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.

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. v0.9: optional MMR diversification + OOD abstention + exact tiktoken-based 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).

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.

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.

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.

Record and query architecture/design decisions.

Knowledge graph analytics: summary (counts + token estimate), health (staleness, entropy, DB size), drift (chi-squared on errors), communities (Leiden), bridges (betweenness centrality). v0.9: 'structural' returns harmonic + closeness + k-core ranking for backbone identification.

Memory maintenance: decay (stratified exponential by type), prune (remove low-importance), merge (deduplicate), summarize (compress observations), pagerank (personalized importance), find_duplicates, export, stats, reembed (re-encode with current model).

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

Analyze knowledge graph for structural gaps: isolated entities, underconnected hubs, type silos, observation gaps (missing decisions/lessons), and statistical density anomalies. Read-only introspection.

Abductive inference: given an observed effect, find plausible causes by traversing causal relations backwards. Returns hypotheses ranked by plausibility (path_strength × importance). Read-only.

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

Prospective memory: set triggers that fire when entities are accessed, sessions start, or errors 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. v0.9: action 'trust' returns per-source credibility (Beta posterior updated by resolve outcomes; Yin-Han-Yu IEEE TKDE 2008).

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 rows with NULL project_id remain visible from every scope.

Compaction-survival protocol (v0.8). Before the agent runs /compact, call action='snapshot' to persist a dense markdown summary of the active session (recent observations, decisions, unresolved errors, pending embeddings, goals). After compaction, call action='restore' to retrieve the latest snapshot for the active session and re-inject it into context.

Git-friendly export/import of the knowledge graph (v0.8). action='export' writes one JSON file per entity (with embedded observations) plus episodes/decisions/errors/relations under CUBA_SYNC_DIR (default ./.cuba-memorys/). 'import' merges files back via INSERT...ON CONFLICT DO NOTHING (idempotent). 'diff' compares disk vs DB. 'status' lists not-yet-imported manifests. Embeddings are omitted by default (set with_embeddings=true to include the binary blob).

Tamper-evident audit log (v0.9, CFR-21 Part 11 inspired). Append-only with SHA-256 hash chain — every row's current_hash commits to the previous row's, the action and the canonical payload. UPDATE/DELETE blocked at the PostgreSQL trigger level (only cuba_admin role can bypass). Use 'verify' to walk the chain and detect tampering, 'tail' to read recent events, 'append' to add a new event.

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 (v0.8). When cosine similarity sits in the ambiguous band (0.6-0.8), heuristic detectors miss vocabulary-different conflicts (e.g. 'Postgres' vs 'MongoDB'). cuba_juez escalates a pair to a real LLM via subprocess (Claude Code CLI, $0 if you have a subscription) or — when feature 'anthropic-api' is built in — the Anthropic API directly. Verdicts are persisted in brain_judgments (UNIQUE per pair = permanent cache).

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 cuba-memorys tools and load their schemas ON DEMAND. The server exposes 29 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 cuba-memorys 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.