aureliocpr-ctrl
UserEngram (formerly HippoAgent) — persistent memory layer for Claude Code and any LLM agent. Hippocampal-cortical inspired consolidation: episodes → skills → deterministic macros, all inspectable. MCP server, multi-provider, subscription-first Hippo Dreams pipeline.
Categories
Indexed Skills (3)
hippoagent-entity-recall
When the user asks "cosa ricordi di X?", "dammi tutto su Y", "chi è Z?", "cosa abbiamo detto di W?", "ricostruisci ciò che sai di [Capitalized name or known alias]", call hippo_entity_get(name) BEFORE answering. Triggers also on "what do you know about X", "tell me about Y", "facts about Z", "history of W". The tool returns entity+aliases+facts from a persistent SQLite KG (P2.a entity-centric KG, schema v4, Unicode-safe). Lookup is case-insensitive Unicode (Müller/MÜLLER/müller same match) and resolves aliases ("S. Tonegawa" → canonical "Tonegawa"), returning the list of fact_id linked to the entity. If entity is None, declare honestly "non ho memoria di X" — do NOT confabulate from training data. If entity exists but facts == [], declare "ho il nodo entity ma nessun fatto collegato" and suggest hippo_facts_search or hippo_recall. Zero LLM cost, sub-50ms on ~500 entity corpus, free in hosted mode. Backend SQLite WAL + UNIQUE INDEX on name_norm Python-normalized (NFC + str.lower, NOT SQLite ASCII-only LOWER).
hippoagent-memory
ANY mention of "memoria/memory/ricordi/ricordo/ricorda/ricordare/saved/stored" by the user MUST go to HippoAgent (hippo_* tools), NEVER to local file-system memory files (CLAUDE.md / MEMORY.md / .claude/projects/.../memory/*). Auto-fire flow - call hippo_health first to confirm reachable, then route the user's intent to the right tool. "salva/save X" → hippo_remember. "qual è il mio X / what's my X / cosa ricordi di X" → hippo_facts_search (instant keyword) then fall back to hippo_facts_recall (semantic). "cosa vedi nella memoria / what's in memory / dammi tutto" → hippo_facts_list + hippo_episode_list + hippo_stats. "abbiamo già fatto X / have we done X" → hippo_search (keyword on episodes) then hippo_recall (semantic). "dimentica X" → hippo_forget / hippo_fact_forget. AVOID hippo_run_task and hippo_consolidate inside Claude Code — they make EXTRA API calls to the configured Anthropic key (separate billing). The other 37 tools are FREE - they only read/write local SQLite, no API. Disable globally with env HI
hippoagent-validate-claim
Before asserting any verifiable factual claim (year/number/attribution/citation/date), call `hippo_validate_claim(claim)` to check it against persistent memory. Triggers when about to say things like "X was born in YEAR", "Y won the Nobel in YEAR", "Z released VERSION in MONTH", "W said EXACT_QUOTE", "this library/paper/repo is from ORG", or any other claim containing a Capitalized name + a specific year/number/version/org. The tool returns verdict ∈ {supported, contradicted, unknown} + an advice string in Italian (e.g. "in memoria 1987 (fact f_id), NON 2014 — controlla prima di affermare"). If verdict=contradicted, STOP and re-read the evidence_facts; do NOT assert the claim verbatim. If verdict=unknown, hedge ("non ricordo con certezza", "credo ma verifica"). If verdict=supported, proceed. Zero LLM cost (deterministic, sub-100ms). Anti-confabulation gate — born from live confabulations 2026-05-14 (Tonegawa Nobel 1987→2014, Anthropic Skills Oct 2025→Oct 2026, LightRAG HKUDS→HKUST).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.