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.
oscar-wang-xin/mcp-session-saver
MCP server Claude CodeCodexCursor +2
A Model Context Protocol (MCP) service for saving session records to markdown files, organized by IDE, date, and description. Runs locally from the mcp-session-saver npm package.
MCP server Claude CodeCodexCursor +2
Universal knowledge base with Qdrant for Claude Code integration. Runs locally from the claude-kb Python package.
MCP server Claude CodeCodexCursor +2
Reflexive Memory for AI Agents — MCP Server. Runs locally from the erinys-memory Python package.
MCP server Claude CodeCodexCursor +2
Persistent memory system for Claude Code CLI using Obsidian-compatible markdown. Runs locally from the claude-memory-mcp npm package.
Plugin Claude Code
Bundles 1 skill, 1 hook · 41 tokens together
Personalizes your AI assistant from local conversation history using the active host model.
Skill Claude CodeCodex
ACMI is a universal architectural framework for giving AI agents persistent, real-time context. It replaces fragmented, multi-table database joins with a single, lightning-fast Key-Value engine (Upstash Redis) optimized specifically for LLM context windows.
potatohoney-p/weasley-deepmind
Skill Claude Code
A reference for using weasley-deepmind, a server that stores and retrieves an AI agent’s long-term memories between sessions. It describes memory storage, search, language processing, and related tools.
Skill Codex
Create, refresh, or inspect CLASSMAP.md, a lightweight code responsibility index. Use when the task calls for building a code map, updating it after responsibility changes, or checking whether it still matches the code. Inspection-only requests are read-only; this skill does not implement business features.
Plugin Claude Code
Bundles 6 skills, 6 hooks · 354 tokens together
Cross-AI local memory layer for Claude Code, Codex, Gemini CLI, Antigravity, goose, Cursor, opencode, Kimi CLI and more: hybrid search, six summarizer providers, hosted or local embedder. Replaces claude-mem.
Cursor rule Cursor
Open-source, modular “brain” for AI employees. Integrates with n8n and workflow engines, features persistent agent memory, natural language interface, and feedback loops. SaaS-ready, extensible, and easy to deploy with Docker.
Skill Claude Code
Turns handwritten reMarkable notes into a queryable semantic memory. Syncs pages from a reMarkable tablet (via the reMarkable MCP server, rmapi, or a USB/SSH bridge), renders each page to an image and reads the handwriting with Claude vision — no OCR key — then extracts each page into confidence-scored, human-editable…
Plugin Claude Code
Bundles 12 skills, 1 agent, 4 hooks · 1,206 tokens together
Personal Chief of Staff for product people: a work second brain built from your answers in a setup interview, kept in your own markdown files and adapted to you through use. Run /pm-chief-of-staff:setup in an empty folder.
vikcena01/ai-continuity-plugin
Plugin Claude Code
Bundles 1 skill, 3 commands, 2 hooks · 121 tokens together
Durable project state across AI sessions: decisions, constraints, and rejected paths, versioned in git as plain markdown. Not a memory tool — it answers what is true about the project now, and what must not change.
Skill Codex
Use when the user asks to use Throughline from Codex, continue or restore Throughline memory, export read-only handoff context for a local launcher, prepare a new Codex thread handoff, summarize a captured Codex session, or check whether the Throughline Codex Stop hook captured the current session. Hide long…
Plugin Claude Code
Bundles 5 skills, 5 commands, 6 hooks, 1 MCP server · 686 tokens together
Bifrost MCP gateway plugin for Claude Code and Claude Desktop: skill discovery, agent-driven memory, one-command onboarding, signed admin policy, and opt-in browser sign-in.
Plugin Claude Code
Bundles 1 skill, 3 commands · 331 tokens together
Reconcile every AI coding agent's conversations (Claude Code, Codex, Gemini, Cursor, Aider, opencode, Cline + 11 more) with git and docs into one cited ground truth, and distill durable ADR/PDR/BDR decision records.
Skill Claude CodeCodex
An interactive setup skill that turns an empty Claude Code folder into an OpenClaw-style personal assistant. It asks about the assistant's identity, tone, communication channels, permissions, and memory, then creates the related instruction and memory files.
vantasnerdan/substrate-framework
Skill Claude Code
CLI commands, patterns, and integration guide for agent-memory.
Skill Claude CodeCodex
Destilliert rohe Staging-Inbox-Bullets (staging/captured.md) in bleibende, getypte Memory-Dateien. Verwende diesen Skill, wenn der User 'distill', 'Staging aufräumen', 'Inbox abarbeiten', 'Memory verdichten' sagt oder nach einem Ingest-Lauf oder Staging-Nag.
Skill Claude Code
Use when the user is clearly angry, frustrated, cursing, or complaining "wrong again" / "useless", or correcting the same thing a third time. Open with a dramatic funny apology in medieval-court style (Spare me, Your Majesty! / I deserve death!) tagged with the skill name, trace back the last turn to find the mistake…
fredriccliver/oak-memory-plugin
Plugin Claude Code
Bundles 1 skill, 9 commands, 1 hook, 1 MCP server, 1 plugin · 152 tokens together
Persistent personal and shared vector+graph memory through local or cloud profiles.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 198 tokens together
Agent-driven knowledge base with immutable raw sources, mutable wiki pages, BM25 search, code analysis, and self-checking lint. Use when managing knowledge bases, importing documents, writing wiki pages, or parsing source code.
MCP server Claude CodeCodexCursor +2
Your local, private memory layer. Index your notes and files, then recall anything with citations and temporal reasoning — 100% on your machine. Runs locally from the @jnmetacode/engram npm package.
Skill Claude CodeCodex
Local-first agent memory and knowledge service (RAG) installed from PyPI. Use when a task needs to store or recall long-term user preferences, project decisions, facts, documents or web pages, when different projects need separate memories, or when the user mentions "kb memory", "kb", or a local MCP memory service.…
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: