Forgetful
Related Servers
Alternatives to Forgetful
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityBmaintenanceA persistent memory server for AI agents using MCP protocol, enabling semantic storage and retrieval of dialogues, documents, and agent states.-
- AlicenseAqualityDmaintenanceMCP server for persistent, semantic memory across AI sessions; store context, decisions, and learnings and recall them with natural language search.227 npmMIT
- AlicenseNot gradedqualityCmaintenancePersistent semantic memory server for AI assistants via MCP, enabling long-term context retention and semantic search across conversations.12MIT
- FlicenseNot gradedqualityDmaintenanceA local MCP server that provides semantic memory storage and retrieval for coding and AI agents, enabling durable context across chat sessions.65 npm4-
- AlicenseNot gradedqualityCmaintenanceUniversal MCP server providing adaptive semantic memory for AI agents, supporting document ingestion, semantic search, chat persistence, cross-project linking, and cloud storage overflow.3GPL 3.0
- AlicenseAqualityCmaintenanceMCP server providing persistent memory for AI agents, enabling them to read, write, and query memories across sessions.97 npmMIT
TDQS
Scored across 3 tools
The three exposed tools have clear names, but discover already returns enough detail to call tools without how_to_use, and execute's description embeds a large quick-start guide, so documentation and execution boundaries are blurred. The buried catalog also contains several similar retrieval verbs (query_memory, get_memory, get_recent_memories) that rely on descriptions to separate.
Names follow a consistent snake_case verb-first pattern with a forgetful_tool(s) suffix: discover_forgetful_tools, how_to_use_forgetful_tool, execute_forgetful_tool. Minor inconsistency is plural vs singular and the multi-word phrasal verb how_to_use, but the pattern is predictable.
Three exposed tools is thin for a system that claims dozens of operations across seven categories, although the discover+execute pattern intentionally compresses the surface. This pushes a huge catalog and examples into descriptions, making the count feel less like 3 well-chosen tools and more like one mega-dispatcher plus helpers.
The catalog covers CRUD for projects, documents, code artifacts, and entities, plus semantic memory search, linking, relationships, and provenance, so the underlying domain is broadly covered. Gaps include no hard-delete memory (only mark obsolete) and no general filtered list of all memories beyond recent/query, but these are workable.