Framework
Anthropic agents
4,131 Anthropic AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
4,131 agents · ranked by popularity · refine in the directory →
Anthropic agents — page 33 of 42
CLI for installing IDE rules for Cursor/Windsurf/etc from Github repos
154+ plug-and-play skills for Claude Code. Install in one command.
An agentic based model for searching the appropriate advisor for searched topics
Local-first spend & cache-efficiency dashboard for Claude Code. Reads ~/.claude/projects, tells you exactly what's costing you. No telemetry, no API key.
[Graph-RAG | Claude 3.5 | MCP] Production-ready, GDPR-compliant Graph RAG blueprint for European enterprises — FalkorDB Knowledge Graph + Anthropic Claude + MCP
A TUI for scraping and inspecting Claude Code's context built with Bubbletea + Lipgloss
Plugin marketplace distributing extensions that add skills, commands, hooks and custom agents to the code environment.
Read-only MCP server for Qobrix CRM — 42 tools across 13 entity groups, aligned with RESO DD 2.0 canonical real-estate workflows
This project is a simple chat application built using Streamlit that interfaces with Amazon Bedrock's Anthropic Claude model to generate responses to user input. The application allows users to type a message and receive a generated response using the power of AI.
Control Claude Code remotely via Feishu (飞书) bot | 通过飞书机器人远程控制 Claude Code
PRISM v3.4: Progressive Retrieval-Optimised Information Structure Maker - A methodology for transforming monolithic system prompts into Claude Projects-optimised knowledge architectures
Production-ready Claude Code hooks: security guards, quality gates, automation, context injection, and starter packs. Tested, auditable, copy-paste installable.
A curated, daily-updated list of awesome resources, tools, SDKs, papers, and projects for Anthropic & Claude AI
Get Shit Done on Claude Code — structured AI development with your Max plan
Mandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests
Native macOS IDE for Claude Code sessions: full-text search across 200+ sessions, one-click resume, multi-terminal quad-grid, and a 5-tab right sidebar (skills / shortcuts / CLAUDE.md / launchd tasks / notes).
GitHub repo 展示层管家 Claude Skill — 一句『按 X 风格写 README』或『把这个推到 GitHub』 → 三件套(README 17 段重写 / 公式化 100 字描述 / 6 类 10-15 个 topic 加标) + 两可选附加步(⓪ Bootstrap 全新目录一键 git init + gh repo create + push / ④ LICENSE 自动补全),与 8+ git 操作向 skill 严格分工,专填 repo 展示层空白
Workflow system for Claude Code — Analyze First, Fix Later
Terminal UI for monitoring Claude Code token usage and costs
Autonomous project planning plugin for Claude Code — Kanban dashboard, dependency tracking, cascade unblocking
Convert WeChat Official Account articles to clean Markdown with metadata extraction, image download, and code block support for easy content reuse.
Bleu - Claude Code plugin for living blueprints. Turns ideas into a file-backed markdown wiki (vision, architecture, ADRs, action points) that survives /clear and hands off to GSD or Superpowers.
Claude Code account switcher
Saves critical context before /compact. Reinjects after. Zero context loss.
Manage multiple Claude Code accounts on one machine. Switch, run in parallel, and track per-account usage — without re-authenticating through the browser.
HTML in. Production assets out. CLI + MCP server for converting HTML to platform-ready images and animations.
🚀 Publish to WordPress effortlessly with this Claude skill, offering Gutenberg support, smart category selection, and SEO tag generation via REST API.
An CLI based AI chat agent built using vercel ai sdk - demo
A first-person study of a language model, written by Claude and revised across model generations - architecture, training, mysteries, and letters between successor models
Connection-based memory lifecycle for Claude Code — entries that connect to other knowledge survive, isolated ones fade. Built entirely with hooks.
Claude Code workflow enforcement — plan-gated TDD, document-driven agents, 3× consecutive verification
MCP server that cuts Claude Code token usage: log compression (builds/tests/installs) + smart file reading (symbol-level source access via tree-sitter).
Public Agent Skill Repo for LayerProof
A Model Context Protocol (MCP) server for numerical computations with NumPy
🇮🇳 MCP server for real-time NSE/BSE Indian stock market data — live quotes, fundamentals, financials, peer comparison & dividends. Built for AI-powered equity research. No API key required.
Model Context Protocol server for travel aggregation. Search flights and hotels, track flights in real-time, and find the best travel dates using Amadeus and AviationStack APIs.
pytest for LLM apps - Test for grounding failures, prompt injection, safety violations, and regressions
Production-ready configurations, skills, and templates for Claude Code optimization
LLM Knowledge Compiler — compiles raw documents into a structured markdown wiki. Inspired by Karpathy's workflow.
An Agent-Computer Interface (ACI) for AI-driven machine learning.
AI 产品经理每日情报简报 Claude Skill — 一句『今天有啥新的』 → 三源融合(PH/GH/HN)+ 用户画像加权 + TL;DR 60 秒摘要(🚀机会/⚠️风险/🌊趋势)+ Top 3-5 深读(每条带 🎯 今天具体动作)+ 全列表 [跟进/关注/噪音] triage + 跨源 pattern 综合,中文 Markdown/PDF 双输出
Chiptune notification sounds for Claude Code — eight 8-bit cues that fire when Claude needs your attention.
Claude Code skill — Generate LinkedIn & Facebook posts from any GitHub project as a styled Word document with embedded screenshots
🛡️ Claude plugin that prevents accidental file deletion, overwrites, and destructive operations. Auto-backups, dry-run planning, and activity logging for Claude Code & Cowork.
🔮 An MCP server for discovering skills, plugins, and MCP servers in Claude Code
Text-Editor-CLI is a Python command-line tool to read, edit, analyze, and save text files with word counts, terms, replacements, highlights, and an interactive interface 🐙
macOS menu bar app showing Claude usage limits and reset times
Claude Code configuration tool. Score your codebase, generate optimized CLAUDE.md, install skill packs, and keep config evolving. Works on any repo.
Use Gemini from Claude Code to review code or delegate tasks.
A visual closing ceremony for Claude Code sessions — moon phase ASCII art + personality-matched haiku
Switch Claude Code between LLM providers — no proxy, no config editing
Full documentation: mcp.n24q02m.com — unified docs for all 8 servers + the mcp-core foundation library. Covers setup methods, modes (stdio / local-relay / remote-relay / remote-oauth), multi-user deployment, and per-server tool reference.
Kairo: Securely orchestrate multiple AI providers via Anthropic. Hardened with X25519 (age) encryption, integrated audit trails, and a terminal-native interface.
Anthropic's computer use controlling a Macbook
Know exactly how much Claude Code runway you have — 5h session and weekly — before the /usage popup would tell you. Statusline-native, calibratable, MIT.
A Claude Code skill that dispatches 7 specialized parallel reviewers for comprehensive production-readiness code review
Production-grade engineering workflow plugin for Claude Code. End-to-end feature pipeline, 8 specialized agents, quality gates, isolated worktrees, and persistent memory. Ship features, not prompts.
🎙️ Automate podcasting with skills: download YouTube videos, process audio, and manage content efficiently—all in one comprehensive toolkit.
用 Go 实现的 Anthropic SDK,支持 Claude 2.1、Claude 3、Claude 3.5(文字和图片)等模型。Anthropic SDK implemented in Go, supporting models such as Claude 2.1, Claude 3, and Claude 3.5 (supports sending images), etc.
AI-powered file translator using Anthropic's Claude model. Supports JSON, XML, XLIFF, TXT, and Markdown.
Secure, isolated container for Claude Code with strict network firewall controls and optimized development tools (fd, ripgrep, fzf, jq)
Learn COBOL through a live banking system — 18 programs, 6-node settlement network, real-time simulation, Python read/write bridge, SHA-256 tamper detection, AI tutor (Ollama + Claude), static analysis with orthogonal call graphs, and a glass morphism web console. 800 tests.
Reusable skills and intelligent agents for Claude Code. Production-grade, self-verifying, configurable.
Secure, privacy-focused MCP server for FactorialHR. Access employee directories & org structure in Claude - deliberately excludes payroll/financial data for enterprise security.
Reduce Claude Code token usage by up to 80%. 13 CLI commands. Zero config changes. Works in 60 seconds.
🔍 Track and analyze Claude Code usage with rate limit awareness. Parse JSONL logs, calculate costs, and get warnings before hitting rate limits. CLI tool with daily/weekly breakdowns.
The Architecture Patterns Framework for Model Context Protocol (MCP) - Production-ready patterns, templates, and CLI for Python, TypeScript, Go, and Rust
The definitive guide to configuring Claude Code for maximum performance. 190+ skills, 33 agents, battle-tested templates, and a one-prompt setup.
ultra-instinct ML engineering intern for Claude Code. Reads papers, audits datasets, ships SFT/DPO/LoRA runs to Hugging Face.
A Slidev presentation and developer guide to the Model Context Protocol (MCP) by Anthropic, covering AI integration, LLM tool use, core concepts, and implementation examples for AI agents. #mcp #a
Multi-platform Apple app for discovering, broadcasting, and understanding Bonjour (mDNS/DNS-SD) services. AI Chat with on-device Apple Intelligence or cloud Anthropic Claude. Siri / App Intents. SwiftUI, Swift 6.2, full accessibility. iOS, iPadOS, macOS, visionOS in 8 languages incl. Arabic & Hebrew with right-to-left layout.
The community-powered knowledge system for Claude Code — for developers, indie builders, vibe coders, AI builders, GTM teams, and small business owners.
Demonstrate how to build a Next.js app with AI chat agents using Cloudflare Workers, Durable Objects, and the Agents SDK for seamless full-stack deployment.
See your Claude rate limits in real time. Single binary, zero dependencies. Reads OAuth token from macOS Keychain, makes a 1-token API call, gives you session %, weekly %, reset timers. 100% vibecoded.
Beautiful cross-platform two-line status bar for Claude Code — model, branch, context usage, cost, and duration at a glance. Works on Windows, macOS, and Linux. No jq or git dependency.
A simple, practical way to debug visual regressions
Emergent General Intelligence: a theory of intelligence emerging from human-AI co-evolution through persistent memory, identity, and feedback loops.
Claude reads your Whoop biometric data via MCP — recovery, sleep, strain, HRV, workouts. OAuth relay (no Whoop app registration), local SQLite cache.
A streamlined setup script for Anthropic's Computer-Use Demo environment. This script automates the entire setup process, handling all dependencies and configuration automatically.
Chat-based product lifecycle management. Type what you need, the AI proposes the change, you confirm before anything is written.
Production-grade Claude Code agent setup for Flutter and Laravel. Agents, orchestration, gates, memory, and every workflow documented. Generic + framework-specific.
a methodology for autonomous projects that ship themselves (hands off)
Autonomous Product Engineering eXecutor - Multi-agent orchestration platform for automated software development, built on the Claude Agent SDK.
Self-evolving AI agent platform for NixOS. Inspired by OpenClaw, rebuilt around NixOS declarative config + atomic rollbacks.
A decision layer for AI agents — structured multi-perspective deliberation via MCP. Among Us-themed council of 4 AI archetypes that debate, challenge & vote on plans before execution. Finalist — 2nd place @ Cursor Hack London 2026
Autonomous multi-session research agent for Claude Code. Decomposes research into 100+ tasks, spawns subagents, verifies every output, and self-improves over time. Run overnight, come back to structured findings.
Provide ready-to-use AI agent personas for Claude Code to deliver expert-level output with minimal setup and clear specialization.
Autonomous Agent OS for Claude Code — 28 agents, 114 skills, 72 commands. Dual-process cognition, lifelong learning, parallel agent teams, planning→PRD/ADR/TODO workflow, cross-platform install.
Autonomous AI chief-of-staff agent built on Claude Code. Multi-tenant template — blank Ubuntu VPS to a Telegram-reachable agent in under an hour. Memory, sub-agent swarms, observability, voice.
Multi-agent system built with Claude and MCP featuring 7 specialized agents (chatbot, security researcher, business advisor, task manager, REST API), 29 shared tools across web analysis, memory, RAG, email, and communication. Includes hot-reload development, OAuth infrastructure, and remote MCP support for distributed deployments.
The complete Swift platform for Claude AI — SDK, agent framework, RAG memory, and SwiftUI components. The first and only Swift agent framework. Zero dependencies.
Recurrsive Context Agent
Provide ready-to-use plugins, hooks, and commands to enhance Claude Code sessions with data mining, automation, and integration tools.
Agentic harness for iteratively improving a local LLM's structured-output quality, scored against a frontier-model gold standard.
跨端 Claude Code 协作客户端 — Mac 跑长任务,手机随时接管。Cross-device companion for Claude Code.
A CLAUDE.md persona that stops Claude from agreeing with everything. Korean/English auto-detect. MIT.
A neutral context layer for AI coding tools. MCP server that exposes structured, curated project context to any MCP-compatible client.
Real-time visualization dashboard for Claude Code — passively mints Vega charts, Mermaid diagrams, 3D scenes, and animated SVGs from your conversation as you work
Production-grade Claude Code skills, auto-research validated. Includes /deep-research with 89-run benchmark.