(S)AGE
Related Servers
Alternatives to (S)AGE
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to safely write to and read from persistent memory by validating every write through three independent consensus nodes, storing memories only on 2/3 agreement and quarantining poisoning attempts.Apache 2.0
- AlicenseNot gradedqualityAmaintenanceProvides AI agents a shared long-term memory layer with evidence-backed, auditable claims, enabling persistent, explainable, and conflict-aware recall across sessions.1,551 PyPI6MIT

Mnemexa MCPofficial
AlicenseAqualityDmaintenanceProvides persistent, self-optimizing memory for AI agents, enabling them to remember preferences and context across sessions and share knowledge across multiple agents.412 npmISC- FlicenseNot gradedqualityBmaintenanceA long-term memory system built for AI Agents. Agent wakes up already knowing who he is, not querying "who am I?" every session. Every turn calling back accurate memory context. Achieving accurate memory hits while also preventing memory from expanding at scale. No compression, no forgetting.36-
- FlicenseNot gradedqualityDmaintenanceGives AI agents persistent memory, handoffs, and shared context across sessions, enabling seamless continuity and multi-agent collaboration.58 npm67-
- AlicenseNot gradedqualityAmaintenanceOpen-source persistent memory infrastructure for AI agents.536 npm328Apache 2.0
TDQS
Scored across 35 tools
The tool set is large but largely distinct: memory lifecycle, messaging, governance, tasks, and federation each have their own tools. The messaging cluster (sage_inbox, sage_messages_receive, sage_message_history, sage_message_replies, sage_message_status) has the most overlap, but descriptions explicitly differentiate their roles (claiming vs unified update surface vs browsing vs sender-side paging). An agent could still confuse inbox and receive at first glance, so it is not perfect.
All tools share a consistent sage_ prefix and snake_case style, making them recognizable. However, the internal pattern is mixed: some are verb-first (sage_get_links, sage_find_agent), some noun-first (sage_scope_get, sage_message_send), and some single words (sage_remember, sage_inbox, sage_recall). This is readable but not a uniform convention.
With 35 tools, this server is heavy for a single MCP surface. While the domain (persistent memory, messaging, governance, federation) is broad, the count exceeds the typical well-scoped range and forces agents to navigate many overlapping-sounding entry points.
The surface covers registration, identity, memory CRUD (with replacement via sage_remember), recall, linking, corroboration, tasks, messaging, governance, scopes, and federation discovery. Minor gaps exist—no explicit memory update tool (handled by replacement) and no message retraction/delete—but these appear intentional or workable.