Skip to main content
Glama
LeandroPG19

Cuba-Memorys

by LeandroPG19
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

Related Servers

Alternatives to Cuba-Memorys

No user-submitted related servers found.

    Related Servers

    • ogham-mcp

      ogham-mcp
      A
      license
      Not graded
      quality
      A
      maintenance
      Persistent shared memory for AI agents. Hybrid search (pgvector + tsvector), knowledge graph, cognitive scoring, and 16-language temporal extraction. 97.2% Recall@10 on LongMemEval with one PostgreSQL query. Works across Claude Code, Cursor, Codex, OpenClaw, and any MCP client.
      61 PyPI
      115
      MIT

    • memory-mcp-ce

      symbiomind
      A
      license
      Not graded
      quality
      B
      maintenance
      Persistent semantic memory for AI agents using PostgreSQL and vector embeddings, enabling cross-session continuity and semantic search.
      AGPL 3.0

    • remembrallmcp

      roboticforce
      A
      license
      Not graded
      quality
      A
      maintenance
      Persistent knowledge memory layer for AI agents. Hybrid semantic + full-text search with pgvector, code dependency graph with blast-radius impact analysis, and incremental indexing for 7 languages. In-process ONNX embeddings, no external API required.
      31 npm
      35
      MIT

    • Second Brain

      guybr3000
      A
      license
      Not graded
      quality
      D
      maintenance
      Persistent, semantically-searchable memory for AI agents using local PostgreSQL, pgvector, and Ollama embeddings, exposed via MCP with hybrid retrieval, knowledge graph, and auto-recall hook.
      0
      MIT

    • Mnemo Cortex

      GuyMannDude
      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.
      157
      MIT
    Deploy Server
    Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

    TDQS

    B3.2/5.0

    Scored across 62 tools

    Disambiguation4/5

    Descriptions carefully partition the memory space into semantic (alma), episodic (cronica), procedural (receta), working (pizarra), prospective (centinela), error (alarma/remedio/expediente) and analytics (vigia/reflexion) roles, so most tools are distinguishable. However, every tool is duplicated under both cuba_ and memory_ prefixes, and search/context tools (faro vs contexto vs cronica) have fuzzy boundaries, which can cause occasional misselection.

    Naming Consistency4/5

    All names use consistent snake_case with clear prefix families (cuba_*, memory_*), and the domain nouns are stable. The only inconsistency is that each tool appears twice under two different prefixes, which is systematic but creates duplicate naming for identical functionality.

    Tool Count2/5

    62 tools is far too many for a clean surface; even discounting the alias duplicates, roughly 31 distinct tools exceeds the 25-tool heavy threshold. The cuba_tools on-demand loading profile mitigates this, but the exposed set is still bloated for an agent to navigate.

    Completeness4/5

    The surface covers an unusually wide lifecycle: entity CRUD, observations, errors, decisions, sessions, artifacts, sync, audit, ingestion, maintenance, calibration, GDPR erasure, and compaction survival. Minor gaps remain, such as no obviously dedicated read/list tool for every resource type, but core workflows are well supported.

    Maintenance

    ActivityActive
    ResponsivenessUnresponsive

    Resources