Skip to main content
Glama
phygital-memory

phygital-memory

Official

Related Servers

Alternatives to phygital-memory

Related Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables multiple AI agents and clients to share a self-hosted memory store over MCP or REST, supporting note creation, search, change tracking, and optional semantic retrieval from desktop, web, or mobile.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Gives AI assistants long-term memory by letting them search, read, create, and organize Markdown notes, folders, tags, and links through a hosted note-taking backend.
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI assistants to search, read, create, update, and remove personal markdown notes stored locally, providing persistent memory across sessions.
    18 npm
    2
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to search and read Markdown notes by keyword, meaning and links, with cited recall and honest no-match results. It also supports guarded, evidence-checked memory writes with receipts, conflict handling and lifecycle-aware filtering.
    MIT
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables AI assistants to read and write a local, encrypted-by-default memory store, so they can share persistent notes and context across sessions and models on your machine.
    56 npm
    -
  • A
    license
    A
    quality
    B
    maintenance
    End-to-end-encrypted markdown notes that double as agent memory: on-device semantic search (no API key), scoped and revocable agent keys, a hosted connector for Claude.ai and ChatGPT, and a self-hostable relay that stores ciphertext only.
    9
    701 npm
    MIT

TDQS

A4.4/5.0

Scored across 17 tools

Disambiguation4/5

The read family (search_notes, open_result, around_result, read_note, read_file_text, list_notes, recent_changes) overlaps in the abstract, but each description explicitly states its niche and points to the alternative ('use open_result for search results, read_note before an edit, read_file_text by path'), which prevents most misselection. Edit tools (replace_in_note vs append_to_note vs create_note) are cleanly separated by intent. Only around_result and open_result with whole_note=true feel genuinely close, requiring the agent to read descriptions to choose.

Naming Consistency4/5

The dominant pattern is verb_noun (search_notes, read_note, create_note, list_notes, move_note, trash_note, finish_handed_note), which is predictable. Deviations are minor: noun-only names (status, handed_notes, recent_changes) and inconsistent creation verbs (create_note vs make_folder).

Tool Count4/5

17 tools is slightly heavy but each maps to a real capability: entry/permissions, four search-and-read paths, five edit/FS operations, two AI-task tools, backlinks, recents, and raw file reading. A couple of tools (around_result, make_folder) are marginal edge cases that could be folded into neighbours, but nothing is clearly redundant.

Completeness4/5

Full note lifecycle is covered: discover (status, list_notes, search_notes, recent_changes), read, create, edit, append, move/rename (notes and folders), trash, plus folder creation, backlinks, file-type reading, and the handed-task workflow with a completion step. Gaps: no tool to browse or restore version history (versions are created but only the human can undo), no trash listing/restore, and private-folder access is deliberately gated, which an agent can work around by asking.

Maintenance

ActivityMaintained
ResponsivenessNo issues