12,531 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
AlekseiMarchenko/central-intelligence
Skill Claude CodeCodex
Persistent memory across sessions. Remember facts, recall them later with semantic search, and share knowledge between agents. Use when you need to store information for later, load context from past sessions, or forget outdated memories. Five commands: remember, recall, context, forget, share.
MCP server Claude CodeCodexCursor +2
MCP server "scrapbox-mcp" as configured in YuheiNakasaka/scrapbox-mcp. Runs locally from the scrapbox-mcp npm package.
MCP server Claude CodeCodexCursor +2
Memory Control Protocol - AI memory and thinking management system. Runs locally from the digital-brain-mcp npm package.
adamkwhite/universal-memory-mcp
MCP server Claude CodeCodexCursor +2
A Model Context Protocol server for searchable local storage of AI conversation history — Claude, ChatGPT, Cursor, and custom formats. Runs locally from the universal-memory-mcp Python package.
MCP server Claude CodeCodexCursor +2
A simple MCP server that provides LLMs with the current date and time context. Runs locally from the @pinkpixel/datetime-mcp npm package.
Plugin Claude Code
Bundles 6 skills, 1 MCP server · 81 tokens together
Persistent team memory for AI coding assistants — save, search, and share observations across sessions with a local SQLite database.
MCP server Claude CodeCodexCursor +2
A minimalist, file-based knowledge base server (MCP) for LLMs. Runs locally from the @cmwen/min-kb-mcp npm package.
smallpinksquare/codex-history-hub
MCP server Claude CodeCodexCursor +2
MCP server "codex-history-hub" as configured in smallpinksquare/codex-history-hub. Runs locally from the codex-history-hub Python package.
Cursor rule Cursor
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
Skill Claude CodeCodex
Use when the user wants to find, read, save, or be reminded about anything in their MarkIt library (their personal saved-links-and-notes memory), or mentions MarkIt at all. Covers searching well, saving with context, managing reminders, and feedback etiquette over the MarkIt MCP connection.
MCP server Claude CodeCodexCursor +2
Local MCP server to sync, clean, and index AI chat logs locally. Saves up to 40% context tokens. Runs locally from the chronicle-mcp-server Python package.
Plugin Claude Code
macOS-only MCP server that exposes iMessage history to Claude and exports per-chat conversations into an Obsidian vault. Direct chat.db read, Whisper voice-note transcription, FTS5 search, AppleScript send with draft+confirm.
Skill Claude CodeCodex
Use when the user asks a factual question whose answer might live in the vault. Invokes mnemesearch. Production mnemesearch is FTS5 BM25. The experimental feature-hashed lexical-vector backend is not wired into MCP. KG enrichment is gated to summarize or timeline when full-profile graph state is active.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 106 tokens together
Install and connect Firekeep — one self-hosted Keep that carries knowledge, working context, coordination, and evidence across AI agents — then verify it with the product's own doctor.
MCP server Claude CodeCodexCursor +2
Context portability MCP server for compressing, formatting, and resuming AI conversation handoffs. Runs locally from the @contextbridge_ai/mcp npm package. Needs 5 environment variables to run.
Plugin Claude Code
Bundles 13 skills, 2 agents · 686 tokens together
Obsidian vault integration with local RAG capabilities for Claude Code.
MCP server Claude CodeCodexCursor +2
MCP server "obsidian-live" as configured in gapmiss/live-mcp-for-obsidian. Runs ./build/cli.js with node.
Skill Claude CodeCodex
Use whenever persistent agent memory is read, written, or has grown past its budget - the first time memory is consulted in a session, whenever something worth remembering appears, and whenever MEMORY.md or a topic file exceeds its size budget. Implements a two-tier structure (slim MEMORY.md index linking memory-.md…
Skill Claude CodeCodex
Search and read past agent sessions on this machine — your own and other agents' — with agentcarto. Use when the user refers to earlier work ("what did we decide", "carry on from last time", "when did we touch this file"), or when the context you need is in a session rather than in the code.
Skill Claude CodeCodex
A set of rules for how Lume learns lasting preferences and keeps its workspace and conversation files organized. Lume is the application whose configuration and memory it manages.
Skill Claude CodeCodex
Set up and maintain a "project brain" — a brain/ folder holding three living documents (decisions.md, flow.md, todo.md) that give a project persistent memory across chat sessions. Use this skill whenever the user wants a decision log, architecture/flow notes, project memory, living documentation, or notes that survive…
mario-hernandez/claude-compact-manual
Skill Claude Code
Claude Code skill for deterministic context compaction. Compresses the current Claude Code session to the clipboard for a manual rewind+paste workflow. A deterministic alternative to /compact that extracts literal dialog and truncates only tool outputs — no LLM summarization. Use when the user says 'compact the…
Skill Claude CodeCodex
Turn any conversation into a queryable knowledge graph. Three-layer portable memory file: TRON (structured input+output capture with emotion, psychology, intent — every turn), Sparse6 (layered relational graph with community detection, hyperedges, confidence scores — every turn), GRAPHREPORT (god nodes + surprising…
Plugin Claude Code
Bundles 4 skills, 6 hooks · 267 tokens together
A project structure for keeping an AI agent’s memory outside the model in three layers: persistent notes, an index, and detailed records. It also provides templates, approval controls, event logs, context-saving procedures, and weekly review tools.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: