Delx Memory
Related Servers
Alternatives to Delx Memory
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables concurrent MCP clients to share a persistent SQLite-backed key-value memory store with semantic search, write attribution, and audit history.MIT
- AlicenseNot gradedqualityBmaintenanceA local-first MCP memory server providing persistent, searchable memory for AI agents, powered by SQLite.1 npm1Apache 2.0
- AlicenseNot gradedqualityBmaintenanceLocal-first MCP memory server providing persistent, versioned, queryable memory for AI agents using JSON categories and SQLite FTS5, with optional fleet sync.2Apache 2.0
- AlicenseCqualityAmaintenanceLocal-first, governable long-term memory for AI agents. Provides SQLite-backed storage, cross-session recall, and traceable memory corrections through a standard MCP interface.4055 PyPI1MIT
- AlicenseNot gradedqualityFmaintenanceLocal-first, auditable memory for AI agents. Provides durable context for MCP hosts with SQLite storage, CLI, and MCP tools for memory management.2Apache 2.0
- AlicenseCqualityAmaintenanceLocal-first memory for MCP clients. It provides shared durable memory without requiring hosted accounts, vector databases, or API keys, and works with Codex, Claude Code, Cursor, and other MCP clients.2564 npm3MIT
TDQS
Scored across 15 tools
Core data operations are distinct, but the six introspection/status tools (agent_manifest, connection_status, data_inventory, capabilities, stats, handoff) overlap in purpose—several report store size or describe privacy modes, and handoff explicitly subsumes stats+list+get. Detailed descriptions mitigate confusion but don't fully eliminate it.
All tools share a consistent memory_ snake_case prefix, but the set mixes noun-style names (memory_stats, memory_handoff, memory_capabilities) with verb-style names (memory_get, memory_set, memory_forget). The prefix keeps it readable, but there is no consistent verb_noun pattern.
15 tools is within the acceptable range for a memory server, and batch/search/export variants earn their place. It feels slightly heavy because several status/introspection tools could be consolidated (e.g., stats vs connection_status vs handoff).
Full lifecycle coverage is present: set/upsert, single and batch get, list/search, forget/forget_by_tag, export, and session-start handoff. Batch operations, namespace awareness, and privacy modes round out the surface with no obvious dead ends.