th-memory-mcp
Related Servers
Alternatives to th-memory-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityDmaintenanceProvides persistent cross-session memory and full-text search for AI coding assistants, storing project context, decisions, and preferences while enabling searchable access to conversation history via local SQLite.81MIT
- AlicenseAqualityBmaintenanceProvides AI coding assistants with persistent memory storage using a local SQLite database. Enables tools to remember project details, notes, and relationships across sessions to maintain context and reduce repetitive explanations.174MIT
- FlicenseNot gradedqualityAmaintenanceGives AI coding agents a local-first persistent memory they can read and write directly during sessions, storing decisions, preferences, error patterns, and guidelines in per-project and global SQLite stores. Enables semantic and keyword retrieval of relevant context across sessions so agents start work already knowing a codebase's conventions and history.-
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read and write persistent memory directly during sessions, storing decisions, preferences, error patterns, research, and cross-project guidelines in local SQLite databases. Supports semantic search so relevant project and global context can be recalled by meaning, fully offline and without API keys.-
- AlicenseNot gradedqualityNot gradedmaintenanceProvides AI coding agents with persistent, long-term memory through local semantic search and SQLite storage. It enables agents to save and retrieve architectural decisions or project context across different conversation sessions without requiring cloud services.MIT
- -licenseNot gradedqualityNot gradedmaintenanceProvides persistent local memory functionality for AI assistants, enabling them to store, retrieve, and search contextual information across conversations with SQLite-based full-text search. All data stays private on your machine while dramatically improving context retention and personalized assistance.3-
TDQS
Scored across 16 tools
Most tools target clearly distinct resources or lifecycle stages, and descriptions clarify the intended use. However, recall vs get_context both retrieve memories for a task, while remember/update_memory and consolidate/merge_memory require reading descriptions carefully to avoid misselection.
Several tools follow a clear verb_noun pattern (link_memory, merge_memory, update_memory, save_lesson, get_profile, search_history), but core operations use bare verbs (remember, forget, recall, consolidate) and one uses a noun form (memory_stats). The set is readable but uses mixed conventions.
At 16 tools the surface is slightly larger than the typical 3-15 sweet spot, but the memory domain is rich enough to justify most tools. Import/export, graph linking, consolidation, and retrieval each earn a place rather than feeling redundant.
The set covers create, read/search, update, delete, linking, import/export, and consolidation lifecycle operations comprehensively. Minor gaps remain, such as no direct get-memory-by-id or bulk clear operation, but agents can work around these through recall/search and targeted deletes.