Skip to main content
Glama
carrasquelalex1

hipocampo

by carrasquelalex1
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to hipocampo

  • knowledge-rag

    lyonzin
    A
    license
    A
    quality
    A
    maintenance
    Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.
    13
    278
    MIT

  • Modular RAG MCP Server

    nobitalqs
    A
    license
    A
    quality
    D
    maintenance
    A fully modular RAG system with MCP protocol integration, enabling hybrid retrieval, multimodal support, and dual-mode transport for connecting to AI assistants like GitHub Copilot and Claude Desktop.
    5
    1
    MIT

Related Servers

  • marsnme

    Marsmanleo
    A
    license
    A
    quality
    B
    maintenance
    Agent-agnostic persistent memory backend. 13 MCP tools, Supabase + Jina embeddings, multi-profile isolation, semantic recall across sessions.
    16
    7
    Apache 2.0

  • pgmnemo

    pgmnemo
    A
    license
    Not graded
    quality
    A
    maintenance
    Agent memory as a PostgreSQL extension: hybrid HNSW+BM25 recall, write-time provenance gates, and outcome-weighted confidence. The MCP server exposes ingest and recall tools over stdio for Claude Code, Codex CLI, and Gemini CLI.
    6
    Apache 2.0

  • memory-mcp

    isaacriehm
    A
    license
    Not graded
    quality
    D
    maintenance
    A self-organizing, persistent semantic memory layer that enables AI agents to store, categorize, and retrieve information using hybrid vector and keyword search. It features autonomous chunking, deduplication, and hierarchical taxonomy management through a PostgreSQL-backed MCP server.
    1
    MIT

  • Second Brain

    guybr3000
    A
    license
    Not graded
    quality
    C
    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.
    2
    MIT

  • mnemostack

    udjin-labs
    A
    license
    A
    quality
    A
    maintenance
    Durable hybrid memory for AI agents. Combines vector search, BM25, temporal retrieval, and optional Memgraph knowledge graph via reciprocal rank fusion. 6 MCP tools: health, search, answer, feedback, graph_query, graph_add_triple. Self-hosted with Qdrant backend.
    7
    7
    Apache 2.0

  • hybrid-recall

    cutlerbenjamin1-cmd
    A
    license
    A
    quality
    C
    maintenance
    A local MCP server enabling hybrid search over documents, memory, and knowledge graphs for retrieval-augmented generation, with tools for SQLite, semantic memory, and entity-relationship queries.
    4
    1
    MIT
Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0

Scored across 37 tools

Disambiguation2/5

Several tools overlap or share confusing boundaries: search_hipocampo and quick_hipocampo_search are exact aliases, search_code and compress_hipocampo are search variants, and 'watch' refers to both directory watching and webhooks (add_watch_dir vs watch_hipocampo). The descriptions clarify intent, but the set would still make an agent choose between near-equivalent retrieval and maintenance tools.

Naming Consistency2/5

Naming mixes verb-first (save_hipocampo, search_hipocampo), noun-first (hipocampo_maintenance, hipocampo_stats), Spanish and English (restaurar_historica vs preload_context), and two different 'watch' concepts. Some tools follow a clear verb_noun pattern, but it is not predictable across the set.

Tool Count2/5

37 tools is well beyond the typical well-scoped range and creates unnecessary surface area. Many operations are available both as standalone tools and bundled inside hipocampo_maintenance or budget/decay, adding maintenance overhead.

Completeness4/5

The surface covers the core memory lifecycle thoroughly: create, update, delete, search, graph links, compression, tiering, restore, health, and webhooks. The main gap is a direct get-by-id/list-memories tool, and retrieval is fragmented across search_code, compress_hipocampo, preload_context, and the search alias.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources