CRUD knowledge graph entities (concepts, projects, technologies, patterns, people). Auto-boosts neighbors on access. For transient info use cuba_cronica instead.

[alias of cuba_alma] CRUD knowledge graph entities (concepts, projects, technologies, patterns, people). Auto-boosts neighbors on access. For transient info use cuba_cronica instead.

Attach facts/lessons/decisions to entities. Also manages episodic memories (specific events with actors/artifacts) via episode_add/episode_list. Timeline view shows chronological history. Auto-creates entity if not found. Dedup gate blocks near-duplicates.

[alias of cuba_cronica] Attach facts/lessons/decisions to entities. Also manages episodic memories (specific events with actors/artifacts) via episode_add/episode_list. Timeline view shows chronological history. Auto-creates entity if not found. Dedup gate blocks near-duplicates.

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.

[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.

Create edges between entities (uses, causes, implements, depends_on, related_to). 'traverse' explores connections, 'infer' does transitive reasoning (A→B→C), 'predict' suggests missing links via Adamic-Adar. Relations strengthen with use (Hebbian).

[alias of cuba_puente] Create edges between entities (uses, causes, implements, depends_on, related_to). 'traverse' explores connections, 'infer' does transitive reasoning (A→B→C), 'predict' suggests missing links via Adamic-Adar. Relations strengthen with use (Hebbian).

RLHF feedback: positive boosts importance (Oja's rule), negative decreases, correct updates content. Also the quarantine gate: 'pending' lists memories withheld from search because they came from untrusted text, 'promote' makes one retrievable, 'quarantine' withdraws one. The gate covers observations, episodes and errors — pick which with 'kind'.

[alias of cuba_eco] RLHF feedback: positive boosts importance (Oja's rule), negative decreases, correct updates content. Also the quarantine gate: 'pending' lists memories withheld from search because they came from untrusted text, 'promote' makes one retrievable, 'quarantine' withdraws one. The gate covers observations, episodes and errors — pick which with 'kind'.

Report errors immediately. Auto-detects patterns (≥3 similar = warning). Hebbian: similar errors get boosted for easier retrieval.

[alias of cuba_alarma] Report errors immediately. Auto-detects patterns (≥3 similar = warning). Hebbian: similar errors get boosted for easier retrieval.

Mark an error as resolved with solution. Cross-references similar unresolved errors.

[alias of cuba_remedio] Mark an error as resolved with solution. Cross-references similar unresolved errors.

Search past errors/solutions. Use 'proposed_action' as anti-repetition guard: warns if similar approach previously failed.

[alias of cuba_expediente] Search past errors/solutions. Use 'proposed_action' as anti-repetition guard: warns if similar approach previously failed.

Track working sessions with goals and outcomes. v0.8: optional 'project' arg binds the session to a named project (upserts in brain_projects); subsequent handlers will scope reads/writes to that project.

[alias of cuba_jornada] Track working sessions with goals and outcomes. v0.8: optional 'project' arg binds the session to a named project (upserts in brain_projects); subsequent handlers will scope reads/writes to that project.

Record and query architecture/design decisions.

[alias of cuba_decreto] Record and query architecture/design decisions.

Knowledge graph analytics: summary, health, drift, communities, bridges, structural.

[alias of cuba_vigia] Knowledge graph analytics: summary, health, drift, communities, bridges, structural.

Memory maintenance, scoped to the active project: decay, prune, merge, summarize, pagerank, find_duplicates, export, reembed, decay_episodes.

[alias of cuba_zafra] Memory maintenance, scoped to the active project: decay, prune, merge, summarize, pagerank, find_duplicates, export, reembed, decay_episodes.

GDPR Right to Erasure: cascading hard-delete of an entity and ALL references across observations, relations, errors, and sessions. IRREVERSIBLE. Requires confirm=true.

[alias of cuba_forget] GDPR Right to Erasure: cascading hard-delete of an entity and ALL references across observations, relations, errors, and sessions. IRREVERSIBLE. Requires confirm=true.

Analyze the knowledge graph for structural gaps. Read-only.

[alias of cuba_reflexion] Analyze the knowledge graph for structural gaps. Read-only.

Abductive inference: find plausible causes of an observed effect. Read-only.

[alias of cuba_hipotesis] Abductive inference: find plausible causes of an observed effect. Read-only.

Detect semantic contradictions between observations of the same entity. Uses embedding cosine distance + negation heuristics. Read-only.

[alias of cuba_contradiccion] Detect semantic contradictions between observations of the same entity. Uses embedding cosine distance + negation heuristics. Read-only.

Prospective memory: triggers that fire on entity access, session start, or error match. 'Remember to remind me about X when Y happens.'

[alias of cuba_centinela] Prospective memory: triggers that fire on entity access, session start, or error match. 'Remember to remind me about X when Y happens.'

Bayesian confidence calibration: track verify predictions, mark outcomes, compute P(correct|level). Closes the feedback loop between faro verify and eco correct.

[alias of cuba_calibrar] Bayesian confidence calibration: track verify predictions, mark outcomes, compute P(correct|level). Closes the feedback loop between faro verify and eco correct.

Bulk knowledge ingestion. 'ingest': array of {entity_name, content, observation_type} items. 'parse': split long text by paragraphs + heuristic classify. 'auto_extract' (v0.11): the calling client's LLM extracts salient durable facts from a turn/conversation via MCP Sampling ($0, no API key) and ingests them — the automatic-extraction that mem0/Zep have. All routes share the dedup/PE-gating/embedding pipeline; none delete.

[alias of cuba_ingesta] Bulk knowledge ingestion. 'ingest': array of {entity_name, content, observation_type} items. 'parse': split long text by paragraphs + heuristic classify. 'auto_extract' (v0.11): the calling client's LLM extracts salient durable facts from a turn/conversation via MCP Sampling ($0, no API key) and ingests them — the automatic-extraction that mem0/Zep have. All routes share the dedup/PE-gating/embedding pipeline; none delete.

Project scoping (v0.8): isolate memories per project so multiple projects sharing one DB don't bleed into each other. Active project is bound to the current session (cuba_jornada start --project NAME). Legacy NULL project_id rows are hidden while a project is active unless faro include_unscoped=true or you backfill them.

[alias of cuba_proyecto] Project scoping (v0.8): isolate memories per project so multiple projects sharing one DB don't bleed into each other. Active project is bound to the current session (cuba_jornada start --project NAME). Legacy NULL project_id rows are hidden while a project is active unless faro include_unscoped=true or you backfill them.

Compaction-survival protocol: persist and restore a session summary across /compact.

[alias of cuba_pre_compact] Compaction-survival protocol: persist and restore a session summary across /compact.

Git-friendly export/import of the knowledge graph between machines that share no database. export/import/diff/status work on a local directory, ./.memory-industry/ by default and otherwise as the dir parameter describes; pull/notify/fetch/conflicts/resolve talk to a peer over HTTP with CUBA_PEER_TOKEN.

[alias of cuba_sync] Git-friendly export/import of the knowledge graph between machines that share no database. export/import/diff/status work on a local directory, ./.memory-industry/ by default and otherwise as the dir parameter describes; pull/notify/fetch/conflicts/resolve talk to a peer over HTTP with CUBA_PEER_TOKEN.

Tamper-evident audit log: append-only, SHA-256 hash chain, UPDATE/DELETE blocked at the PostgreSQL trigger level.

[alias of cuba_archivo] Tamper-evident audit log: append-only, SHA-256 hash chain, UPDATE/DELETE blocked at the PostgreSQL trigger level.

Working memory buffer (v0.9, Baddeley 1992): a TTL-bounded scratchpad orthogonal to episodic and semantic memory. Use for inter-step plan state during long-horizon agent tasks, tentative observations, cross-tool-call reminders inside one session. Auto-expire by ttl_seconds; bulk-purged by cuba_zafra REM cycle.

[alias of cuba_pizarra] Working memory buffer (v0.9, Baddeley 1992): a TTL-bounded scratchpad orthogonal to episodic and semantic memory. Use for inter-step plan state during long-horizon agent tasks, tentative observations, cross-tool-call reminders inside one session. Auto-expire by ttl_seconds; bulk-purged by cuba_zafra REM cycle.

LLM-judge for semantically-conflicting observations in the ambiguous cosine-similarity band (0.6-0.8), where heuristics miss vocabulary-different conflicts. Verdicts are cached in brain_judgments.

[alias of cuba_juez] LLM-judge for semantically-conflicting observations in the ambiguous cosine-similarity band (0.6-0.8), where heuristics miss vocabulary-different conflicts. Verdicts are cached in brain_judgments.

Identify this MCP client against the MemoryIndustry daemon: client id, project, session, node, LLM, graph-db, resource plan. Alias: memory_whoami.

[alias of cuba_whoami] Identify this MCP client against the MemoryIndustry daemon: client id, project, session, node, LLM, graph-db, resource plan. Alias: memory_whoami.

Shared versioned artifacts between agents on the same daemon (and peers). put requires base_version (optimistic concurrency); lock is a short lease. Alias: memory_artifact.

[alias of cuba_artefacto] Shared versioned artifacts between agents on the same daemon (and peers). put requires base_version (optimistic concurrency); lock is a short lease. Alias: memory_artifact.

Visible context window for the agent: working memory + agent notes (exact Mcp-Client-Id) + artifact index + recall of this session's recent writes (then WM mentions, then importance). Call at the start of a turn; call cuba_cronica add BEFORE editing. Alias: memory_context.

[alias of cuba_contexto] Visible context window for the agent: working memory + agent notes (exact Mcp-Client-Id) + artifact index + recall of this session's recent writes (then WM mentions, then importance). Call at the start of a turn; call cuba_cronica add BEFORE editing. Alias: memory_context.

PROCEDURAL MEMORY: how things are DONE here — bring up the dev services, run the test suite, deploy, migrate. The other tools remember what is TRUE; this one remembers what to DO, so an agent stops rediscovering it every session. Ranked by reliability, not by how often it is read: report the outcome with action='outcome' after running one, or the memory learns nothing. A recipe that keeps failing is worse than none, because it is trusted.

[alias of cuba_receta] PROCEDURAL MEMORY: how things are DONE here — bring up the dev services, run the test suite, deploy, migrate. The other tools remember what is TRUE; this one remembers what to DO, so an agent stops rediscovering it every session. Ranked by reliability, not by how often it is read: report the outcome with action='outcome' after running one, or the memory learns nothing. A recipe that keeps failing is worse than none, because it is trusted.

Find MemoryIndustry tools and load their schemas ON DEMAND. The server exposes 31 tools; under CUBA_TOOL_PROFILE=lean only the everyday core is pre-loaded and the rest live here. Search by capability ('audit', 'decay', 'contradiction', 'session'), then call what you find with cuba_call. detail='names' is cheapest, 'full' returns the exact argument schema.

[alias of cuba_tools] Find MemoryIndustry tools and load their schemas ON DEMAND. The server exposes 31 tools; under CUBA_TOOL_PROFILE=lean only the everyday core is pre-loaded and the rest live here. Search by capability ('audit', 'decay', 'contradiction', 'session'), then call what you find with cuba_call. detail='names' is cheapest, 'full' returns the exact argument schema.

Invoke any MemoryIndustry tool by name — including the ones not pre-loaded in this session. Discover them first with cuba_tools (use detail='full' to see the exact arguments). Goes through the same dispatcher as a direct call, so behaviour is identical.

[alias of cuba_call] Invoke any MemoryIndustry tool by name — including the ones not pre-loaded in this session. Discover them first with cuba_tools (use detail='full' to see the exact arguments). Goes through the same dispatcher as a direct call, so behaviour is identical.