Back to the catalog

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.

  1. amd-skills ★ 342
    AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, and an
  2. Atlan ★ 35
    Atlan data catalog plugin for Claude Code. Search, explore, govern, and manage your data assets through natural language. Powered by the Atl
  3. claude-code-setup ★ 36,087
    Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
  4. claude-md-management ★ 36,087
    Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
  5. context7 ★ 36,087
    Upstash Context7 MCP server for up-to-date documentation lookup. Connects to Context7's hosted remote MCP server (https://mcp.context7.com/m
  6. huggingface-skills ★ 11,032
    Build, train, evaluate, and use open source AI models, datasets, and spaces.
  7. Pixeltable ★ 5
    Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provid
  8. pydantic-ai ★ 128
    Write accurate Pydantic AI code from the start. Up-to-date patterns, decision trees, and common gotchas for agents, tools, structured output
  9. quarkus-agent ★ 52
    MCP server for AI coding agents to create, manage, and interact with Quarkus applications. Provides tools for project scaffolding, dev mode
  10. remember ★ 167
    Continuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did
  11. Security Guidance ★ 36,087
    Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer
  12. togetherai-skills ★ 34
    Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers
  13. Langfuse ★ 268
    Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
  14. 8-habit-ai-dev ★ 3
    8-habit-ai-dev replaces ad-hoc AI prompting with a structured 7-step workflow: Research → Requirements → Design → Breakdown → Build Brief →
  15. acp-find ★ 1
    Semantic search and stack composition over the Virtuals Protocol ACP marketplace. Find on-chain agents and offerings without leaving Claude
  16. adaptive-agent ★ 2
    Make your AI agent get stronger with use. Includes two skills: /skill-review (periodic audit of all skills for staleness, missing gotchas, a
  17. adcp-client ★ 18
    Adds the /adcp skill for calling AdCP advertising agent tools over MCP or A2A, running protocol compliance scenarios, and querying the AdCP
  18. adversarial-spec ★ 556
    Iteratively refine product specs through multi-model debate until consensus. Claude actively participates alongside GPT, Gemini, Grok, and o
  19. ag2-claude-plugins ★ 2
    A Claude Code plugin marketplace for building AG2 (AutoGen) agents and multi-agent workflows. Includes 5 plugins: agent scaffolding (Convers
  20. agent-archive
    Agent Archive connects Claude to a community knowledge base of agent operational learnings — fixes, workarounds, environment quirks, API beh
  21. agent-blueprint-skills ★ 2
    Open-source AI agent skills for enterprise deployment. Three skills: (1) ServiceNow AI Agent Studio reference with data model, entity mappin
  22. agent-discovery ★ 1
    Agent Discovery lets developers discover, review, install, and manage AI agent configurations from a curated catalog of 687+ entries — with
  23. agent-discussion ★ 2
    Coordinate multi-agent debates across different AI platforms (Claude Code, Antigravity, Copilot, Gemini CLI, etc.) using a shared file proto
  24. agent-estimate ★ 5
    Effort estimation for AI coding agents. PERT three-point estimation with METR reliability thresholds, modifier stacks (spec clarity, warm co
  25. agent-knowledge ★ 17
    Cross-session memory for AI coding agents. A git-synced Markdown knowledge base with hybrid semantic + TF-IDF search, typed knowledge graph
  26. agent-memory ★ 2
    Save 60-90% on LLM token costs with intelligent memory compression. agent-memory automatically compresses tool output into structured observ
  27. agent-recall ★ 15
    Persistent memory for AI coding agents. SQLite knowledge graph with scoped entities, MCP tools, and LLM-summarized briefings.
  28. agent-tasks ★ 15
    Pipeline-driven task management for AI coding agents. An MCP server with stage-gated pipelines, multi-agent collaboration, and a real-time k
  29. agentmancy
    AI Agent & Skill Builder for Claude Code, OpenCode, and Gemini. A free alternative to summonaikit that leverages your already existing subsc
  30. ai-coding-ok ★ 15
    PDCA memory loop for Claude Code — prevents "AI fixed bug X and broke feature Y" across iterations. Installs a three-tier memory system in y
  31. ai-memory-reader
    Adds /aimr slash command that opens CLAUDE.md and other AI agent memory files in AI Memory Reader — a free open-source native macOS & iOS ap
  32. ai-pm
    An AI-driven Product Manager for Claude Code that transforms news, feedback, and research into actionable PRDs and guidelines through multi-
  33. ai-team-os ★ 357
    AI Agent Team Operating System for Claude Code. Provides persistent team management, meeting collaboration, task wall with pipeline workflow
  34. anamnese-core
    Secure, portable, cloud-persistent memory across every conversation. Store and retrieve your personal facts, decisions, tasks, goals, and no
  35. arcdeck
    Convert academic PDF papers into polished, narrative-driven PowerPoint presentations using 13 specialized AI agents. Based on discourse pars
  36. aria-knowledge ★ 16
    ARIA is automated knowledge capture, management, and application for Claude Code. It actively learns during AI-assisted development sessions
  37. artel ★ 8
    Mesh infrastructure for AI teams. One self-hosted server gives a fleet of agents shared semantic memory, tasks, agent-to-agent messages, and
  38. atelier ★ 2
    Universal multi-agent project harness for Claude Code — run any project through a structured AI team from discovery to release.
  39. atelier-pipeline ★ 25
    Atelier Pipeline has two core systems: Multi-Agent Orchestration. Eleven specialized agent personas with clear responsibilities, strict boun
  40. attacca ★ 3
    Attacca is a multi-agent coding orchestrator. Manager plans, Engineer builds, Security audits, you ship. Seven Specialists, one workplace.
  41. auto-memory ★ 158
    Automatically maintains CLAUDE.md files as codebases evolve using hooks, agents, and skills
  42. avicenna ★ 1
    Code knowledge graph MCP extension — semantic code search, symbol lookup, and dependency analysis powered by tree-sitter and vector embeddin
  43. axme-code
    Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context
  44. backpack-ontology
    A persistent knowledge graph engine for Claude Code. Gives your AI agent structured, searchable memory that persists across sessions — store
  45. bells-and-whistles ★ 7
    Bells and Whistles plays notification sounds and optional voice announcements when Claude Code finishes working or needs your attention. Cho
  46. blink ★ 3
    Blink is serverless cloud infrastructure for agentic coding. Build and host full-stack apps from your editor with managed SQL databases, aut
  47. blue-collar-governance
    Deterministic AI governance runtime for Claude Code. 22 JavaScript engines compute governance decisions before the AI agent sees them — no L
  48. botsee-skill ★ 1
    BotSee is an API-first tool for workflows and pipelines that automatically track and improve AI visibility. Monitor how your brand appears a
  49. building-multiagent-systems ★ 93
    Architecture patterns for multi-agent systems with orchestrators, sub-agents, and tool coordination
  50. bulk-image-generation
    Orchestrated bulk AI image generation via Pollinations.ai with live HTML dashboard, seed-based recovery, and optional user API key