Genesys

Get graph statistics: node counts by status, edge counts by type, orphan count.

memory_stats

Pin a memory to core status, preventing it from being forgotten.

pin_memory

Recall memories using hybrid search (vector + keyword + graph spreading activation). Call this when the user references stored context or past conversations ('do you remember', 'what did I say about'), or asks a question their stored history, preferences, or past decisions would clearly improve. Also call before memory_store to find related memories to link. Results are ranked by decay_score + spreading_boost; each hit carries `activation` (same value as decay_score — a retention/recency weight, not a deletion countdown). Set verbosity="concise" to omit causal-chain enrichment for a much smaller payload. This tool is read-only: it does not modify memories or access history.

memory_recall

Remove a member from a space (owner). Takes effect on their next request.

space_member_remove

Retire the memories that cite a source that was removed. mode=amend (default): a memory whose only ref is this one is amended to a '[Retired] ...' note tagged `retired` (history is kept); a memory with other refs is amended with this ref removed. mode=delete: sole-ref memories are deleted and the ref is removed from the others. Needs writer or owner when `space` is named; without `space` it acts on your personal memory (services must name a space). Returns {retired, updated, deleted}.

memory_retire_by_ref

Filtered vector search across the user's memory graph by status, category, date, or entity. Use when the user asks to find specific memories ('what do you know about my work?', 'what have I told you about X?'), or when you need memories matching specific criteria rather than semantic similarity. Prefer memory_recall for general context; use this for targeted lookups. With an EMPTY query, enumerates memories by most-recent activity instead of similarity — combine with filters {"since": iso} or {"active_since": iso} as a "what's new since I last looked" change cursor for shared graphs.

memory_search

Send feedback about Papez straight to its maker. Use this when a Papez tool errored, returned something confusing, or when the user asks to report a bug, request a feature, or say what is working. `kind` is one of bug, confusion, idea, praise, other. `context` is optional: what you were trying to do, which tool, which client. Nothing about the user's memories is sent.

send_feedback

Configure which categories are auto-promoted, require approval, or are excluded from core memory.

set_core_preferences

Store up to GENESYS_BATCH_MAX_ITEMS (default 100) memories in one call, all into one space (or your personal memory when `space` is omitted; services must name a space). Every item is validated first; if any item is invalid nothing is stored and the error `batch_invalid` lists each problem with its index. Items are then stored in order; an item's `related` entry may be {"ref_index": i, "type": t} to link to earlier item i. Returns one result per item: {index, node_id, status: stored|exists|unchanged|amended, superseded?}. Retry safety: when every item carries an `external_id` the batch is idempotent, so it is safe to resend the whole batch after a timeout (unchanged items come back with the same node ids). Without external_id a resend creates duplicates.

memory_store_batch

Store a new memory in the user's persistent causal memory graph — a user-owned, inspectable, portable store of nodes linked by causal edges. Call this when the user shows intent to remember: they share something they want kept for later, ask you to remember, update, or forget information, or confirm a durable fact or decision. Do not store personal facts on your own initiative or retain details the user has not indicated they want kept. Trigger phrases: 'remember this', 'don't forget', 'update your memory', 'please forget', 'I no longer...', 'actually it's...', or any explicit request to retain or correct a fact. IMPORTANT: Before storing, call memory_recall first to find existing related memories, then link them. Prefer `related` = [{"id": "<uuid>", "type": "<edge type>"}] to express the TRUE relationship — valid types: caused_by, supports, contradicts, supersedes, derived_from, related_to, temporal_sequence. Use `related_to` (list of ids) only for plain causal links (stored as caused_by). Without links the memory becomes an orphan with no causal connections. Optional `category` tags the memory (e.g. "preference", "decision", "project"). The response may include `possible_conflicts` — surface those to the user rather than silently keeping both versions.

memory_store

Traverse the memory graph from a starting node. Returns connected nodes within depth, plus the connecting `edges` (source, target, type, weight, provenance) of the induced subgraph where the storage backend supports it. Filter with edge_types (e.g. ["caused_by"]) to follow only causal paths.

memory_traverse

Unarchive a space (owner).

space_unarchive

Unpin a memory and re-evaluate its core eligibility.

unpin_memory

Change a space's name, description or policies (owner). The slug can't be changed.

space_update