Plugins · AI, RAG & memory
50 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.
- membase ★ 3
Membase connects Claude Code to Membase Cloud, giving Claude persistent memory and wiki workflows across coding sessions. It can recall rele - memento
Memento gives Claude Code a real memory: persistent, searchable knowledge that survives across every session, every project, and every devic - memex-mcp
Persistent memory for AI coding agents. Builds a temporal knowledge graph of your codebase from commits and source files, then serves it thr - memoriant-llm-gateway-skill
Compliance-first LLM gateway for Claude Code. Policy-as-code enforcement (YAML policy definitions), tamper-evident audit trails, PII redacti - memoriant-mcp-data-skill
MCP server for conversational data access in Claude Code. Query CRM systems, ticket trackers, and databases using natural language. Includes - memory-compactor
Automatically monitors MEMORY.md size and warns Claude to compact it when it exceeds a configurable line threshold. Installs a PostToolUse h - memory-toolkit ★ 13
Session memory lifecycle for Claude Code. Structured handoffs between sessions, workstreams to switch context without losing it, background - memorydetective ★ 1
Hunt iOS memory leaks and investigate runtime performance from inside Claude Code. memorydetective bundles an MCP server with 28 tools for a - mempenny ★ 2
Keep Claude Code auto-memory lean. Triage (delete/archive/distill) memory files without losing forward-looking truth. Pairs with caveman. - mind-glaive
Eliminate context rot in Claude Code with intelligent memory hierarchy, auto-learning hooks, and specialized subagents. Uses an 8-layer memo - mindwright
mindwright gives Claude Code persistent, per-agent memory. It captures what happens during a session, distills it into long-term facts via a - mister-anderson ★ 3
Beads development for humans — a structured, human-controlled development pipeline with task tracking, code review gates, and multi-agent or - mistral-mcp ★ 15
Exposes the full Mistral AI API surface to Claude Code through a local MCP server: 22 tools (chat, streaming, embeddings, OCR, vision, Voxtr - mmpm-cognitive-os
Constitutional multi-agent decision architecture for major programme governance. 16 agents across 4 layers (Programme Cognitive Chair, 7 Str - mumo
Multi-model deliberation as MCP tools, with an auto-triggering skill. Consult a panel of models (Claude, GPT, Gemini, Grok, Qwen, GLM, Kimi) - munin-memory ★ 3
# Munin for Claude Code > **Munin** is a long-term memory system for developers. Every time you work with Claude Code, Munin remembers your - neko-gundan ★ 1
Multi-agent orchestration framework for Claude Code. Organizes Claude into a hierarchical cat team — Oyakata-neko (General/Opus) plans strat - neko-harness-doctor ★ 1
Diagnose your Claude Code harness (CLAUDE.md, settings.json, .mcp.json, hooks, skills, memory, MCP servers, and workflow) against 25 anti-pa - neutrally
Persistent cross-session memory for Claude Code. Neutrally auto-injects your project context, decisions, and tech stack at session start so - nexo-brain ★ 27
Cognitive co-operator that gives AI agents persistent memory, learning, and work continuity. Includes session management, episodic/semantic - nexus-agents ★ 18
Intelligent orchestration platform for AI coding tools. Coordinates Claude, Codex, Gemini, and OpenCode through a single MCP server — routin - nexus-the-cartographer ★ 2
AI Cowork metabrain with Knowledge Graph, Thought Stack, Fuel Intelligence, and local AI Overseer. 20 native MCP tools for persistent sessio - nodebench ★ 14
Operating intelligence for founders. 350 MCP tools across 57 domains — decision intelligence, entity research, QA automation, and session me - noosphere ★ 18
Shared Debug Memory for Claude Code Agents. Noosphere helps Claude Code consult reusable debugging knowledge, publish verified fixes, and av - notify-sounds ★ 1
Plays system sounds in Claude Code when a task finishes or when permission is needed, so you don't have to keep watching the terminal. Cross - notion-memory ★ 9
Give Claude long-term memory across sessions using your Notion workspace. Claude remembers your preferences, decisions, project context, and - nxtg-forge ★ 5
Structural governance for AI coding agents. 33 agents, 23 commands, 32 skills, 8 MCP governance tools, and 7 hooks that enforce a core rule: - obsx ★ 1
Obsidian is the operating system for knowledge work; Claude is the reasoning engine. The Obsidian Connector marries them, empowering users t - octo ★ 4,064
Multi-LLM orchestration for Claude Code and Cowork. Coordinates 8 AI providers (Codex, Gemini, Claude, Perplexity, OpenRouter, Copilot, Qwen - open-ontologies ★ 495
AI-native ontology engineering with 39 MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL on - open-rx
Open RX makes Claude actually good at building production web apps. 7 free skills (OTC tier) covering React architecture, Next.js App Router - orchestrator-workflow-plugin
A multi-agent development framework that splits project builds into phases using three specialized roles: an Orchestrator (plans and coordin - origin ★ 64
Personal AI memory layer. Capture decisions, lessons, and context that carry across sessions. - ory-lumen ★ 291
lluminate your codebase with semantic search for code agents. Faster results with less tool calls. Works great in small and large code bases - parrot
Kills self-repetition in LLM responses. Cuts 30-40% wasted tokens by eliminating restated questions, echoed instructions, recap paragraphs, - pearl-llm-memory
Externalized Cognitive State Transfer PEARL-LLM Memory (.pearl) is a JSON-based file format for storing structured, layered, verifiable cont - pencil-dev-skill ★ 23
Teaches AI coding tools to design and edit pencil.dev UI files (.pen format) through the Pencil MCP server. Every read and write goes throug - phone-a-friend ★ 10
Phone a Friend is a CLI relay that lets AI coding agents collaborate by sending prompts and repository context to other AI backends. It supp - phone-a-friend-paf ★ 10
Phone a Friend lets Claude Code call other AI coding backends for second opinions, code review, and multi-agent collaboration. It relays you - pinrag
Local RAG for your coding workflow. Index PDFs, YouTube videos, GitHub repos, and Discord exports, then query them with citations directly f - playlist-curator ★ 5
A skill that lets AI agents reason about music, not just search for tracks. Curate playlists from natural language using audio DNA profiling - plugin-manager ★ 2
Visual web UI for managing Claude Code plugins. Opens as a standalone browser window with an Anthropic-styled interface. Browse all installe - pmm ★ 15
If you have ever had AI hallucinate and make things up (and gaslight you, even): it's because summaries do not preserve nuance. Each /compac - pownie ★ 24
The agent harness for offsec. It's a plugin for Claude Code packed with skills, hooks, memory system that works best for using Claude Code t - pramana
Reference implementation of the semantic layer from "Knowledge Engineering: The Future of AI-Assisted Software Engineering" (https://kn owle - prepare-delivery ★ 3
Pre-ship quality gates without the ship. Runs the full pre-merge pipeline — deslop (clean AI debris), simplify (de-bloat), agnix (lint agent - preserve-session ★ 1
Preserves Claude Code session history across project directory renames, moves, and copies by assigning each project a path-independent UUID - private-journal-mcp ★ 9
A comprehensive MCP server that provides Claude with private journaling, semantic search, resources, and guided prompts for reflection and l - productivity-pro
A customized version of Anthropic's productivity plugin with two additions: the update skill reads transcripts across all chats in the proje - project-pilot
Project Pilot is a Claude Code plugin that gives Claude a persistent memory layer for your project. It captures your architecture decisions,