Skip to main content
Glama
stoneskin

open-memex

by stoneskin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to open-memex

  • Remnic

    joshuaswarren
    A
    license
    Not graded
    quality
    A
    maintenance
    Local-first memory for AI agents: one store shared by Claude Code, Codex CLI, Cursor, Pi, Hermes, OpenClaw, and any MCP client. Plain markdown with YAML frontmatter on your disk, hybrid BM25 + vector recall with per-result provenance (Recall X-ray), a correction contract, and the MemCorrect benchmark.
    230
    MIT

Related Servers

  • auxly-memory-cli

    Tzamun-Arabia-IT-Co
    A
    license
    Not graded
    quality
    A
    maintenance
    Local-first, file-based memory layer for AI agents — one shared Markdown vault across Claude, Codex, Gemini, Cursor and any MCP client. Provides read/write memory tools with an audit trail, per-agent trust levels, and Git sync; no cloud and no lock-in.
    2
    MIT
  • Memryzed by hamzaarja

    Memryzedofficial

    hamzaarja
    F
    license
    Not graded
    quality
    C
    maintenance
    Local-first cross-agent memory for AI coding agents. Persistent, shared memory over MCP — what you tell one agent can be recalled by another — with all data stored in a single local SQLite file, no cloud and no API keys.
    -

  • peon-mem

    VineetV2
    A
    license
    Not graded
    quality
    A
    maintenance
    Local-first hierarchical memory for AI coding agents, providing automatic session capture, belief consolidation, and relevant memory injection via an MCP server.
    34 npm
    2
    MIT

  • memmd-mcp

    matamong
    A
    license
    B
    quality
    D
    maintenance
    A shared memory layer for AI agents — one memory.md synced across Claude Desktop, Cursor, Claude Code, OpenAI Codex, and any MCP client.
    4
    2
    MIT
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A4.3/5.0

Scored across 11 tools

Disambiguation4/5

Each tool targets a distinct verb on the memory store, and descriptions actively cross-reference their neighbors (memory_status vs memory_pr_status vs memory_list; memory_propose vs memory_submit vs memory_promote; memory_forget vs memory_supersede), which resolves most confusion. The only residual friction is the three-stage review pipeline (propose/submit/promote) plus two status tools, which an agent must reason about carefully.

Naming Consistency4/5

All 11 names use a uniform snake_case `memory_` prefix with short, readable suffixes. The minor deviation is that two are noun phrases (memory_status, memory_pr_status) while the rest are verb-led, but the pattern remains predictable.

Tool Count5/5

11 tools is squarely in the well-scoped range, and each one earns its place: core CRUD (add/search/list/supersede/forget), the sync/review pipeline, PR mapping, and conflict resolution. Nothing feels redundant or padded.

Completeness4/5

The surface covers the full memory lifecycle — creation, retrieval, listing, supersession, retraction, the propose→submit→promote review chain, sync status, and conflict resolution. Minor gaps: no direct get-by-id tool (ids only come back from list/search) and no in-place edit or tag/alias management command.

Maintenance

ActivityActive
ResponsivenessResponsive

Resources