Mnemexa MCPofficial
A
licenseA
qualityD
maintenanceProvides persistent, self-optimizing memory for AI agents, enabling them to remember preferences and context across sessions and share knowledge across multiple agents.
4
11 npm
ISC
hubd
by bzdOS
Related Servers
Alternatives to hubd
- AlicenseAqualityDmaintenanceGives Claude Code, Claude Desktop, Cursor, VS Code Copilot, and other MCP-compatible tools persistent memory.1853 npm1MIT
- AlicenseAqualityAmaintenanceHosted memory for AI agents that learns from outcomes, with shared rooms. One key across Claude, Cursor & ChatGPT.6111,285 npm25MIT
Related Servers
- AlicenseNot gradedqualityDmaintenanceA file-backed MCP server for hierarchical project management that enables AI assistants to create, claim, and complete tasks within a project→epic→feature→task structure, with dependency management and Markdown-based storage.MIT
- AlicenseAqualityAmaintenanceRepository-native protocol and MCP server for coordinating work items, documentation, changelogs, and project memory between humans and AI agents, using Markdown files in a Git repository as the canonical data source.303MIT
- FlicenseNot gradedqualityAmaintenanceA local-first MCP server and CLI that gives coding agents structured project memory, task contracts, context packs, backlog workflows, and verification evidence, storing data in reviewable Markdown/YAML with a fast SQLite index.4-
- AlicenseAqualityBmaintenanceA Jira-lite MCP server that enables planning-first workflows for AI-assisted development. It manages tickets as markdown files with YAML frontmatter, guiding agents through epics, stories, tasks, and architecture decision records.17432 PyPIMIT
- FlicenseNot gradedqualityCmaintenanceMCP server for managing a project backlog as Markdown files in Git, enabling AI agents to read, create, and update tasks programmatically.2-
- AlicenseBqualityCmaintenanceTask planning and tracking for AI agents with project-based organization and Obsidian-compatible markdown storage.138 npmMIT
TDQS
B3.4/5.0
Scored across 39 tools
Disambiguation2/5
Many tools have overlapping purposes: hub_status/hub_brief/hub_inbox/hub_whatsnew/hub_agenda/hub_kanban/hub_recall/hub_search all serve orientations/readback with subtle distinctions that require careful reading. Descriptions are long and self-aware about the distinctions, but the sheer number of subtly different 'what's going on' tools guarantees misselection.
Naming Consistency4/5
Consistent snake_case throughout with predictable verb_noun patterns (hub_task_add, hub_queue_send, hub_resource_get, hub_claim_check). Minor deviations like hub_next, hub_recall, hub_sync are still readable and domain-appropriate.
Tool Count2/5
39 tools is heavy and feels like a full operating system rather than a well-scoped server. Many tools exist only to disambiguate between other tools (hub_agenda vs hub_brief vs hub_inbox), suggesting the surface grew organically rather than being designed as a set.
Completeness4/5
Covers an unusually full lifecycle: project cards, resources, tasks, queues, presence, claims, usage, rules, audit, lint, journal. Minor gaps exist around journal query/retrieval beyond hub_search and no explicit deletion tools, but the domain surface is remarkably broad.
Maintenance
ActivityNo data
ResponsivenessNo issues