Skip to main content
Glama
terrizoaguimor

celiums-memory

by terrizoaguimor
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Hybrid

Related Servers

Alternatives to celiums-memory

  • MemoryMesh

    CheMiguel23
    A
    license
    C
    quality
    F
    maintenance
    This project is based on the Knowledge Graph Memory Server from the MCP servers repository and retains its core functionality.
    44
    354
    MIT

  • RecallNest

    AliceLJY
    A
    license
    A
    quality
    A
    maintenance
    Persistent memory MCP server for AI coding agents (Claude Code, Codex, Gemini CLI). Hybrid retrieval (vector + BM25), cross-encoder reranking, knowledge graph, session checkpoint/resume, and multi-scope isolation. Local-first with LanceDB.
    30
    9 npm
    15
    MIT

Related Servers

  • Brain-MCP

    DDguan2010
    A
    license
    B
    quality
    D
    maintenance
    Provides AI with persistent memory management including short-term memory (FIFO queue), long-term memory (graph-based storage with associations), and thought process management with multiple cognitive modes for continuous learning and reasoning.
    24
    4 npm
    3
    MIT

  • MCP Memory Server

    TED-H-com
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides persistent long-term memory, knowledge base, and audit trail for AI agents, with intelligent recall, salience tracking, and CJK-aware context management.
    3
    MIT

  • knowledge-base-server

    umazgwcywy
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to capture, classify, synthesize, and retrieve persistent shared knowledge from sources such as Obsidian, code, transcripts, bookmarks, and sessions. It provides token-efficient search, context briefings, and tiered memory through MCP and REST APIs.
    14 npm
    MIT

  • BuildAutomata Memory MCP

    brucepro
    F
    license
    Not graded
    quality
    D
    maintenance
    Provides AI agents with persistent, searchable memory that survives across conversations using semantic search, temporal versioning, and smart organization. Enables long-term context retention and cross-session continuity for AI assistants.
    14
    -

  • MCP AI Memory

    scanadi
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to store, retrieve, and manage contextual knowledge across sessions using semantic search with PostgreSQL and vector embeddings. Supports memory relationships, clustering, multi-agent isolation, and intelligent caching for persistent conversational context.
    8 npm
    50
    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

A3.6/5.0

Scored across 26 tools

Disambiguation3/5

The tools are mostly distinct by domain (memory, journal, writing, research), but there is notable overlap between forage, sense, and research_search — all perform knowledge-base search with slightly different framing. Similarly, absorb and research_synthesize both retrieve and synthesize knowledge, and journal_recall vs recall could confuse an agent about which memory store to query.

Naming Consistency3/5

Naming is mixed: some tools follow verb_noun (journal_write, research_search, write_scene_create), but others use bare verbs (forage, absorb, sense, remember, recall) and one uses a noun_verb pattern (map_network). The write_* and research_* prefixes are consistent within their groups, but the overall set lacks a unified convention.

Tool Count3/5

26 tools is on the heavy side, but the server covers four distinct subdomains (memory, journal, writing, research), so each tool has a plausible role. The count feels borderline — a few tools could be consolidated (e.g., forage/sense/research_search) without losing capability.

Completeness4/5

The writing and research subdomains have solid lifecycle coverage: create/get/update/export for writing, and create/search/synthesize/export/continue for research. The memory and journal subdomains cover write/read well. Minor gaps: no tool to delete or update memories, no journal entry deletion, and no research project update/delete, but agents can work around these.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources