Mirsad
Related Servers
Alternatives to Mirsad
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to share a local-first, versioned memory of decisions, conventions, tasks, conflicts, and handoffs over MCP and REST.3 npmMIT
- FlicenseNot gradedqualityCmaintenanceA local-first, privacy-preserving centralized memory hub for AI agents — MCP-compatible, zero cloud egress.3-
- AlicenseAqualityDmaintenanceLocal-first MCP server for governed AI memory where agents propose memories and humans approve them, with optional cloud sync.61MIT
- AlicenseNot gradedqualityCmaintenanceA permissioned memory tree for you and your AI — served over MCP.26 npm1MIT
- AlicenseAqualityBmaintenanceGives MCP-compatible AI assistants one shared, append-only memory stored as a graph, so facts persist across tools and sessions with their full reasoning chain. Enables finding disagreements between tools, resolving them by recording a winner, and seeing which downstream decisions become stale.9MIT
- AlicenseNot gradedqualityBmaintenanceEnables self-hosted, provenance-aware shared memory with scoped access, attributed observations, correction history, disagreement tracking, and durable idempotent writes for humans and AI agents via REST and MCP.1Apache 2.0
TDQS
Scored across 12 tools
Most tools target clearly distinct operations (remember_fact vs current_fact vs timeline vs record_decision), and the descriptions clarify the temporal/provenance differences. The main soft spot is the read side: recall, why, timeline, and current_fact all retrieve stored knowledge and could be confused by an agent deciding which to call, though 'why' and 'recall' are reasonably differentiated by their descriptions.
All names are snake_case or single lowercase words, so the surface is readable, but the convention is mixed: some are verb_noun (remember_fact, record_decision, add_alias, resolve_conflict), some are bare nouns (version_info, current_fact, timeline, memory_stats), and some are bare verbs (why, recall). There is no single predictable pattern an agent can rely on.
Twelve tools is well within a healthy range and each one maps to a distinct part of the memory/decision lifecycle: writes, reads, conflict handling, aliasing, and diagnostics. Nothing feels like padding, and no obvious operation is duplicated by another tool.
The surface covers a full lifecycle for facts (write, current, history), decisions (record, outcome, why), and conflicts (list, resolve), plus aliases and stats. Minor gaps remain: there is no way to list or inspect entities, no explicit forget/delete or entity-merge operation, and no bulk/query-by-subject listing, though the design intentionally closes rather than deletes facts.