MemVault
Related Servers
Alternatives to MemVault
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceA self-hosted memory server that gives AI agents a shared, persistent second brain, enabling verbatim storage, hybrid semantic/keyword retrieval, and a synthesized wiki layer through MCP tools.MIT
- FlicenseNot gradedqualityAmaintenanceA local-first MCP memory server that lets AI coding agents store, search, and recall project-specific and cross-project knowledge, so architecture decisions, preferences, error patterns, and coding guidelines persist across sessions. It also exposes optional task-queue tools for handing off autonomous work that draws on the same stored context.-
- AlicenseNot gradedqualityDmaintenanceMCP server that enables persistent, hybrid, local memory for LLM agents, with vector + BM25 search, knowledge graph, and policy-driven retention, providing token-budgeted context injection for AI assistants.MIT

Kagura Memory Cloudofficial
AlicenseNot gradedqualityAmaintenanceProvides AI agents and teams with self-hosted adaptive memory, combining hybrid search and a self-improving neural memory graph to enable precise recall and serendipitous discovery across MCP-compatible clients.13Apache 2.0- AlicenseNot gradedqualityBmaintenanceProvides a self-hosted shared memory service that lets AI agents capture and recall durable facts, decisions, and context across multiple tools and MCP-capable clients.3MIT
- AlicenseNot gradedqualityAmaintenanceA vendor-independent memory layer MCP server that enables multiple LLMs and AI agents to share and persist personal memories, knowledge, and context across sessions, with support for full-text search and tagging.ISC
TDQS
Scored across 20 tools
Most tools target distinct resource+action pairs, and the descriptions carefully delineate the trickiest pairs (delete_memory vs forget_memory, record_outcome vs infer_outcome, review_memory vs save_memory). A few boundaries remain soft — save_memory vs extract_memories with auto_save, and review_memory's edit action vs a dedicated update — but an agent can reason through them from the text.
The set follows a strong verb_noun convention (confirm_read, add_evidence, delete_memory, save_memory, search_memory, get_compliance_report) with a consistent run_* prefix for batch pipeline operations. The only notable deviation is session_start (noun_verb), which breaks the pattern but is unambiguous.
At 20 tools this sits slightly above the comfortable range, but the domain genuinely spans memory CRUD, decay, dedup, promotion, evidence chains, session injection, and compliance reporting, so nearly every tool earns its place. It could be trimmed (e.g. collapsing the report getters) but is not bloated.
Lifecycle coverage is broad: create, search, review/edit, soft-delete, hard-forget, decay, dedup, promote, import, extract, evidence, plus session and outcome/compliance loops. Minor gaps exist — restore is CLI-only, there is no get_memory-by-id or general list/pagination outside the inbox, and update is only reachable via review_memory's edit action.