nanomem
Related Servers
Alternatives to nanomem
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceLocal memory for AI agents in one SQLite file on your own machine. Facts carry a validity window and a confidence score, so an outdated one is superseded and downweighted rather than deleted, and retrieval fuses BM25, vector similarity and a knowledge graph.2AGPL 3.0
- AlicenseAqualityAmaintenanceEmbedded, local-first agent memory: facts extracted into a per-namespace SQLite file (vec0 + FTS5) with hybrid retrieval and point-in-time (time-travel) queries. ADD-only history over stdio — no server process, no cloud dependency.746 PyPI42Apache 2.0
- AlicenseNot gradedqualityAmaintenanceProvides persistent, searchable memory with hybrid keyword and semantic search, storing memories in a single SQLite file without external dependencies.MIT
- AlicenseNot gradedqualityAmaintenanceGives AI agents governed, provenance-tagged memory where facts are invalidated rather than deleted and every recall result carries validity dates, confidence, and replacement links. Stores memory in a local SQLite file with tools for remembering, recalling, invalidating, and pinning facts, plus policy enforcement and an audit trail.230 npm3Apache 2.0
- AlicenseNot gradedqualityCmaintenanceLocal-first semantic memory layer for MCP agents. Recall, remember, forget, stats over stdio. ChromaDB plus sentence-transformers, all on-machine.57 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceProvides persistent long-term memory for LLMs via local SQLite storage and semantic search, enabling recall across sessions without external APIs.8 npm4MIT
TDQS
Scored across 7 tools
Each tool has a distinct primary purpose (write, search, temporal history, as-of query, stats, change log, volatility stats), but the temporal tools (history, as_of, changes) overlap in scope and could be confused without careful reading of descriptions. The descriptions do clarify boundaries, so misselection is unlikely but possible.
All tools share the 'nanomem_' prefix, but the second part is inconsistent: some are verbs (add, search), some are nouns (history, stats, changes, volatility), and one is a prepositional phrase (as_of). The pattern is not uniform, though it remains readable and predictable in the prefix.
Seven tools is a well-scoped set for a memory server. Each tool covers a distinct aspect of storing, retrieving, analyzing, and inspecting memory, with no unnecessary bloat or obvious missing core functionality.
The surface covers the core lifecycle: add, search, and temporal/analytical views. There is no explicit update or delete tool, but the memory model appears to handle changes via superseding writes, and search handles superseded values. Minor gap: no direct tool to remove a fact entirely, but this may be intentional.