Skip to main content
Glama
n24q02m

Mnemo - Persistent AI Memory

by n24q02m

Related Servers

Alternatives to Mnemo - Persistent AI Memory

Related Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Lightweight persistent memory for AI agents using a single SQLite file with hybrid search (keywords + semantics). Zero to 12MB install, no cloud or server required.
    5
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Persistent semantic memory for AI agents. SQLite-backed, local-first, zero config. Semantic search via Ollama embeddings with keyword fallback. Tools: remember, recall, history, forget, stats.
    17
    37 npm
    1
    MIT
  • -
    license
    Not graded
    quality
    Not graded
    maintenance
    Provides persistent local memory functionality for AI assistants, enabling them to store, retrieve, and search contextual information across conversations with SQLite-based full-text search. All data stays private on your machine while dramatically improving context retention and personalized assistance.
    3
    -
  • A
    license
    Not graded
    quality
    A
    maintenance
    Persistent semantic memory for AI agents — hybrid SQLite + FTS5 with DAG-based summaries, context compaction, and 7 MCP tools. Open source, self-hosted, zero API cost.
    154
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Provides persistent, searchable memory with hybrid keyword and semantic search, storing memories in a single SQLite file without external dependencies.
    MIT

TDQS

A3.7/5.0

Scored across 15 tools

Disambiguation3/5

Most granular memory tools are clearly distinct, but the deprecated 'memory' composite tool overlaps with nearly all of them, and 'config' status overlaps with 'memory_stats' by also reporting database statistics. The detailed action guides help, but the presence of overlapping dispatchers creates avoidable ambiguity.

Naming Consistency3/5

The core tools mostly follow a verb_noun pattern (add_memory, search_memory, update_memory), but 'archived_memories', 'memory_stats', 'config', 'memory', and 'config__open_relay' break the pattern. The naming is readable and all snake_case, but the mix of bare nouns, noun_noun, and a double-underscore tool prevents it from being highly consistent.

Tool Count4/5

At 15 tools, the server is at the upper bound of a well-scoped set, and the deprecated 'memory' tool plus the composite 'config' dispatcher make it feel slightly heavier than necessary. Excluding deprecated/helper tools, the remaining surface is reasonable for a persistent memory system with configuration and sync features.

Completeness4/5

The memory lifecycle is well covered: add, search, list, update, delete, archive listing, restore, import, export, stats, and consolidation are all present. Minor gaps exist, such as no direct get-by-ID tool and no explicit user-facing archive action beyond soft-delete/automatic archiving, but these are workable through existing tools.

Maintenance

ActivityActive
ResponsivenessResponsive