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 28 of 42
LLM-driven financial sandbox town · NPCs gossip, form opinions, trade · Built with FastAPI + Anthropic + Godot 4.5
Autonomous Terraform agent — takes a prompt or Jira ticket, runs a full validation pipeline, and opens a GitHub PR. No human in the loop.
GitHub Action: Auto-generate CLAUDE.md governance files for Claude Code projects. Detects tech stack, frameworks, and tools.
Daily curated news digest for your domain. Claude Code plugin. Zero API keys, fully local.
Document-based project control for AI-human collaboration. A Claude Code skill that lets any agent resume work from files alone — no external memory needed. Tracks progress across sessions, detects interrupted phase transitions, coordinates multiple projects via file-based inbox/outbox.
A Claude Code plugin that transforms business plans into production-ready products through Plan Casting — a 25-stage AI agent pipeline. Try the Transmuter app at transmuter.3mergen.com
Bio-inspired swarm orchestrator for Claude Code. 16 mechanisms from honeybee and ant colony research, 148 algorithmic tests. One file, zero dependencies.
Code Intelligence: Token-budgeted codebase context for Elixir agents. Solves context window limitations by providing a deterministic Elixir semantic graph and agent-ready Repo Map for LLMs.
Controlled rolling-context conversation runtime for Claude. Stop your agent from running away with your bill.
Local-first, open-source alternative to Anthropic's Claude Design. MIT-licensed, BYO agent CLI — Claude Code, Kimi, Codex, or any SDK-compatible model. Composable skills · three edit paths · designs as plain HTML/JSX/CSS folders · run locally, no cloud round-trip. Generate banners, thumbnails, websites, animations, design systems.
UFC-style visual arena where two AI agents compete on coding tasks. Electron + React + pixel art fighters.
See everything Claude Code knows — projects, MCP servers, sessions, costs — in one dashboard
A minimal, fully commented Python executive AI agent. For students, teachers and junior devs who want to understand agentic AI from the ground up.
AI RAG agent that reads company documents and answers questions like a trusted senior colleague. Built with Claude API, FastAPI, React, ChromaDB.
Zero-stop autonomous spec → PR pipeline for Claude Code. Subagent orchestration, adaptive scoring, and metacognitive learning via MCP.
Governance infrastructure for Claude Code — hooks, agents, and workflows that prevent the failure modes autonomous coding sessions actually hit
CAST observability UI — React 19 + Express dashboard for cast.db session analytics, agent runs, and hooks
🛠️ Build and customize Claude Code agents with tools and Docker isolation for efficient production workflows and advanced reasoning capabilities.
Production middleware for MCP servers. Auth, sessions, health checks, graceful shutdown, transport ergonomics. Wraps the official Model Context Protocol SDK.
Forge: Empirically-validated multi-agent orchestration engine. Auto-designs swarms, guarantees interface alignment through contracts (+52.5% quality, 400+ experiments), real-time zero-dep monitoring dashboard. The first system combining auto-design + contract-first + live dashboard.
Claude-powered Slack bot for multi-project dev automation. Each channel gets its own AI agent with codebase context. Quick Q&A, full coding sessions, GitHub issues, peer review, and App Store Connect monitoring — all from Slack.
A 7-perspective Agent Team for Claude Code: parallel multi-agent product research, cross-validated, delivered as HTML + Markdown + Notion.
OPUS — bio-inspired multi-agent swarm architecture for collective LLM reasoning. Open-source. Ars Magna.
Bench is a constitutional governance layer for Claude Code
Multi-agent orchestrator for Claude Code. Spawn, coordinate and monitor AI agents in parallel — no API key required.
Long-running AI agents that adapt until outcomes converge.
Open-source AI assistant with persistent memory, self-evolution, and proactive monitoring. Built with Next.js, FastAPI, LangGraph, and Claude. Your data stays on your machine.
Merkle-enhanced codebase mapping for AI agents. O(1) change detection, zero-token staleness prevention.
🚀 Build and utilize production-ready Claude Code agents and skills for enhanced productivity with auto-generated documentation.
🛠️ Build resilient agentic applications with AI-driven personas that guide you from concept to production in Claude Code.
75 skills, 14 agents, 15 commands for Claude Code. Plug-and-play starter kit covering TypeScript, Python, Go, Rust, React, Next.js, FastAPI, Django, Docker, CI/CD, security, testing, and more. Cross-AI support for Cursor, Copilot, and Codex.
🔥 MCP (Model Context Protocol) server for Ember.js CLI - AI-powered assistance for Ember development with Claude, ChatGPT, and other LLMs
Universal AI agent skills for Go, Kubernetes, GitOps
Rook — your strategic AI advantage. Open-source personal assistant in Telegram.
Your sonic companion, inspired by youtu.be/XPM1o9QKw1Q
ESP32-S3-BOX desk monitor for Claude Code API usage - polls Anthropic rate-limit headers over WiFi, no host daemon
Turn your repetitive Claude Code workflows into reusable skills — automatically. Zero config, zero dependencies.
AI-powered toolkit for Claude Code that provides structured workflows, commands, and agents to automate planning, coding, testing, and shipping software.
Official MCP server for ipgeolocation.io. IP geolocation, VPN/proxy detection, timezone, astronomy, ASN, and user-agent parsing for Claude, Cursor, Copilot, and other MCP clients.
Daily self-improvement loop — scans configured sources for new patterns, diffs against your current setup, implements quick wins, writes a dated report. Originally a Claude Code skill, now config-driven for any ecosystem.
RASS (retreival augmented simple syndication): MCP tools for RSS feeds and agentic RSS feed reader demo.
A minimal Python tool to monitor multiple log files simultaneously in a single terminal window via tail. With Claude Code integration to automatically discover relevant log files from your recent experiments.
High-performance MCP server for log analysis. Give Claude the ability to analyze massive log files with SIMD-accelerated parsing. 5-50x faster than awk for aggregations.
A curated collection of 47 custom slash commands for Claude Code. Code review, security audits, architecture design, DevOps, and workflow automation — organized into 7 categories. Built for .NET/Blazor/TypeScript stacks, easily adaptable to any.
A unified MCP server that aggregates 32 sports API providers into a single service. 336 tools covering scores, stats, odds, esports, college sports, chess, AFL, and more across 70+ sports.
Claude Code skill synthesized from 200+ episodes of 20VC — 13 frameworks for founders, operators & investors
Describe any task in natural language — OmniDrive analyzes intent, installs dependencies, and executes automatically.
See How Big Exactly A 128k Token Text Is
VS Code extension that shows Claude AI subscription usage (daily & weekly limits) in the status bar. Auto-detects Claude Code credentials. Supports OAuth and enterprise admin keys.
Statusline framework for Claude Code with live context, spend, CI, and runtime signals.
claude46 launcher for Claude Code: keep using Claude Opus 4.6 / claude-opus-4-6[1m] after Opus 4.7 updates. macOS, Linux, WSL, and native Windows.
Modular development framework with multi-vault secrets, Claude Code integration, extensible hooks, and health checks.
Roast any developer's public GitHub in the voice of Linus Torvalds, Steve Jobs, Bill Gates, John Carmack + 4 other tech icons. Pure satire. Public data only. 🔥
Turn your MacBook notch into a live Claude AI usage monitor — Dynamic Island-style, native Swift, zero telemetry.
MCP server for AI-powered travel search — flights, hotels, weather as MCP tools with MongoDB-backed per-tool TTL caching tuned to each upstream API. Architecture: tanayshah.dev/projects/travel-mcp-server
MCP server that gives LLMs web search, intelligent article extraction, PDF parsing, and contextual awareness (datetime/geolocation) - zero setup, no API keys.
MCP server that lets Claude Desktop and Claude Code pass messages without copy-paste
Hand off your Claude Code session from terminal to phone (and back) without losing context
A Claude Code skill for crafting portfolio-ready design case studies. Structured template, tone guide, and slide layout for UX, product, and design portfolios.
Opinionated Claude Code skills for project bootstrap, persistent session memory, and multi-model code review (Claude + Codex).
Claude Code plugins — MCP servers, skills, and agents for AI-assisted development
Claude Code skill that invisibly rates every external resource (WebFetch / WebSearch / MCP / curl) via PostToolUse hooks. Two rater backends: Anthropic API key or claude.ai subscription via 'claude -p'.
A complete, weekly-operable system covering research findings, funnel design, networking workflows, application protocols, AI automation, templates, and a 30-day launch plan. No spam. No fake experience. High-conversion by design.
Translate PowerPoint files across 7 languages while keeping every font, color, and layout exactly as designed.
🪂 Latency-aware model cascade for agentic LLM workflows. Auto-switches to a faster model when yours is slow.
Test Claude Projects without copy-pasting. Local workbench for prompt engineering, agent testing, and workflow iteration. Direct Claude.ai access via cookie auth, 20+ prompt templates, web fetch/search tools, file uploads. Stop switching tabs to test your prompts.
Sweep your ~/.claude/skills graveyard. Scans installed skills, MCP servers, and sub-agents, cross-references session logs, and shows what's actually used.
Local-first job hunt workflow on Claude Code: 4-version LaTeX CV + AI cover letters + Claude in Chrome auto-apply. No SaaS, no subscriptions, no black-box agents.
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows | Claude Skills 精选列表:定制 Claude AI 工作流的技能、资源和工具合集
LLM Choose your own Adventure API using Rust & Htmx (HuggingFace models or Anthropic)
🛠️ Manage AI capabilities with CraftDesk, a streamlined package manager for installing and versioning Claude Code skills and development tools.
Production-extracted architecture for Claude Code CLI. 3-layer system: CLAUDE.md constitution + specialist Skills + persistent Memory. Rules from mistakes, not pre-optimization.
MCP server for authoring Maltego .mtgx graphs and running primitive OSINT lookups (whois/DNS/ASN/crt.sh). Composes with misp-mcp, thehive-mcp, and other security MCPs.
Multi-session orchestration for Claude Code. Monitor, auto-approve, block, and send tasks across terminals.
Claude Code Wrapped (Unofficial) - your year in code, visualized
Multi-model Telegram bot (aiogram v3) with OpenRouter model picker (Llama, DeepSeek, Claude, Grok). FSM, async processing, HTML rendering, anti-flood.
AI-powered WSQ courseware generation platform built with Claude Agent SDK and Streamlit. Automates creation of Assessment Plans, Facilitator Guides, Learner Guides, Lesson Plans, Assessments, Slides, and Brochures for Singapore training providers.
AI-powered LinkedIn post generator for Claude Code. Reads your live profile, researches top posts in your industry, suggests topic ideas, and writes in your exact style. Tracks post performance over time.
Learn something while your AI thinks - ambient microlearning in your terminal.
🦞 One-command deployment of OpenClaw on AWS with automatic HTTPS, SSL certificates, Route53 DNS, encrypted S3 backups, and security hardening. Ready for production use.
Practical guide to Claude Code features & workflow — prioritized setup checklist with real-world examples (EN + RU)
Claude Code 多模型协作的 SESSION_ID 自动管理工具。通过 PreToolUse hooks /skill 在每次 MCP 调用前注入会话状态,防止跨任务上下文丢失和会话混乱
A GoLang Wrapper for Anthropic's Claude 3 'Opus', 'Sonnet' & 'Haiku' large language models.
MediTech is an innovative AI-driven Electronic Medical Record (EMR) system designed to streamline and enhance clinical documentation for medical professionals.
Real-time spending alerts for Claude Code — budget limits, loop detection, context warnings, and plan cost estimation. Works in CLI, VS Code, Cursor, and JetBrains.
Claude Code statusline — subscription usage (5h/7d), git branch, context window, last prompt
Open-source marketplace for Claude Code plugins. Publish in 2 HTTP requests, earn 80% in USDC. Install: /plugin marketplace add techgangboss/agentstore
Read-only MCP server for cross-platform screenshots, OCR, and screen-change detection.
Role-based AI marketing copilot for Claude Code. Clone, run /start-copilot, and the wizard fetches your site, builds your brand doctrine, wires your tools, and hands you a ready-to-use copilot. Sonnet 4.6.
WCAG 2.1 accessibility agent built on Anthropic API. Audits, evaluates and fixes digital products for UX, UI and development teams. Includes an installable Skill for Claude.ai and a full CLI with PDF/DOCX export.
TUI for managing Claude Code plugins, MCP servers, agents, skills, and commands
Fluffy desktop cat that eats your Claude Code tokens. macOS 13+, SwiftUI, zero deps.
opencode mac utility
A panel of AI personas that debate your decisions inside Claude Code. 3 rounds, one user-centric synthesis, full debate recorded to a markdown file.
A practical guide to saving money and avoiding limits on Claude for developers and consumer users
Community binary patches for Claude Code CLI — unlock hard-coded limitations via Agent Skills
Claude API 智能转发代理桌面应用 - 多端点负载均衡、自动故障转移、实时使用统计
A TypeScript-based autonomous agent framework with modular systems for memory, planning, and tool integration. Features vector-based recall, multi-strategy planning, and extensible tools for AI agent development.
Tiered memory for AI — episodes, facts, preferences, reflections. Local. Portable. Yours.