1,208 projects whose own agent configuration covers analytics and metrics. These are not mods to install — they are how the maintainers of these repositories tell an agent what to do, and what to avoid.
All projects Building agents8,442Claude Code6,875Data and AI3,584Git and workflow3,574Backend and APIs3,550Languages3,468Planning3,315Code review2,876Testing2,653DevOps and cloud2,462Writing and docs2,461Memory and context2,373
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| stoa-platform/stoa gostoa.dev 🏛️ The European Agent Gateway — Open-source MCP Gateway for Enterprise AI | gostoa.dev | 9 | Claude Code, Codex, OpenCode | 40 | 3,981 tok |
| dodobrands/ai-hub | 9 | Claude Code, Codex, OpenCode | 25 | 2,848 tok |
| cyanheads/eurostat-mcp-server npmjs.com Search and query the Eurostat catalogue — EU economy, demography, trade, health, and NUTS | 9 | Claude Code, Codex, OpenCode | 2 | 14,528 tok |
| ken-jo/agent-connector agent-connector.ai Deploy one MCP to every agent host. Declare your MCP server once with defineConnector() → | 8 | Claude Code | 1 | — |
| yideng-xl/gemini-cli-hud Real-time bottom-sticky HUD for Gemini CLI — model, context usage, tool calls, and more | 8 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 421 tok |
| brendadeeznuts1111/betting-brain-v3 🧠 Edge-native betting intelligence platform with MCP server, real-time analytics, and AI- | 8 | Claude Code, Cursor | 2 | 6,708 tok |
| haenara-shin/codex-hud Claude Code plugin that displays OpenAI Codex usage and rate limits | 8 | Claude Code | 1 | 477 tok |
| feiphoon/pydata-london-2026-mcp-server-tracing-with-open-telemetry | 8 | Claude Code, Codex, OpenCode | 2 | 1,177 tok |
| Bobby-cell-commits/open-brain-server Self-hostable MCP memory server for AI assistants — 16 tools, hybrid search, knowledge gra | 8 | Claude Code | 4 | 969 tok |
| redwoodmeridian/nexus-for-meta redwoodmeridian.github.io Connect your Facebook Ads, Pages, Instagram and lead forms to Claude Code. Ask about spend | 8 | Claude Code | 1 | 1,068 tok |
| V-Songbird/razor YAGNI checks for Claude Code and Codex: reconsider dependencies, file growth and unnecessa | 8 | Claude Code, Codex, OpenCode | 2 | 1,232 tok |
| johnib/kusto-mcp MCP server for Azure Data Explorer (Kusto), enabling AI agents to explore, query, and unde | 8 | Claude Code | 2 | 1,118 tok |
| cekura-ai/cekura-skills Claude Plug-Ins & Skills for Cekura | 8 | Claude Code, Gemini CLI | 2 | 16,084 tok |
| BENZEMA216/music-analyzer Claude Code plugin — analyze audio files, extract musical features, generate Dreamina prom | 8 | Claude Code | 10 | 632 tok |
| essentialproject/essential-view-builder-mcp This MCP (Model Context Protocol) server provides tools and resources for building high-qu | 8 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 373 tok |
| ChainBench/OpenChainBench openchainbench.com Open, reproducible benchmarks for crypto infrastructure: aggregators, bridges, blockcha | 8 | Claude Code, Codex, OpenCode | 3 | 472 tok |
| MetriLLM/metrillm metrillm.dev Benchmark local LLM models: speed, quality, and hardware fitness scoring. CLI, MCP server, | 8 | Claude Code, Codex, OpenCode | 2 | 2,834 tok |
| Aero25x/ASO-Copilot persocia.com Self-hosted App Store Optimization tracker with keyword rank tracking, competitor spying, | 8 | Claude Code, Codex, OpenCode | 2 | 79 tok |
| malda231125/TradingAgents-KR Korea-market multi-agent equity research framework (KOSPI/KOSDAQ) — CLI-first LLM executio | 8 | Claude Code, Codex | 2 | 1,553 tok |
| tardigrde/obsidian-agentic-chat tardigrde.github.io Agent-led AI chat in the Obsidian sidebar - typed tool-calling agent, OpenRouter ZDR by de | 8 | Claude Code, Codex, OpenCode | 12 | 1,653 tok |
| Neetx/ai-security-research-radar AI Security Research Radar — AI for security and security for AI | 8 | Claude Code, Codex, OpenCode | 14 | 3,004 tok |
| dengxuhui/igpsport-mcp pypi.org A local MCP server that brings iGPSport cycling data into LLM clients, with training metri | 8 | Claude Code | 1 | 2,436 tok |
| Jwrede/llmprobe bench.jonathanwrede.de Synthetic monitoring and CI smoke tests for LLM inference endpoints. | 8 | Claude Code | 1 | — |
| spy007111/Vibe-Research Personal AI investment research dashboard for Chinese, US, and Hong Kong stocks — with mob | 8 | Claude Code, Codex, OpenCode | 8 | 4,457 tok |
| VirtueSecurity/VirtueWebAgent | 8 | Claude Code | 11 | 1,716 tok |
| condevtools/pr-agent pr-agent.condevtools.com AI-powered code review bot for GitHub — supports OpenAI-compatible providers. Built with T | 7 | Claude Code | 2 | — |
| PierreJanineh/TechDebtMCP pierrejanineh.github.io MCP server for analyzing and managing technical debt in codebases via the Model Context Pr | 7 | Claude Code, GitHub Copilot | 7 | 8,684 tok |
| altmetric/altmetric-mcp MCP server for Altmetric APIs - retrieve citation metrics and research output data for AI | 7 | Claude Code, Codex, OpenCode | 2 | 3,594 tok |
| bntvllnt/codebase-intelligence npmjs.com CLI-first TypeScript codebase analysis with hotspots, impact, dead-export detection, and a | 7 | Claude Code, Codex, OpenCode | 2 | 3,174 tok |
| Zenobia000/ai-agentic-coding-template_unified | 7 | Claude Code | 9 | — |
| nexus-labs-automation/agent-observability Claude Code plugin for AI agent observability - LLM tracing, tool calls, multi-agent coord | 7 | Claude Code | 1 | 1,309 tok |
| bpinheiroms/claude-office A Claude Code statusline plugin that shows plan quota, real-time costs, and monthly saving | 7 | Claude Code | 1 | 2,420 tok |
| pyang2045/twsemcp MCP server for Taiwan Stock Exchange (TWSE) - Access real-time market data, financial repo | 7 | Claude Code | 1 | 1,041 tok |
| richfrem/agent-plugins-skills Agentic OS Control Plane: deterministic state-machine governance for AI coding agents with | 7 | Claude Code, Codex, OpenCode | 2 | 2,061 tok |
| ThoTischner/observability-mcp npmjs.com Unified observability gateway for AI agents — one MCP server for Prometheus, Loki, and any | 7 | Claude Code | 1 | 1,961 tok |
| debugbundle/debugbundle debugbundle.com DebugBundle product source and runtime code. | 7 | Claude Code, Codex, OpenCode | 7 | 3,452 tok |
| PlunderStruck/scip-query npmjs.com Evidence and verification for AI coding agents: map code, reuse concepts, finish migration | 7 | Claude Code, Codex, OpenCode | 4 | 720 tok |
| Jcstack/ashare-ai-analyst LLM-powered A-share (Chinese stock) market analysis platform — technical analysis, predict | 7 | Claude Code | 5 | 966 tok |
| steven-jzt/MCM-AI-Assistant An AI assistant system for mathematical modeling competitions based on Claude Code + DeepS | 7 | Claude Code | 6 | 381 tok |
| robomoto/agent-system A framework for building specialist Claude agents that delegate work through a team lead, | 7 | Claude Code | 44 | 2,933 tok |
| DuqueOM/ML-MLOps-Portfolio Production-grade MLOps platform: 3 end-to-end ML projects with CI/CD, Terraform (GCP GKE) | 7 | Claude Code, Codex, OpenCode | 17 | 8,452 tok |
| LongLeo287/seosona-flow seosona-flow.vercel.app SEOSONA Flow — Chrome MV3 extension tự động hoá tạo ảnh/video AI (Google Flow, ChatGPT, Ge | 7 | Claude Code, Codex, OpenCode | 21 | 284 tok |
| vikrantd/TLDRGraph vikrantd.github.io Dynamic Multi-Layer Code Flow, Instant Semantic Call Tracing, and Interactive Architectura | 7 | Claude Code, Codex, OpenCode | 4 | 352 tok |
| kelesmert/turnlens npmjs.com Per-turn token and cost monitoring for Codex and Claude Code. | 7 | Claude Code, Codex, OpenCode | 8 | 2,064 tok |
| snyk-labs/snyk-vulnbench vulnbench.com A benchmark harness for measuring how AI coding agents find and fix security vulnerabiliti | 7 | Claude Code, Codex, OpenCode | 12 | 3,693 tok |
| DYAI2025/Plumbline dyai2025.github.io Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. | 6 | Claude Code | 7 | 12,434 tok |
| aweussom/claude-code-quota Claude Code OAuth quota in your status line — Windows (PowerShell) and Linux (or WSL2) | 6 | Claude Code | 1 | 3,360 tok |
| patrykkopycinski/elastic-cursor-plugin | 6 | Claude Code, Cursor | 26 | — |
| srbryers/slope SLOPE — Sprint Lifecycle & Operational Performance Engine. Golf-metaphor sprint scoring fo | 6 | Claude Code, Codex, Cursor, OpenCode | 10 | 5,072 tok |
| GMIG/laborant-skills Laborant is an agent skills that allows you to design and check evaluations for LLM, agent | 6 | Claude Code, Codex | 2 | — |