Compartment
Related Servers
Alternatives to Compartment
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEngram is an epistemic engine that provides persistent, confidence-ranked memory with contradiction detection and autonomous learning, enabling AI coding agents to recall and reason across projects via MCP.2 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEngram MCP provides persistent, cross-session memory for AI agents by automatically encoding errors, decisions, and discoveries during development sessions. It enables local, intelligent recall and automated context management to help AI learn from experience and avoid recurring mistakes.6 npmBusiness Source 1.1
- AlicenseAqualityBmaintenanceEngram is a local-first memory server that lets AI agents remember things across sessions with zero cloud dependencies.649 npm8MIT
- AlicenseNot gradedqualityBmaintenanceZero-knowledge, self-hostable MCP server providing encrypted durable memory for AI agents, with tools to save, recall, search, list, and delete memories.58MIT
- AlicenseNot gradedqualityAmaintenancePersistent cognitive memory for AI agents. Sub-millisecond recall, fully offline, encrypted. 8 tools: recall, recall_structured, store, store_code, store_decision, search, insights, consolidate.100 PyPI77MIT
- AlicenseAqualityAmaintenanceEmbedded memory and retrieval engine for AI agents, providing local-first memory with MCP support for multi-agent access control.322 PyPI2MIT
TDQS
Scored across 14 tools
Most tools are clearly distinct (status, selftest, lock, unlock, get, store, search, recent, namespaces, link, relations, unlink), but memory_store and memory_store_many overlap in purpose (single vs. batch), and memory_forget vs. memory_unlink could be confused by name alone (deleting a memory vs. removing a relation).
The memory_* prefix is consistent and most tools follow verb_noun (memory_get, memory_store, memory_search, memory_forget, memory_unlock, memory_link, memory_unlink). Minor deviations: memory_status, memory_selftest, memory_recent, memory_list_namespaces are noun/adjective-first rather than verb-first, but the pattern is still readable.
14 tools is well within the ideal range for a memory vault server. Each tool covers a distinct operation: lifecycle (store/get/forget), search/recent, graph (link/relations/unlink), vault management (lock/unlock/status/selftest), and namespaces. No tool feels redundant or extraneous.
The surface covers the full memory lifecycle: store (single and batch), retrieve by id, search, list recent, forget with shred, plus graph relations (create/query/delete), namespace management, and vault lock/unlock/status/selftest. The only minor gap is no explicit update tool, but supersedes in memory_store covers corrections, so no dead ends.