A
licenseA
qualityC
maintenanceMCP server for long-term agent memory, providing persistent memory, searchable knowledge, and evolving identity for AI agents.
5
3
Apache 2.0
Lorekeeper
by Jessinra
Related Servers
Alternatives to Lorekeeper
No user-submitted related servers found.
Related Servers
- AlicenseAqualityCmaintenanceMCP server providing persistent memory for AI agents, enabling them to read, write, and query memories across sessions.94 npmMIT
- AlicenseAqualityBmaintenanceAn MCP server providing long-term memory for AI agents with forgetting curves, consolidation, and graph-based retrieval.1014 npmMIT
- AlicenseNot gradedqualityBmaintenanceMCP server providing persistent AI memory with four-tier retrieval (SQLite FTS5, graph, vector, LLM agent) to give AI assistants structured, long-term memory without RAG.1Apache 2.0
- FlicenseNot gradedqualityBmaintenanceA persistent memory server for AI agents using MCP protocol, enabling semantic storage and retrieval of dialogues, documents, and agent states.-
- AlicenseNot gradedqualityCmaintenancePersistent memory infrastructure for AI agents, enabling cross-session recall and autonomous memory evolution via an MCP server.1MIT
TDQS
A3.9/5.0
Scored across 10 tools
Disambiguation3/5
Most tools target distinct operations, but lore_insert and lore_remember both create memories with only a lightweight-vs-structured distinction, and lore_recommend_links vs lore_get_suggestions both surface link candidates through different pipelines. The descriptions help, but an agent could reasonably choose the wrong tool in these overlapping cases.
Naming Consistency4/5
Tools consistently use the lore_ prefix and mostly follow verb_noun naming like lore_search, lore_insert, lore_update, and lore_review_suggestion. Deviations include bare verbs like lore_remember and lore_reflect, the noun-phrase lore_processed_sessions, and lore_get_suggestions using get_ where other retrieval-like tools do not.
Tool Count5/5
10 tools is well-scoped for a memory store: search, write, feedback, forgetting, link suggestions, and session reflection all have a dedicated tool. No tool feels redundant enough to remove, and the set is not bloated.
Completeness4/5
The surface covers the core memory lifecycle: create, search, rate, soft-delete, plus link suggestion handling and session reflection. Minor gaps include no direct way to update memory content and no undelete, but bulk-fetch by ID and explicitly reversible soft-delete mitigate the impact.
Maintenance
ActivitySlowing
ResponsivenessUnresponsive