1. Conduid
  2. RAG
  3. Apex Memory
MCP server · RAG

Apex Memory

Persistent memory MCP server for AI coding agents. Ultra-lightweight (46 kB), cloud sync, works with Claude Code, Cursor, Windsurf. npm install apex-memory

34Low

Scored a month ago · breakdown

About Apex Memory

Apex Memory is an MCP server published by JJerryChoi in the RAG category: persistent memory MCP server for AI coding agents. Ultra-lightweight (46 kB), cloud sync, works with Claude Code, Cursor, Windsurf. npm install apex-memory.

The repository has 2 stars and 0 forks, with the last commit 7 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/JJerryChoi/apex-memory

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (30)

apex_memory_auto_captureAutomatically capture session context (decisions, files, errors, solutions) at session end

Parameters not published.

apex_memory_loginRegister this machine with apex-memory cloud and get a Pro upgrade link

Parameters not published.

apex_memory_statusShow cloud sync status: workspace ID, subscription tier, last sync time

Parameters not published.

apex_memory_syncManually trigger a cloud sync — push local changes and pull remote (Pro)

Parameters not published.

batch_save_memoriesSave multiple memories in a single transaction — much faster than calling save_memory repeatedly

Parameters not published.

cleanup_orphaned_linksRemove links pointing to deleted memories — keep the knowledge graph clean

Parameters not published.

decay_memoriesArchive old low-importance memories that were never accessed — keeps the store clean

Parameters not published.

delete_memoryRemove a specific memory by ID

Parameters not published.

end_sessionEnd a session with a summary of what was accomplished

Parameters not published.

export_memoriesExport all memories and sessions as JSON — useful for backup, migration, or sharing context across machines

Parameters not published.

Show all 30 tools
export_to_claudemdExport key memories as a CLAUDE.md-ready context block — inject project memory directly into your agent's instructions

Parameters not published.

find_duplicate_groupsScan for duplicate clusters using Jaccard similarity — returns groups of similar memories

Parameters not published.

find_duplicatesDetect similar existing memories using FTS5 search

Parameters not published.

get_linked_memoriesQuery the knowledge graph — find all memories connected to a given memory

Parameters not published.

import_memoriesImport memories and sessions from a JSON export — restore backups or merge context from another machine

Parameters not published.

link_memoriesCreate directional links between memories (related, depends_on, supersedes, contradicts, extends) — build a knowledge graph

Parameters not published.

list_sessionsView past coding sessions

Parameters not published.

list_tagsList all tags across memories with counts — discover how memories are organized and find tags to filter by

Parameters not published.

memory_contextGet full memory context in one call — combines relevant memories, linked memories (knowledge graph), and recent sessions

Parameters not published.

memory_graphGet the knowledge graph as nodes and edges — visualize how memories relate to each other

Parameters not published.

memory_healthDiagnose store health — stale memories, orphaned links, untagged items, cleanup candidates

Parameters not published.

memory_statsGet detailed statistics: totals, category breakdown, importance distribution, most accessed memories

Parameters not published.

memory_timelineChronological activity feed of memory events: creations, updates, sessions, and links

Parameters not published.

merge_memoriesConsolidate duplicates: keeps primary content, max importance, union tags, re-points links, soft-deletes merged

Parameters not published.

recallRetrieve recent memories filtered by project, category, or tags. Sort by `recent` or `relevant` (weighted by importance + recency + access frequency).

Parameters not published.

save_memorySave knowledge, decisions, patterns, or context with categories, tags, and importance scoring (1–5). Warns about potential duplicates automatically.

Parameters not published.

search_memoriesFull-text search across all memories (supports AND, OR, NOT, phrases). Falls back to fuzzy substring matching when FTS5 returns no results.

Parameters not published.

session_summaryReview all memories captured in a session — use at session start to restore prior context

Parameters not published.

start_sessionBegin a coding session tied to a project

Parameters not published.

update_memoryUpdate an existing memory's content, category, tags, or importance in place

Parameters not published.

Ask AI

✦

Ask AI about Apex Memory

Powered by Claude · Grounded in docs

I know everything about Apex Memory. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About Apex Memory

How do I install Apex Memory?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Apex Memory safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Apex Memory still maintained?

The last commit was 7 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.