Skip to main content
Glama
LeandroPG19

Cuba-Memorys

by LeandroPG19
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

memory_faro

Search long-term memory before answering to ground responses, verify claims against evidence, and return confidence scores with session-aware and temporal filters.

Instructions

[alias of cuba_faro] Search memory BEFORE answering to ground responses. Returns grounding scores. Mode 'verify' checks claims against evidence (confidence: verified/partial/weak/unknown). Session-aware: boosts results matching active session goals. Supports temporal filtering. Optional MMR diversification, OOD abstention and an exact tiktoken-based token budget.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoSearch mode (default: hybrid). 'verify' checks if claim is grounded.
tagsNoFilter observations by tag keyword (exact match against auto-extracted tags)
afterNoISO8601 datetime — return results created after this time
limitNoMax results (default 10, max 50)
queryYesSearch text
scopeNoWhere to search (default: all)
beforeNoISO8601 datetime — return results created before this time
formatNoResponse format. compact (DEFAULT): abbreviated keys — e=entity, c=content, t=type, i=importance, s=score. 71% fewer tokens (798 vs 2787 at limit=10, measured). verbose: full key names, only when you need every field.
rerankNoCross-encoder rerank top-50 → top-K with bge-reranker-v2-m3. Auto-enabled when CUBA_MODE=completo, or when this build has a real GPU provider active (CUDA/DirectML compiled in AND a working device). Off by default everywhere else, even with the model on disk: on CPU it costs 60-110s and blows the search budget. Explicit true/false always wins; run `memory-industry doctor` to see which reason applies here.
diversifyNoPost-RRF MMR pass that penalizes near-duplicates among top-K. Default false.
max_tokensNoToken budget for results (default 5000). Counted exactly via tiktoken cl100k_base.
mmr_lambdaNoMMR balance — 1.0 pure relevance, 0.0 pure diversity. Default 0.7.
abstain_oodNoAbstain (return empty results with abstain_reason) when the query is out-of-distribution via Mahalanobis distance. Default false.
associativeNoMulti-hop expansion: seeds spreading activation from query-matched entities and pulls in observations on graph-connected entities that no lexical/vector signal surfaced. Additive — never lowers a base hit. Default false.
enable_bm25NoEnable BM25 (ts_rank_cd) as third RRF signal alongside text + vector. Catches queries with rare terms that dense embeddings miss. Default true.
ood_thresholdNoMahalanobis distance threshold for abstention. Defaults to sqrt(chi2_0.99(d)), which scales with the embedding dimension (~21.25 for d=384). Override only if you calibrated on your own corpus.
include_unscopedNoWhen a project is active, rows with project_id NULL are hidden. Set true to include that leftover corpus. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.27.0
    • addedInput schema / properties / include_unscoped
      Added value: +{
+  "description": "When a project is active, rows with project_id NULL are hidden. Set true to include that leftover corpus. Default false.",
+  "type": "boolean"
+}
    • changedInput schema / properties / rerank / description
      Previous value: -"Cross-encoder rerank top-50 → top-K with bge-reranker-v2-m3. Auto-enabled when CUBA_MODE=completo, or when this build has a real GPU provider active (CUDA/DirectML compiled in AND a working device). Off by default everywhere else, even with the model on disk: on CPU it costs 60-110s and blows the search budget. Explicit true/false always wins; run `cuba-memorys doctor` to see which reason applies here."New value: +"Cross-encoder rerank top-50 → top-K with bge-reranker-v2-m3. Auto-enabled when CUBA_MODE=completo, or when this build has a real GPU provider active (CUDA/DirectML compiled in AND a working device). Off by default everywhere else, even with the model on disk: on CPU it costs 60-110s and blows the search budget. Explicit true/false always wins; run `memory-industry doctor` to see which reason applies here."
  2. Addedv0.25.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It discloses genuinely behavioral traits: session-aware goal boosting, grounding-score returns, confidence tiers (verified/partial/weak/unknown), and optional MMR/OOD/token-budget machinery. However it never states the operation is read-only/non-destructive, nor any auth, rate-limit or side-effect profile, so it is only adequate.

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 actionable directive and keeps to five tight sentences. The trailing feature list ('Optional MMR diversification, OOD abstention and an exact tiktoken-based token budget') slightly duplicates schema content but is short enough to be tolerable.

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

Completeness3/5

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

For a 17-parameter tool with no output schema, the description covers the intent and some return semantics (grounding scores, confidence categories) but does not describe result shape beyond that, and gives no guidance on the many optional flags. The alias note is a useful completeness touch, but gaps remain.

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

Parameters3/5

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

Schema description coverage is 100%, so all 17 parameters are self-documenting in the schema. The description only lightly echoes a few of them (verify mode, temporal filtering, MMR, OOD, token budget) without adding syntax or values beyond the schema, so baseline 3 applies.

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+resource (search memory) and its grounding intent ('BEFORE answering to ground responses'), plus the [alias of cuba_faro] tag which lets an agent deduplicate against a known sibling. It does not explicitly differentiate itself from the many other memory_* tools (memory_context, memory_expediente, memory_hipotesis), so it stops short of a 5.

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?

Gives a clear trigger ('Search memory BEFORE answering') and a mode-specific use case ('verify' checks claims against evidence). It does not name when NOT to use it or which sibling to prefer for non-grounding retrieval, so no explicit alternative routing.

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