memory-mcp
Related Servers
Alternatives to memory-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients such as Claude Code and Claude Desktop to keep long-term memory: store facts with remember, retrieve them with recall, and submit feedback so rankings adapt to which memories actually helped across tasks. It also infers outcomes when feedback is skipped, retiring replaced facts and demoting useless look-alikes while staying within a token budget.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables all local Claude Code sessions, subagents, and other MCP clients to read and write one shared long-term memory over HTTP on localhost, so facts retained by one agent can be recalled by another. It extracts atomic facts, entities, and observations into an embedded local Postgres with ONNX embeddings and reranking, requiring no API key.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to persist and retrieve structured memory across sessions and models via MCP tools for cataloging, searching, and saving facts, with automatic supersession and scope filtering.MIT
- AlicenseNot gradedqualityDmaintenanceGives AI persistent personal memory with hybrid search, temporal decay, and knowledge graph. Works with Claude and any MCP client.7 npm10MIT

PseudoLife-MCPofficial
AlicenseAqualityBmaintenanceEnables persistent long-term memory for Claude Code across sessions, with tools for storing, searching, and managing facts, knowledge graphs, and procedural lessons.381,774 PyPI6Apache 2.0- AlicenseNot gradedqualityBmaintenanceEnables MCP clients such as Claude Desktop, Cursor and Claude Code to add, search, answer from, and audit an agent's long-term memory stored in a single local SQLite file. Memories are backed by verifiable quotes, ranked by task outcomes, access-controlled, and usable fully offline.Apache 2.0
TDQS
Scored across 5 tools
Each tool has a clearly distinct role: remember writes, recall does query-based retrieval, list_memories enumerates all facts, list_entities enumerates people/places, and forget deletes. The recall vs. list_memories boundary (search vs. full listing) is explicitly spelled out in the descriptions, leaving no real overlap.
All names are imperative lowercase verbs, which gives a readable, predictable style. However, the pattern is not strictly verb_noun: remember/recall/forget omit the object while list_memories/list_entities include one, a minor inconsistency but not confusing.
Five tools is well-scoped for a personal memory store: one write, three read shapes, and one delete. Every tool earns its place with no redundant or speculative operations.
The lifecycle is essentially covered: remember implicitly handles updates with history, and forget handles deletion. Minor gaps exist, such as bulk deletion of all of a user's data (beyond one memory at a time) and no way to remove or merge entities explicitly.