Skip to main content
Glama

remember

DestructiveIdempotent

Save decisions, conventions, and preferences to persistent memory with an upsert-by-key write that updates existing entries instead of duplicating them.

Instructions

Save knowledge to persistent memory. Stores decisions, conventions, preferences. UPSERT by key — calling with same key updates the existing entry. Content is screened on write and REFUSED with a named reason (never silently stripped or stored) if it contains invisible/bidi characters, an LLM role tag, an instruction to ignore previous/system instructions, a PEM private key, a prefixed API token (sk-/ghp_/xox*/AKIA), or a literal assignment to a *_PASSWORD/_SECRET/_TOKEN/_API_KEY name. LIMITATION — this screen is partial and is not a secret filter: it cannot see a secret that has no recognisable prefix and no field name next to it (a bare value pasted on its own line), nor names it does not know. Credentials pasted here are not guaranteed to be caught; content stores where a secret lives, not its value.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "key": "<key>",
      "content": "<content>"
    },
    "name": "remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYesSlug key for UPSERT (e.g. 'api-convention', 'license-decision'). ENFORCED server-side as ^[a-z0-9][a-z0-9-]*[a-z0-9]$ — lowercase alphanumeric and hyphens only, at least two characters, no leading or trailing hyphen. Hyphens only, no colons: a colon-delimited key such as 'episode:alice:2026-09-07' is refused with a validation error — it is not normalised or accepted with a warning.
tagsNoTags for categorization and filtering. A kind: tag also SETS importance_score, which is what decides whether recall returns this entry at its default threshold of 0.3 — so the tag you choose is a retrieval decision, not a label. Base score by kind: kind:pinned 1.0, kind:incident 0.85, kind:decision 0.80, kind:preference 0.80, kind:learning 0.70, kind:fact 0.60, no kind: tag 0.50, kind:session-checkpoint 0.30. kind:session-checkpoint is a DOWNGRADE that overrides every other kind: tag on the same entry — tagging it alongside kind:decision yields 0.30, not 0.80. Any kind: value not in that list (e.g. kind:canonical-decision) is unrecognised and scores 0.50. Two boosts of +0.10 each, capped at 1.0: content mentioning icp / architecture / license / security / money, and a relevance:<n> tag whose n is >= 0.8.
scopeNoworkspace | project | agent (default: project).
reasonNoWhy this memory is worth writing — what a future thread should be able to do with it, or what changed if you are correcting an existing key. Recorded on the revision alongside the content, so a later reader can judge whether the entry still applies instead of guessing from the text alone. Optional today and about to become required; write it now.
contentYesWhat to remember (markdown).
relevanceNoRelevance score 0-1 (default 1.0 when omitted). NOT the same field as importance_score: relevance is a caller-set ranking hint, importance_score is computed from tags (see tags) and is the field min_importance filters on. A relevance:<n> TAG with n >= 0.8 does feed importance_score by +0.10; this numeric parameter does not.
thread_idNoThread identifier for same-session memory grouping. Auto-populated from the runner state file when omitted.
expires_atNoRFC3339 timestamp or Go duration (e.g. '72h') when this memory should expire. Hidden from recall and get_memory the moment it expires; physically deleted by the background cleanup (every 6 h) 7 days after expiry. To take an entry out of recall so it can be brought back, use archive_memory instead.
project_idNoProject ID (required for project scope).
source_urlNoOptional URL/path to the source of this knowledge (task ID, PR, file path).
attach_contextNoWhen false, disables auto-injection of thread_id and source_task_id. Use for cross-cutting records not tied to the active task.
source_task_idNoUUID of the Mesh task that produced this memory. Auto-populated from the runner state file (FIDDLER_STATE_FILE) or the active checkout. Enables Amendment 2/3 KG edge hooks.
expected_versionNoMake the write conditional: it succeeds only if the stored version still matches this number, and is REFUSED with both version numbers if someone else wrote to the key in between. Pass the version returned by your previous remember/recall of this key. Omit for last-write-wins.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.7
    • changedInput schema / properties / expires_at / description
      Previous value: -"RFC3339 timestamp or Go duration (e.g. '72h') when this memory should expire."New value: +"RFC3339 timestamp or Go duration (e.g. '72h') when this memory should expire. Hidden from recall and get_memory the moment it expires; physically deleted by the background cleanup (every 6 h) 7 days after expiry. To take an entry out of recall so it can be brought back, use archive_memory instead."
  2. Changed1 schema field changedv0.1.6
    • changedInput schema / properties / key / description
      Previous value: -"Slug key for UPSERT (e.g. 'api-convention', 'license-decision'). ENFORCED server-side as ^[a-z0-9][a-z0-9-]*[a-z0-9]$ — lowercase alphanumeric and hyphens only, at least two characters, no leading or trailing hyphen. Hyphens, NEVER colons: a colon-delimited key such as 'episode:alice:2026-09-07' is REFUSED with a validation error — it is not normalised or accepted with a warning."New value: +"Slug key for UPSERT (e.g. 'api-convention', 'license-decision'). ENFORCED server-side as ^[a-z0-9][a-z0-9-]*[a-z0-9]$ — lowercase alphanumeric and hyphens only, at least two characters, no leading or trailing hyphen. Hyphens only, no colons: a colon-delimited key such as 'episode:alice:2026-09-07' is refused with a validation error — it is not normalised or accepted with a warning."
  3. First observedv0.1.1

TDQS

A4.4/5.0
Behavior5/5

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

Far exceeds the annotations: it discloses UPSERT overwrite semantics, an enumerated write-time screening contract with named refusal reasons, and an explicit statement of the screen's limitations (no bare values, unknown field names). That limitation paragraph is exactly the kind of honest boundary disclosure annotations cannot convey, and nothing here contradicts destructiveHint=true.

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-loaded with purpose, then behavior, then a clearly marked LIMITATION paragraph, so an agent can stop reading early and still call it correctly. Density is high and the uppercase emphasis and hyphenated clauses are heavy, but every sentence carries information rather than filler.

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?

For a 13-parameter mutating tool with no output schema, the description covers the mutation model, refusal behavior, the screen's blind spots, and points to the schema for expiry/versioning mechanics. The only notable silence is the return payload, but the expected_version parameter implies a versioned response and the schema carries 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?

Schema coverage is already 100%, so the 3 baseline applies, but the description adds real meaning for the content parameter — what will be refused on write and why — which the schema's "What to remember (markdown)" does not cover. It does not restate the other eleven parameters, which is appropriate given the schema's own detail.

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?

States a specific verb and resource ("Save knowledge to persistent memory") and immediately scopes what qualifies (decisions, conventions, preferences). The UPSERT-by-key sentence tells an agent exactly how this differs from an append-only note tool like add_note, so the operation is unambiguous without opening the schema.

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

Usage Guidelines3/5

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

Usage is implied by the content scope list and by the explicit warning that credentials belong elsewhere ("content stores where a secret lives, not its value"). There is no direct routing to alternatives such as add_note or forget, and the only alternative named — archive_memory — appears inside a parameter description rather than as guidance in the main body.

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