Skip to main content
Glama

remember

Persist agent memories with tags, importance, source, and type. Supports supersession keys to retire obsolete values and lineage tracking for erasure compliance.

Instructions

Store a memory (append-only; raw text is never edited afterward). tags group memories into cohorts; value (>=1) is its importance — higher-value memories outrank merely-similar ones at recall. Recall does NOT change it: a read leaves value, last_access and the state digest as they were, so an anchor or witness pinned to the store stays valid across reads. credit is what moves a memory's standing after an outcome. mtype ∈ {episodic, semantic, procedural} sets the decay prior — episodic (events) fades fast, semantic (durable facts) slow, procedural (rules / preferences) barely; pass it when you know the kind, else it's inferred.

Optional key is a deterministic (subject, relation) supersession key (e.g. "billing-api::auth-method"): storing a new value with the same key retires the old one so recall never returns the stale value — no similarity threshold, no extra LLM call. Use it for facts that get updated (config, prices, versions, status). Pass object = the asserted VALUE (e.g. "frankfurt") alongside key: with the echo guard on (default here), a later RE-STATEMENT of an already-retired value cannot resurrect it (a corrected fact stays corrected even if the old value is said again). Without object the guard still catches a verbatim restatement (text hash), but a reworded one needs the value in object to be caught. Set reaffirm=True to intentionally revert to a previously-retired value (an explicit change-of-mind, not an echo).

source — WHO OR WHAT this came from ("crm/alice", "user-42", "docs.example.com/pricing"). Pass it whenever the memory is about, or came from, an identifiable person or system. It is what makes the memory reachable later by SUBJECT rather than only by id: forget_subject("crm/alice") erases a person's data and everything derived from it, erasure_audit can then say whether anything survived, and slash can forfeit a source's standing after a bad outcome. Without it a record is attributable to nothing, and none of those can reach it -- measured: a store written through this server answered would_erase=0 to every right-to-erasure request, while the same write with a source answered 1.

derived_from — the ids this memory was BUILT FROM (a summary, a merge, a conclusion drawn from earlier notes). Provenance rides along the edge: erasing the source erases what was derived from it, so a summary of a person's file goes when their file goes. erasure_audit walks these edges and reports unaudited -- never a pass -- when nothing declares them, because a store with no edges to walk has not been checked, it has been left uninspected.

If this server was started with a PROJECT scope (--project <name> / INSPEXIMUS_PROJECT), the memory is stamped with it and later recalls in OTHER projects will not return it. The active scope is echoed back as project in the result (null = unscoped, shared by every project).

Returns the new id, and the VERDICT on the write: blocked is true when a keyed write was retired on arrival (policy names the guard, current_id the value that stands, note what to do); lineage_dropped is the anchor count of the value this write followed when this write carries no derived_from; persisted is false when the save after the write failed (persist_error says why; the server retries on its next write). A result with blocked: true or persisted: false is not a landed write.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNo
tagsNo
textYes
mtypeNo
valueNo
objectNo
sourceNo
user_idNo
agent_idNo
reaffirmNo
session_idNo
derived_fromNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2.20.1
    • addedInput schema / properties / agent_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Agent Id"
      +}
    • addedInput schema / properties / derived_from
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Derived From"
      +}
    • addedInput schema / properties / session_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Session Id"
      +}
    • addedInput schema / properties / source
      Added value: +{
      +  "default": "",
      +  "title": "Source",
      +  "type": "string"
      +}
    • addedInput schema / properties / user_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "User Id"
      +}
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full behavioral burden, and it does so thoroughly. It discloses append-only semantics, read-invariance of value/last_access/digest, supersession and echo-guard behavior, persistence failure and retries, provenance edges, and project scoping. There is no contradiction with annotations because none exist.

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 exceptionally dense and well-organized, front-loading the core append-only constraint before walking through parameters and return semantics. Each paragraph covers a distinct behavioral axis, and the length is proportionate to the complexity of a 12-parameter persistence tool with non-obvious semantics.

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

Completeness4/5

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

The description is remarkably complete for a tool with no output schema and no annotations: it explains return fields, error cases, project scoping, provenance, and behavioral invariants. It falls short only in omitting the three identity/session parameters (`user_id`, `agent_id`, `session_id`) and leaving some phrases like `lineage_dropped` more terse than the rest.

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

Parameters4/5

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

With schema description coverage at 0%, the description compensates well for most parameters, giving meaningful semantics to text, tags, value, mtype, key, object, reaffirm, source, and derived_from. However, `user_id`, `agent_id`, and `session_id` are completely unexplained in both the schema and the description, leaving a real gap.

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 a memory', and immediately adds the defining constraint (append-only, raw text never edited). It clearly distinguishes this tool from recall/get/forget_subject and other storage-adjacent siblings by explaining what this write operation does, how it scopes memories, and what it returns.

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?

The description gives rich conditional guidance: use `key` for facts that get updated, pass `source` whenever the memory relates to an identifiable person or system, use `mtype` when the kind is known, and set `reaffirm=True` for intentional reversion. It does not explicitly compare against sibling write tools like `remember_decision` or `remember_in_partition`, so the when-not-to-use guidance is implicit rather than explicit.

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

Deploy Server

Other Tools