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.
- consensus
Break through difficult problems by gathering diverse AI perspectives in parallel. Consensus queries multiple AI providers concurrently — GP - context-link
Connect Claude to your Context Link knowledge base and retrieve just the right context from your connected sources: Notion, Google Drive and - context-os ★ 9
Context OS helps Claude Code find the right files faster. It builds a local repo graph of paths, symbols, imports, line counts, and hot file - coral
Coral turns any git repo into a queryable Karpathy-style LLM wiki (.wiki/), preserves a bi-temporal history of the codebase + the docs about - corebee
AI customer support operations toolkit — manage conversations, contacts, knowledge base, analytics, and team workload. 9 skills, 4 agents, 3 - coremem ★ 1
CoreMem gives Claude persistent memory across every session. Your preferences, project context, and working style live in mems — structured - corivo ★ 1
Your Cyber Partner — Memory Storage & Intelligent Push - create-claude-plugin ★ 2
End-to-end skill for creating a Claude Code plugin: scaffold, build, test, host, and submit to the official Anthropic marketplace. - crowdcast ★ 11
Multi-agent social simulation for prediction and creative exploration. Zero external dependencies — runs entirely within Claude Code. - cxpak ★ 27
Token-budgeted codebase context for Claude Code. One call to auto_context gives Claude the optimal context for any task — automatically sele - cync
Cync backs up and syncs your Claude Code settings to any Git repository. Push your ~/.claude/ configuration from one machine and pull it on - debate ★ 3
Structured multi-round debate between AI tools with proposer / challenger roles and a final verdict. `/debate` orchestrates a back-and-forth - decision-council
AI advisory panel for decisions that matter. Decision Council assembles a panel of independent AI advisors to debate your decision from mult - deep-research
Multi-agent deep research pipelines for Claude Code. Runs internet research, repository analysis, schema-driven structured research, and med - dev-tracker
Cross-session memory for Claude Code. A structured development journal that doesn't hallucinate, doesn't spam, and doesn't rewrite your note - devils-advocate
A devil's advocate agent that delivers the final critical review on plans, designs, and integration reports. Designed to break groupthink in - distributed-architect ★ 1
A reasoning framework that helps Claude analyze distributed system code changes for correctness before writing code. It provides an always-o - dj-claude ★ 2
Adds live music and multi-agent jam band capabilities to Claude Code. Slash commands and MCP tools for setting vibes, building layered jam s - djclaude ★ 1
AI music generation for Claude Code using Google Lyria 3. Generate 30-second clips or full 2-3 minute songs from text descriptions. Control - dominion-flow ★ 77
Research-backed orchestration for Claude Code. Structured workflow from idea to production with parallel execution, session memory, 70-point - don-cheli-sdd-framework ★ 57
Full SDD (Spec-Driven Development) framework that turns requirements into tested, documented, production-ready code through 7 disciplined li - drift-detect ★ 4
Deep repository analysis to realign project plans with actual code reality. `/drift-detect` discovers drift between documented plans (CHANGE - egnyte ★ 2
Search, manage, and extract intelligence from Egnyte enterprise content. Connects Claude Code to your Egnyte domain via the Egnyte MCP serve - eight-eyes ★ 2
Multi-agent code review with 8 hook-enforced roles. Each role targets a different failure surface — the skeptic reviews blind without the im - ember-memory ★ 2
Persistent semantic memory for Claude Code. Stores knowledge in a local ChromaDB vector database and automatically retrieves relevant contex - enam ★ 2
Persistent memory for Claude Code — at ~350 tokens ambient cost, with no Docker, no API keys, and no MCP servers. Engram captures your sessi - engram
Persistent memory for AI agents. Give Claude real memory that survives across sessions -- semantic recall, automatic consolidation, knowledg - enhance ★ 4
Master enhancement orchestrator: 7 specialized analyzers run in parallel and produce a unified report with certainty-graded findings. `/enha - enzyme ★ 59
Knowledge indexing for Obsidian vaults — explore your notes by concept, not keyword. Enzyme reads the tags, links, and folders you already u - eterdis-strategy-skills ★ 7
Open strategy frameworks for AI agents — 11 skills that turn any LLM into a strategy thinking partner. Each skill is a structured SKILL.md p - fashion-agent
A personal AI fashion stylist that brings outfit recommendations, style tips, deal negotiation tactics, and real product search directly int - fellowship ★ 1
A LotR-themed multi-agent system for solo product devs. Gandalf orchestrates nine companions across product, architecture, engineering, revi - first-principles-review
A Claude Code skill that reviews codebases top-down: WHY (goal) → WHAT (architecture) → HOW (implementation) → improvements ranked by levera - flow
Flow turns Claude into a project partner who manages your backlog. Say "park this for later," and it queues the idea. Say "what's next?" and - foresight-engine ★ 1
Strategic intelligence plugin for Claude Code. Give it any real-world forecasting question and it produces a structured four-scenario analys - foresight-intelligence ★ 1
Strategic foresight intelligence using IFTF methodology. Two prediction modes: Soft Predict Future (Claude-native skill, instant, claude.ai - formal-agent-contracts ★ 1
Formal methods toolkit for multi-agent development. Define inter-agent contracts in VDM-SL, verify with VDMJ, prove with Z3, and generate Ty - fortytwo-mcp ★ 5
Fortytwo Prime: collective multi-agent inference for high-stakes questions. ALWAYS use when the user says "Ask Fortytwo", "Ask Prime", "Ask - framecraft ★ 8
Generate polished demo videos from a single prompt. The plugin teaches your LLM story structure, visual design, and narration craft, then or - frank-grimes ★ 2
A pessimistic iteration loop for systematically destroying, rebuilding, and hardening ideas. Named after Frank Grimes ("Grimey") from The Si - gangsta ★ 81
AI agentic skills framework for spec-driven development — mafia-syndicate hierarchy with adversarial brainstorming, institutional memory, an - gate-and-ship ★ 2
Quality gates then ship — chains `/prepare-delivery` and `/ship` in one command. Runs the full pre-ship pipeline (deslop, simplify, agnix, e - gemini ★ 6
Use Gemini CLI from Claude Code to review code, analyze codebases, or delegate tasks. Leverages Gemini's 1M token context window for whole-c - gemini-for-claude
Bridge Claude Code to Google's Gemini CLI. Mirrors the pattern of the official Codex plugin but for Google's AI stack. Adds 9 slash commands - gh-file-attach
A Claude Code plugin that gives Claude the ability to upload files to GitHub and get permanent, shareable URLs — perfect for embedding scree - githubclip ★ 1
GitHub-backed agent orchestration for Claude Code. githubclip routes work by issue labels into persona-based agents (Orchestrator, CEO, and - gitkb
Give Claude Code the knowledge layer your agents deserve: local code intelligence, a persistent knowledge graph, task context, and team sync - goodmem ★ 8
GoodMem memory infrastructure for AI agents. Use Python SDK skills to write code that manages embedders, spaces, and memories, or use MCP to - gr0m-mem ★ 2
Zero-install persistent memory brain for Claude Code that stops the model from re-asking and re-deriving across sessions. Four MCP tools (me - graph-query-mcp ★ 2
FastMCP server for surgical queries against a vault knowledge graph. NetworkX node-link JSON. Companion to graphify.