Agent Plugins Marketplace
← All plugins

memories

v5.16.0

Self-hosted semantic memory with graph-aware search (PPR multi-hop traversal), temporal reasoning (version preservation, date-range filters), multi-backend routing, 6-signal hybrid search, auto-feature metrics, operator workbench, lifecycle policies, and full audit trail

Claude Code1 Skill

By Divyekant GuptaLicense: MIT3 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 24, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install memories for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install memories@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/divyekant/memories

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is mcp-server/assets/claude-code/.

Plugin files

mcp-server/assets/claude-code/
├── .claude-plugin/plugin.json
└── skills/memories/SKILL.md

Included Skills1

memoriesskills/memories/SKILL.md

Memory discipline for capturing and recalling important context across sessions using Memories MCP. Use this skill whenever you make an architectural decision, defer work for later, discover a non-obvious pattern or fix, or when the user explicitly asks to remember something. Also use it when you're about to ask the user a clarifying question or when entering a project domain where prior context might exist — search memories first, the answer might already be stored. Triggers on: "remember this", "store this", "save this for later", phase transitions, post-decision moments, deferred work, implicit tech mentions, entering a new domain, and before clarifying questions. Even if the user doesn't say "do you remember", search proactively when the topic might have prior context.

Plugin manifests1

mcp-server/assets/claude-code/.claude-plugin/plugin.json
{
  "name": "memories",
  "description": "Self-hosted semantic memory with graph-aware search (PPR multi-hop traversal), temporal reasoning (version preservation, date-range filters), multi-backend routing, 6-signal hybrid search, auto-feature metrics, operator workbench, lifecycle policies, and full audit trail",
  "version": "5.16.0",
  "author": {
    "name": "Divyekant Gupta"
  },
  "homepage": "https://github.com/divyekant/memories",
  "repository": "https://github.com/divyekant/memories",
  "license": "MIT",
  "keywords": [
    "memory",
    "memories",
    "mcp",
    "semantic-search",
    "agent-memory",
    "recall",
    "extraction"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[memories on Agent Plugins Marketplace](https://pluginsmp.com/plugins/memories)