A
licenseNot graded
qualityA
maintenanceEnables AI agents to persist and recall episodic memories across sessions, consolidating experiences into reusable rules and lessons to reduce repeated mistakes and improve task performance.
1
MIT
memshelf-mcp
by ignatenkofi
Related Servers
Alternatives to memshelf-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceProvides persistent, searchable memory for AI agents, enabling them to retain, recall, and reflect on information across conversations.1916 PyPI1MIT
- AlicenseNot gradedqualityFmaintenanceEnables persistent, portable memory for AI agents across sessions, devices, and providers with token-efficient 5-level lazy loading and automatic session capture.8 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to automatically capture durable knowledge and retrieve only relevant, token-bounded context from a secure local-first long-term memory, with support for progressive disclosure, snapshots, health diagnostics, and background tasks.Apache 2.0
Memra MCP Serverofficial
AlicenseNot gradedqualityCmaintenanceProvides persistent memory for AI agents with hybrid semantic and lexical recall, including write-time contradiction detection and token-budgeted retrieval.MIT- AlicenseNot gradedqualityAmaintenanceEnables AI agents to persistently store and retrieve memories across sessions, workspaces, and context limits so prior decisions, patterns, and knowledge remain available in future conversations.24 npmMIT
TDQS
A4/5.0
Scored across 14 tools
Disambiguation5/5
Each tool targets a clearly distinct operation within the memory-shelf lifecycle: reading (index, recall, search), writing (shelve, import), diagnostics (lint_digest, doctor), maintenance (rebuild, rollup, purge, resolve), and insights (stats, advise). Potential overlaps like lint_digest vs. doctor or rebuild vs. resolve are explicitly differentiated by scope and timing in the descriptions.
Naming Consistency5/5
All 14 tools consistently use the memshelf_ prefix and lower snake_case. The action/artifact naming is predictable across the set, even when a few names are noun-like (stats, doctor) rather than purely verb_noun.
Tool Count5/5
With 14 tools, the server sits in the well-scoped 3-15 range and covers a full lifecycle without obvious filler. Each tool maps to a distinct phase or concern of managing a memory shelf.
Completeness4/5
The surface covers initialization, creation, import, retrieval, search, metrics, validation, rebuild, rollup, retention purge, conflict resolution, and diagnosis. Minor gaps remain, such as no direct per-episode edit, manual delete, or export operation, though retention and rollup mitigate deletion and archival needs.
Maintenance
ActivityMaintained
ResponsivenessWithin a week