A
licenseB
qualityD
maintenanceMCP server providing context usage estimation, conversation compaction, and durable semantic memory via local embeddings and SQLite.
17
12 npm
3
MIT
Library of Context
by hwillGIT
Related Servers
Alternatives to Library of Context
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server that provides persistent long-term memory for AI agents via local SQLite storage with low token overhead, enabling memory storage, retrieval, and management across sessions.1MIT
- AlicenseNot gradedqualityAmaintenanceAn MCP server that extends AI agents' context window by providing tools to store, retrieve, and search memories, allowing agents to maintain history and context across long interactions.MIT
- AlicenseNot gradedqualityAmaintenanceMCP server providing persistent AI memory with four-tier retrieval (SQLite FTS5, graph, vector, LLM agent) to give AI assistants structured, long-term memory without RAG.1Apache 2.0
- FlicenseNot gradedqualityAmaintenanceA local MCP server using SQLite to unify context and memory across multiple AI agents, enabling persistent decisions and preferences without re-explanation.-
- FlicenseNot gradedqualityDmaintenanceA local MCP server that provides semantic memory storage and retrieval for coding and AI agents, enabling durable context across chat sessions.40 npm4-
TDQS
B3.3/5.0
Scored across 16 tools
Disambiguation3/5
The tools split into understandable areas (shelving, reading desk, context governor), but several pairs overlap in behavior: desk_refresh/desk_watch, context_prepare/prompt_build, and message_record/context_commit can all be confused without close reading. Descriptions mostly disambiguate them, but the boundaries are not immediately obvious from names alone.
Naming Consistency4/5
The library_ prefix plus domain area gives a predictable feel, especially for the desk_* and context_* families. A few standalone verbs/nouns like library_shelve, library_consult, and library_stats break the noun_verb pattern, but these are minor deviations.
Tool Count3/5
At 16 tools, the surface is slightly heavy and crosses the usual well-scoped range, though the three subsystems (library, desk, and context governor) explain most entries. A couple of prompt/recording tools could likely be consolidated without losing core functionality.
Completeness4/5
The context lifecycle is well covered: shelve/consult, desk refresh/get/watch/stop, and prepare/commit/protect/release/status/flush form coherent workflows. Missing direct book-level listing/removal or get-by-ID is a minor gap, but it does not create a dead end for the main use cases.
Maintenance
ActivitySlowing
ResponsivenessNo issues