AI Marketplaces Leaderboard

AiAkiv Memory

ChatGPT plugin

Shared memory for AI agents

View in ChatGPT directory
Featured

shelf not read today

Movement

Over the last 30 days of daily snapshots.

Rank by placement

#3800of 3,89224h7d

Not enough data points to chart.

In its category

Where this plugin sits among the plugins filed beside it. Each row keeps its standing in the whole directory.

Developer tools231st of 235 by placement
#PluginPosition7d
3755Build macOS Apps#3755340places down
3756Build Web Apps#3756340places down
3758Build iOS Apps#3758340places down
3800AiAkiv MemoryThis page#3800
3816Gateway#3816
3840Chartquery#3840
3859Veille#3859

All 235 Developer tools plugins

AiAkiv is long-term memory that AI agents and teammates share over MCP. It saves the important parts of your conversations as a knowledge graph and recalls them across sessions, tools, and teammates — so context one AI saves, the next one picks up, and a whole team works from one shared memory instead of scattered private chats. Save with an explicit command ("ak save"), recall by meaning with semantic search. Hosted remote MCP server with OAuth sign-in; Korean and English supported.

Example prompts

  • ak save — store a summary of this conversation in my long-term memory
  • search my memory for what we decided about the pricing model, newest first
  • what did I save most recently, and under which topic tags?

Skills

  • aiakiv-cards

    Create a public AiAkiv card from the user's memory. Use when the user asks to make a card, share a memory as a link/page, publish a summary card, or asks what AiAkiv cards are or how to fix/delete one. A card is a one-page public site (card.aiakiv.com) written by YOU from memory search results and baked by the card service — live on the open web the moment it is created.

  • aiakiv-graph-query

    Write graph queries (Cypher subset) against AiAkiv/MWeft memory with query_memory_graph (and query_partner_memory_graph across a link). Use when the user asks HOW memories are connected — shared entities, bridges, threads, timelines, multi-hop paths, "similar but structurally related", entity co-occurrence — or when a search hint block contains a `graph_query` example. Not for plain recall (use search_memory).

  • aiakiv-links

    Read a LINKED partner org's memory through the partner memory tools. Use when the user asks what a partner/linked org/team knows, wants to compare their memory with a partner's, mentions a link or partner org, or when a probe candidate carries side=remote. Covers choosing between search_partner_memory, find_partner_memory_connections and query_partner_memory_graph, reading results, and what each error reason means.

  • aiakiv-save-and-recall

    How to write a memory that will be found again, and how to read what AiAkiv memory returns. Covers summary and entity spelling rules, what to do when a save is rejected (summary or content too long, a truncation marker, arguments arriving merged or empty), and how to interpret the related-memory signal that search responses carry. Use when saving to AiAkiv memory, when a save call fails or its arguments collapse, or when deciding whether a search result needs a follow-up expansion call.

Categories
Made by
AiAkiv · Website
Version
2.0.0
Created At
July 19, 2026
More info