contentNo
memoriesNoBatch mode: omit outer content, type and occurred_at; each entry supplies its own claim fields.
session_idYes
visibilityNouser: store as a user-wide rule delivered in every project.
occurred_atNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.20.9
    • addedInput schema / $defs / RememberEntry / properties / always
      Added value: +{
      +  "default": false,
      +  "title": "Always",
      +  "type": "boolean"
      +}
    • addedInput schema / $defs / RememberEntry / properties / content / maxLength
      Added value: +65536
    • addedInput schema / properties / always
      Added value: +{
      +  "default": false,
      +  "title": "Always",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / content / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "maxLength": 65536,
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / scope / maxLength
      Added value: +200
    • addedInput schema / properties / visibility
      Added value: +{
      +  "anyOf": [
      +    {
      +      "const": "user",
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "user: store as a user-wide rule delivered in every project.",
      +  "title": "Visibility"
      +}
  2. Changed3 schema fields changedv0.20.5
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "memories": [
      +      {
      +        "content": "A standalone claim",
      +        "type": "fact"
      +      }
      +    ],
      +    "scope": "project:<repo>",
      +    "session_id": "<active>"
      +  }
      +]
    • addedInput schema / oneOf
      Added value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "memories"
      +      ]
      +    },
      +    "required": [
      +      "content",
      +      "type"
      +    ],
      +    "title": "Scalar claim"
      +  },
      +  {
      +    "not": {
      +      "anyOf": [
      +        {
      +          "required": [
      +            "content"
      +          ]
      +        },
      +        {
      +          "required": [
      +            "type"
      +          ]
      +        },
      +        {
      +          "required": [
      +            "occurred_at"
      +          ]
      +        }
      +      ]
      +    },
      +    "required": [
      +      "memories"
      +    ],
      +    "title": "Batch claims"
      +  }
      +]
    • addedInput schema / properties / memories / description
      Added value: +"Batch mode: omit outer content, type and occurred_at; each entry supplies its own claim fields."
  3. First observedv0.20.3

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses dedup/matching behavior ('a matched claim is acceptable', disposition created vs. matched), that internal raw-event ts is always the write time and occurred_at never reorders events, and that batch items return independent ok/error envelopes. It stops short of stating whether claims can later be edited or deleted, or any limits on volume.

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

Conciseness4/5

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

Front-loads the trigger condition and exclusions before the writing-style guidance, and each paragraph is topical. It is long for a tool description, and the 'write for later retrieval' block plus the worked example could be tightened, but nearly every sentence carries actionable instruction.

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?

Complete for an 8-parameter mutation tool with an output schema: activation prerequisites, scope matching, batch error semantics, and provenance are all covered. The Returns block mirrors the output schema, so return values need no further explanation.

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 coverage is only 25%, so the description must compensate and it does: it defines scope/session inheritance, content vs. memories mutual exclusivity, batch entry fields, and adds real semantics beyond the enums - instruction for reusable directions, 'execution-backed procedures' only for verified commit steps, and an RFC 3339 example for occurred_at with its ordering caveat. Only visibility is left to the schema's own description.

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

Purpose4/5

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

States a specific verb and resource - record newly discovered knowledge as durable memory in a scope - and clarifies the scalar vs. batch forms and that they share one session/scope. It does not explicitly contrast itself with siblings like slowave_commit or slowave_recall, leaving the write-vs-commit boundary implicit.

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

Usage Guidelines5/5

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

Gives explicit when-to-use triggers (pursue a goal, avoid rework, avoid re-asking the user), tells the agent not to wait for the user to say 'remember', enumerates good candidate categories, and lists concrete exclusions (speculation, progress notes, pending steps, temporary task state). It also instructs a duplicate check against activated memories before writing.

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