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 |
|---|---|---|---|---|
| vectorize-io/agent-memory-benchmark Agent Memory Benchmark | 164 | Claude Code | 1 | 80 tok |
| farukkamcici/mectrics mectrics.app A lightweight, private system monitor that lives in your macOS menu bar. CPU, memory, batt | 161 | Claude Code, Codex, OpenCode | 2 | 7,571 tok |
| RightNow-AI/AutoMegaKernel runinfra.ai An agent harness that compiles a model into one provably-correct, self-retargeting CUDA me | 161 | Claude Code, Codex, OpenCode | 6 | 2,279 tok |
| nanvon/cc-bar Native macOS menu bar AI quota monitor and local usage dashboard. Tracks Codex, Claude Cod | 161 | Claude Code, Codex, OpenCode | 3 | 3,348 tok |
| AgentEvalHQ/AgentEval agenteval.dev AgentEval is the comprehensive .NET toolkit for AI agent evaluation—tool usage validation, | 158 | Claude Code, Codex, GitHub Copilot, OpenCode | 15 | 24,461 tok |
| whanyu1212/gem-dota whanyu1212.github.io Python replay parser for Dota 2 | 157 | Claude Code, Codex, OpenCode | 2 | 10,979 tok |
| Alex8791-cyber/cognithor cognithor.ai Cognithor · Agent OS: Local-first autonomous agent operating system. 19 LLM providers, 18 | 156 | Claude Code, Cursor | 2 | 2,552 tok |
| docglow/docglow docglow.com Modern documentation site generator for dbt Core — lineage explorer, health scoring, full- | 153 | Claude Code | 1 | 1,633 tok |
| kubestellar/console console.kubestellar.io World's first fully integrated and fully Automated Kubernetes management and orchestration | 151 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode | 12 | 9,406 tok |
| bradautomates/content-ideas youtube.com Track competitors across X, Instagram, TikTok, and YouTube, see what they post, what perf | 151 | Claude Code, Codex, OpenCode | 2 | 569 tok |
| PostHog/mcp posthog.com Official PostHog MCP Server 🦔 | 151 | Claude Code | 1 | 1,247 tok |
| dinglebear-ai/unraid Query, monitor, and manage Unraid servers via GraphQL API through MCP tools. Supports syst | 150 | Claude Code, Codex, Gemini CLI, OpenCode | 4 | 1,351 tok |
| disler/pi-agent-observability | 148 | Claude Code | 6 | — |
| zhnd/lumo Local-first dashboard for observing Claude Code usage, cost, sessions, and time. | 147 | Claude Code | 1 | 3,048 tok |
| joa23/linear-cli A token-efficient CLI for Linear | 147 | Claude Code, Codex, OpenCode | 8 | 3,177 tok |
| nansen-ai/nansen-cli | 147 | Claude Code, Codex, OpenCode | 2 | 3,300 tok |
| tobiasosborne/alethfeld Rigorous Proofs via Adversarial AI Agents | 144 | Claude Code, Codex, OpenCode | 13 | 444 tok |
| PatrickSUDO/fadacai-portfolio Claude Code investment research and portfolio management framework: skills + MCP + first-p | 144 | Claude Code, Codex, OpenCode | 17 | 41,212 tok |
| vogler75/monster-mq monstermq.com MonsterMQ is a MQTT broker built on Vert.X and Hazelcast with data persistence through Pos | 143 | Claude Code, Codex, OpenCode | 7 | 4,344 tok |
| openclaw/shellbench huggingface.co The agent benchmark that scores the full stack — harness, config, and model — not just the | 141 | Claude Code, Codex | 2 | — |
| sidequery/sidemantic sidemantic.com The universal metrics layer. Compatible with 15+ formats: Cube, MetricFlow, LookML, Omni, | 139 | Claude Code, Codex, OpenCode | 2 | 1,680 tok |
| psu-efd/pyHMT2D Python Hydraulic Modeling Tools - 2D | 134 | Claude Code, Codex, OpenCode | 11 | 2,924 tok |
| okikusan-public/stock_skills | 133 | Claude Code | 12 | 1,275 tok |
| microsoft/fabric-rti-mcp MCP server for Fabric Real-Time Intelligence (https://aka.ms/fabricrti) supporting tools f | 133 | Claude Code, Codex, GitHub Copilot | 2 | 1,346 tok |
| grafana/agento11y grafana.com Actually Useful Agent Observability | 132 | Claude Code, Codex, OpenCode | 2 | 3,186 tok |
| assafkip/kipi-system Your AI brain, externalized. It remembers everything you do, then becomes whatever role yo | 131 | Claude Code, Codex, OpenCode | 15 | 1,826 tok |
| guhcostan/b3analysis Agente de análise de ações brasileiras (B3) com Claude Code — sem API keys | 131 | Claude Code | 24 | 1,889 tok |
| computesdk/benchmarks computesdk.com Compare performance across sandbox, storage, browsers, and ai gateway providers. | 131 | Claude Code, Codex | 4 | — |
| nickustinov/itsyconnect-macos itsyconnect.com Better App Store Connect | 130 | Claude Code | 1 | 877 tok |
| malloydata/publisher Publisher is the open-source analytics engine for Malloy. It lets you define data models o | 130 | Claude Code, Codex, OpenCode | 4 | 10,157 tok |
| langchain-ai/langsmith-mcp-server langsmith-mcp-server.vercel.app | 130 | Claude Code | 1 | 6,401 tok |
| mxtommy/Kip SignalK Instrument package | 129 | Claude Code, Codex, GitHub Copilot | 11 | 6,085 tok |
| sulaiman013/powerbi-mcp MCP server for natural language interaction with Power BI datasets | 126 | Claude Code, Codex, OpenCode | 2 | 1,738 tok |
| tma1-ai/tma1 tma1.ai Local-first observability your agent reads back. TMA1 records every LLM call, then routes | 124 | Claude Code, Codex, OpenCode | 2 | 2,387 tok |
| githits-com/githits-cli githits.com CLI & MCP for GitHits - The Code Context Layer for AI Coding Agents | 124 | Claude Code, Codex, Gemini CLI, OpenCode | 6 | 3,815 tok |
| rajbos/ai-engineering-fluency marketplace.visualstudio.com Extension that shows information about the estimated token usage and more of AI in editors | 124 | Claude Code, Codex, GitHub Copilot, OpenCode | 48 | 19,124 tok |
| deusXmachina-dev/memorylane trymemorylane.com | 123 | Claude Code, Codex, Cursor, OpenCode | 7 | 1,013 tok |
| revfactory/claude-code-harness | 122 | Claude Code | 4 | — |
| luongnv89/context-stats luongnv.com Understand how you use Claude Code, and spend less doing it. | 118 | Claude Code, Codex, OpenCode | 3 | 4,636 tok |
| fiorastudio/buddy A virtual pet companion for your AI — Designed to provide in-context code review feedback | 118 | Claude Code, Codex | 2 | — |
| androidZzT/cc-statistics AI Coding stats dashboard — track costs, tokens, and efficiency across Claude Code / Gemin | 117 | Claude Code, Codex, OpenCode | 2 | 1,823 tok |
| dreadnode/agent-lens dreadnode.github.io Agent observability and replay tooling for AI safety & interpretability research. | 117 | Claude Code | 2 | 2,762 tok |
| cj-vana/claude-swarm MCP server for orchestrating parallel Claude Code worker swarms with protocol-based behavi | 117 | Claude Code | 1 | 3,967 tok |
| ai-twinkle/Eval twinkleai.tw High-performance LLM evaluation framework with parallel API calls — up to 17× faster than | 117 | Claude Code | 3 | 12,871 tok |
| nexus-labs-automation/mobile-observability Claude Code plugin for mobile app observability: crash reporting, performance monitoring, | 116 | Claude Code | 1 | 510 tok |
| nwiizo/cargo-coupling crates.io A coupling analysis tool for Rust projects - measuring the 'right distance' in your code | 116 | Claude Code, Codex, OpenCode | 21 | 2,432 tok |
| Prism-Shadow/agenthub One interface for 1,000+ LLMs, with zero-code switching and built-in observability. (GPT-6 | 113 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 1,349 tok |
| cisco-foundation-ai/fully-automated-prompt-optimization An self-improvement suite for optimizing chains with Claude Code | 113 | Claude Code, Codex, OpenCode | 12 | 1,537 tok |
| jbarbier/claude-code-cost-estimate Claude Code skill that estimates the full development cost of any codebase | 112 | Claude Code | 1 | — |
| avivsinai/langfuse-mcp A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse t | 112 | Claude Code, Codex, OpenCode | 2 | 872 tok |