Cuba-Memorys

Overview Schema Source Related Servers Discussions Admin

cuba_faro

Search long-term agent memory before answering to ground responses and verify claims against evidence, returning grounding confidence scores.

Instructions

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

Name	Required	Description
`mode`	No	Search mode (default: hybrid). 'verify' checks if claim is grounded.
`tags`	No	Filter observations by tag keyword (exact match against auto-extracted tags)
`after`	No	ISO8601 datetime — return results created after this time
`limit`	No	Max results (default 10, max 50)
`query`	Yes	Search text
`scope`	No	Where to search (default: all)
`before`	No	ISO8601 datetime — return results created before this time
`format`	No	Response 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.
`rerank`	No	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.
`diversify`	No	Post-RRF MMR pass that penalizes near-duplicates among top-K. Default false.
`max_tokens`	No	Token budget for results (default 5000). Counted exactly via tiktoken cl100k_base.
`mmr_lambda`	No	MMR balance — 1.0 pure relevance, 0.0 pure diversity. Default 0.7.
`abstain_ood`	No	Abstain (return empty results with abstain_reason) when the query is out-of-distribution via Mahalanobis distance. Default false.
`associative`	No	Multi-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_bm25`	No	Enable BM25 (ts_rank_cd) as third RRF signal alongside text + vector. Catches queries with rare terms that dense embeddings miss. Default true.
`ood_threshold`	No	Mahalanobis 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_unscoped`	No	When 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.

Changed2 schema fields changedv0.27.0Sep 30, 2026

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."

Changed7 schema fields changedv0.25.0Sep 12, 2026

changedInput schema / properties / abstain_ood / description

Previous value: -"v0.9: abstain (return empty results with abstain_reason) when query is out-of-distribution via Mahalanobis distance. Default false."New value: +"Abstain (return empty results with abstain_reason) when the query is out-of-distribution via Mahalanobis distance. Default false."

changedInput schema / properties / associative / description

Previous value: -"v0.11: multi-hop expansion (HippoRAG-style). 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. Measured +10pts recall@10 on the smoke set. Default false."New value: +"Multi-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."

changedInput schema / properties / diversify / description

Previous value: -"v0.9: post-RRF MMR pass that penalizes near-duplicates among top-K. Default false."New value: +"Post-RRF MMR pass that penalizes near-duplicates among top-K. Default false."

changedInput schema / properties / enable_bm25 / description

Previous value: -"v0.9: enable BM25 (ts_rank_cd) as third RRF signal alongside text + vector. Catches queries with rare terms that dense embeddings miss. Default true."New value: +"Enable BM25 (ts_rank_cd) as third RRF signal alongside text + vector. Catches queries with rare terms that dense embeddings miss. Default true."

changedInput schema / properties / mmr_lambda / description

Previous value: -"v0.9: MMR balance — 1.0 pure relevance, 0.0 pure diversity. Default 0.7."New value: +"MMR balance — 1.0 pure relevance, 0.0 pure diversity. Default 0.7."

changedInput schema / properties / ood_threshold / description

Previous value: -"v0.9: Mahalanobis 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."New value: +"Mahalanobis 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."

changedInput schema / properties / rerank / description

Previous value: -"v0.9.2: cross-encoder rerank top-50 → top-K with bge-reranker-v2-m3 (Xiao 2023). Auto-enabled when CUBA_RERANKER_PATH points to a valid ONNX. Identity fallback otherwise."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 `cuba-memorys doctor` to see which reason applies here."

First observedv0.18.0Jul 29, 2026

TDQS

A3.9/5.0

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 discloses meaningful behavior: grounding scores, verify-mode confidence levels, session-aware boosting, temporal filtering, and optional MMR, OOD abstention, and token budgeting. It does not cover auth requirements or default operational details like the compact response format, which are left to the schema.

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?

The description is front-loaded with purpose and is reasonably sized for a 17-parameter tool. It uses multiple short sentences to cover distinct features, though it could be slightly tighter.

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?

For a complex search tool with no output schema and 100% schema coverage, the description provides enough context to understand the main modes and optional behaviors. It mentions returning grounding scores, but does not elaborate on the return shape, which is acceptable given the detailed parameter schema.

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 the baseline is 3. The description mentions mode verify, temporal filtering, diversification, OOD abstention, and token budget, but these largely restate or lightly expand on what the schema already documents, adding little parameter-specific meaning beyond the structured fields.

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?

The description states a specific verb and resource: searching memory to ground responses. It clearly explains the tool's role in retrieval and grounding, though it does not differentiate itself from sibling tools such as memory_faro or cuba_contexto.

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 clear contextual guidance: search memory BEFORE answering to ground responses. It does not explicitly name when not to use the tool or which alternatives to prefer, but the timing guidance is strong.

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

Deploy Server

cuba_faro

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools