Mem0 MCP Serverofficial
A
licenseA
qualityF
maintenanceAn MCP server that integrates with mem0.ai to help users store, retrieve, and search coding preferences for more consistent programming practices.
9
659
Apache 2.0
dakera-mcp
Officialby Dakera-AI
Related Servers
Alternatives to dakera-mcp
- FlicenseNot gradedqualityDmaintenanceEnables Claude to store, search, and retrieve persistent memories using Zep Cloud's thread-based memory system for maintaining context across conversations.-
- AlicenseNot gradedqualityAmaintenanceA graph-based MCP server that provides AI coding agents with persistent memory to store patterns, track complex relationships, and retrieve knowledge across sessions. It leverages graph structures to handle temporal queries and relational paths that traditional vector stores often miss.244MIT
Related Servers
Recallofficial
AlicenseNot gradedqualityCmaintenanceOpen-source MCP memory server for AI agents — persistent, searchable, tiered memory across sessions. Works over stdio (Cursor, Claude Desktop) or HTTP+SSE. MIT licensed.7MIT- AlicenseNot gradedqualityCmaintenanceA self-hostable MCP server that provides permanent memory for AI agents using Postgres + pgvector for semantic search and Markdown file sync.MIT
- AlicenseAqualityAmaintenanceLocal MCP server giving AI coding agents (Claude Code, Cursor, VS Code/JetBrains Copilot) a shared, persistent memory of your projects and every bug/issue faced during development. Stateless, plain-file storage (AGENTS.md + issues.jsonl) — no database.16207 npm1MIT
- AlicenseNot gradedqualityBmaintenanceSelf-hosted MCP server giving AI agents persistent memory — Markdown source of truth, hybrid BM25+embedding search, typed graph relations.2MIT
- AlicenseNot gradedqualityCmaintenanceA local-first long-term memory system for AI coding agents, exposed as an MCP server.49 npmMIT
- FlicenseNot gradedqualityBmaintenancePersistent semantic memory MCP server for AI agents with hybrid search, LLM scoring, and decay engine, fully local.2-
TDQS
A3.7/5.0
Scored across 14 tools
Disambiguation2/5
Multiple tools for semantic retrieval (dakera_search, dakera_recall) and search variants (fulltext, hybrid, batch_recall) have heavily overlapping purposes, making it hard to decide which to call. The distinction between search and recall is subtle and likely to cause misselection.
Naming Consistency2/5
All tools share the dakera_ prefix, but the verb/noun structure is inconsistent: some use bare verbs (search, store, recall, forget, extract), some compound verbs (batch_recall, session_start), and some noun phrases (knowledge_graph, fulltext_search). 'fulltext_search' also lacks an underscore convention.
Tool Count4/5
14 tools is within the typical 3–15 range and reasonable for a memory server covering storage, retrieval, sessions, extraction, and tool discovery, though slightly on the higher side.
Completeness4/5
The surface covers core memory operations (store, forget, multiple retrieval modes), sessions, knowledge graph construction, extraction, and tool metadata. It lacks an explicit update or get-by-id operation, but the provided features are largely sufficient for the domain.
Maintenance
ActivityMaintained
ResponsivenessUnresponsive