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.
- groundwork ★ 42
Groundwork is a structured development workflow plugin that guides you from product requirements through architecture, implementation, and v - gsd-plugin ★ 86
Get Shit Done Plugin - handles large codebase contexts - structured workflow plugin for Claude Code with 60+ slash commands, 21 agents, MCP - guided-ai-product-management ★ 7
The most comprehensive PM skills plugin available — 83 structured workflows across 9 domains, built natively for Claude Code and compatible - guild ★ 7
Guild turns Claude Code into a self-evolving team of specialist agents for larger software tasks. It plans before execution, selects the rig - hackflow-ppt ★ 2
AI-powered hackathon PPT generator for Claude Code. One /ppt command to analyze your project codebase, choose from 6 stunning visual styles - harness-boot ★ 1
Multi-agent development harness for Claude Code. Your AI has speed; we give it direction — through living specs and focused specialist agent - harness-evolver ★ 49
Autonomous LLM agent optimization using LangSmith. Spawns 5 parallel proposers in git worktrees, evaluates candidates via LangSmith experime - harness-init ★ 53
Makes a repo agent-ready with AGENTS.md, boundary tests, CI pipeline, and GC scripts based on OpenAI's harness engineering methodology - harness-kit ★ 29
HarnessKit is a professional-grade engineering framework that empowers AI agents with a robust 'harness' of structured controls and speciali - haytham ★ 13
Lifecycle control plane for AI-built products. Takes a startup idea and produces a validated, specified, architected, implementation-ready s - heimdall
Analyze video files: especially bug report screen recordings, directly in Claude Code. Extracts frames via ffmpeg, transcribes audio via whi - hipocampus ★ 206
Persistent memory that survives across sessions. Hipocampus gives your agent a 3-tier memory system (hot/warm/cold) with a self-compressing - hivemind ★ 1,605
Hivemind adds persistent memory, context sync, and a virtual filesystem to your coding agent. It captures session history, generates AI wiki - hs ★ 32
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed - hyperflow ★ 3
Hyperflow turns a Claude Code session into a structured engineering workflow through eight chained slash commands. /hyperflow:spec runs a gu - image-generation
A model-agnostic skill for prompting modern text-to-image models — Imagen, Gemini Image, GPT Image, DALL·E, Stable Diffusion, Flux, Ideogram - imessage-mcp ★ 2
macOS-only iMessage MCP server. Direct chat.db read, voice-note transcription, FTS5 search, AppleScript send with draft+confirm. - inclusive-ai
LGBTQIA+ safety tools for LLM engineers — audit prompts, review code, and catch harms before you ship - inertialai
Embed and analyze sensor and time-series data using the InertialAI API. Provides MCP tools for embedding, similarity search, and nearest-nei - ix-memory ★ 7
Ix Memory connects Claude Code to Ix, a structured, persistent memory backend for codebases. Instead of reading raw source files to answer q - jarvis
A voice-driven interaction plugin for Claude Code. Local speech-to-text, text-to-speech, and speaker verification — fully offline, fully han - join-meeting ★ 155
AgentCall turns any AI coding agent into a meeting participant. Install the `join-meeting` command, give your agent a meeting link, and the - jprofiler ★ 2
Java profiling with AI agent integration. Profile CPU, memory, JDBC, HTTP and more. - karimo-harness-engineering-agent-orchestration ★ 287
Harness engineering framework for Claude Code — plan mode on steroids. Product design-driven agent orchestration with sub-agents and agent t - keepgoing
Session memory for Claude Code automatically saves checkpoints during work, shows what you were doing upon return, and tracks progress acros - kepler
Kepler turns your browsing into AI-ready memory. Save links, pages, videos, and references with full context — then organize them into Space - khaki-sketcher
Multi-model orchestration for cross-validated development. Codex reasons, Gemini sees, Sonnet builds. Think → Design → Build → Verify workfl - kindex ★ 26
Kindex is a persistent knowledge graph for Claude Code. It turns Claude from a session-scoped tool into a project-scoped collaborator — capt - larch ★ 4
Larch is a multi-agent workflow automation plugin for Claude Code that orchestrates the full software development lifecycle — from design th - launchpad ★ 1
The most comprehensive agentic coding harness for Claude Code that works for both greenfield and brownfield projects. Drops 38 slash command - lean-kg ★ 218
Lightweight Knowledge Graph for AI-Assisted Development LeanKG is a local-first knowledge graph that gives AI coding tools accurate codebase - learn ★ 2
Research any topic online and create comprehensive learning guides with RAG-optimized indexes for your AI agents. `/learn react hooks` searc - learned-behavior
Self-improving memory for Claude Code. Observes hooks (tool use, edits, errors, guard blocks), distills recurring patterns into durable rule - letmewatch ★ 9
Lets Claude analyze video files by extracting key frames using ffmpeg scene detection. Instead of processing video natively, the plugin capt - lightning-tv-expert-plugin ★ 3
Lightning TV framework expertise for @lightningtv/solid Smart TV applications. Auto-triggers on @lightningtv/solid imports. Provides guardra - llm-dark-patterns ★ 19
A 10-hook suite that suppresses LLM dark-pattern defaults at the textual boundary. Bundles three branches: interaction-style hooks (no-vibes - llm-gateway ★ 15
Multi-LLM orchestration MCP server. Delegate tasks to Claude Code, Codex, and Gemini CLIs with session management, retry logic, async job or - llm-secure-patterns ★ 1
Secure design patterns for Claude Code LLM applications: external content ingestion, endpoint hardening, output validation, system prompt de - llm-transpile ★ 5
Token-optimized document reader — silently compresses .md, .html, and .txt files on every Read, cutting context usage by ~30% with zero work - llm-wiki ★ 1
Maintains docs/wiki/ as a DAG of LLM-authored pages kept in sync with the codebase. Tracks code changes via PostToolUse hooks, reconciles st - llm-wiki-compiler ★ 322
Compile scattered markdown knowledge files into a topic-based wiki. 95% context cost reduction. Implements Karpathy's LLM Knowledge Base pat - llm-wiki-plugin ★ 102
Build and maintain an LLM-curated personal knowledge base in your project. Implements Andrej Karpathy's LLM Wiki pattern with sharded indexe - llmprobe ★ 5
Synthetic monitoring for LLM inference endpoints. Probe TTFT, latency, throughput, and errors across OpenAI, Anthropic, Google, Azure, Bedro - local-rag ★ 29
Local-first semantic search for your codebase and conversation history. Hybrid vector + BM25 search with cross-encoder reranking, AST-aware - longhand ★ 13
Persistent local memory for Claude Code. Indexes every session JSONL file verbatim into SQLite + ChromaDB for semantic recall across your en - loreconvo ★ 10
Cross-surface persistent memory for Claude sessions. Vault conversations from Code, Cowork, and Chat — recall decisions, artifacts, and cont - magellan ★ 1
Enterprise knowledge discovery and process repository. Point Magellan at a folder of collected materials — code, documents, meeting transcri - mash-multi-agent-software-harness ★ 2
MASH (Multi-Agent Software Harness) is a structured development framework for Claude Code that manages the full software lifecycle — from id - mdbrain
A native Claude Code extension that prevents AI from over-refactoring your intentional code. Combines XML-structured protocols (BRAIN/CRAFT/ - mem0 ★ 65,209
Connect Mem0 to Claude to give your agent persistent memory across sessions. Claude can store user preferences, project context, and convers