Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ERINYS_DB_PATHNoSQLite database path~/.erinys/memory.db
ERINYS_EMBEDDING_MODELNofastembed modelBAAI/bge-small-en-v1.5

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
erinys_saveC

Save a structured observation to ERINYS memory.

principal: この記憶を書いた主体(例 claude-opus-4-8 / codex)。省略時は env ERINYS_PRINCIPAL → "unknown"。VMG provenance に記録される。

P0-7 (opt-in): allowed_projects / allowed_scopes は書き込み許可の access gate。明示引数 > env(ERINYS_ALLOWED_PROJECTS / ERINYS_ALLOWED_SCOPES)> 無効(None)。どれも設定されなければ従来どおり無条件に保存する。許可外の project/scope への書き込みは POLICY_DENIED で拒否する。

erinys_getA

Get a single observation by ID (full content, untruncated).

erinys_lineageB

VMG Provenance Visibility: 記憶の出自系譜を祖先方向に辿って返す。

各ノードの provenance.parents(無ければ distilled_from)を辿り、 どの記憶からどう派生したかの lineage-complete な鎖を構成する。

erinys_updateA

Update an existing observation. Only provided fields are changed.

erinys_deleteA

Delete an observation and cascade dependent rows via FK rules.

erinys_forgetA

VMG Verified Forgetting: 観測とその distilled 派生物を全 DB substrate から 削除し、不在を membership test で実証する。

forgetting は派生物に伝播する: distilled 子孫を含む closure ごと忘れる (子に親の情報が残るのを防ぐ)。closure を leaf-first で単一Txで削除し、 observations/vec/FTS(トリガ)/edges/collisions(CASCADE) を消す。 erinys_delete と違い、子を持つ親も忘れられる(NO ACTION FK を closure で解消)。 dry_run(既定)では削除せず closure と現在の在席のみ返す。

範囲外(正直な明示): Obsidian 書庫は次回 export の orphan 掃除で遅延除去、 .bak バックアップは復元用に設計上保持するため、この DB 検証の対象外。

erinys_searchC

RRF hybrid search (FTS5 keyword + vector similarity).

P0-7 (opt-in): allowed_projects / allowed_scopes は取得許可の access gate。 明示引数 > env(ERINYS_ALLOWED_PROJECTS / ERINYS_ALLOWED_SCOPES)> 無効 (None)。設定時は、許可外の project/scope の行を結果から除外する(global scope は常に可視)。どれも設定されなければ従来どおり全件返す。

erinys_save_promptC

Save a user prompt to track intent and goals.

erinys_session_startC

Start a new session.

erinys_session_endB

End a session with optional summary.

erinys_session_summaryB

Save comprehensive end-of-session summary (Goal/Discoveries/Accomplished).

erinys_recallC

Recall recent observations for context.

erinys_contextC

Get recent session context for a project.

erinys_exportB

Export observations as markdown payload (Obsidian-compatible [[wikilinks]]).

erinys_backupC

Create a consistent SQLite backup and return backup metadata.

erinys_statsC

Database statistics: observation count, project breakdown, health.

erinys_linkC

Create typed edge between observations.

erinys_traverseC

Traverse graph from a starting observation.

erinys_backfillC

Plan or apply bounded historical records with event-ledger idempotency.

erinys_pruneC

Prune decayed observations below threshold.

erinys_batch_saveA

Bulk-add observations with automatic similarity linking.

erinys_reinforceB

Reinforce an observation by updating access_count and last_accessed.

erinys_conflict_checkC

Detect contradicting observations.

erinys_supersedeC

Supersede an old observation with updated fact.

erinys_timelineC

Query facts valid at a specific point in time.

erinys_collideB

Manually collide two observations to generate insight.

erinys_dreamC

Run Dream Cycle: batch collision of candidate memory pairs.

erinys_distillD

Distill observation to higher abstraction level.

erinys_evalC

Self-evaluate memory quality (LOCOMO-inspired metrics).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/GhostyAI-HA/ERINYS-mem'

If you have feedback or need assistance with the MCP directory API, please join our Discord server