688 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 agents7,374Claude Code6,573Data and AI3,706Backend and APIs3,486Languages3,398Planning3,181Git and workflow3,100Code review2,701Memory and context2,354Testing2,311Research2,292DevOps and cloud2,282
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| martinambrus/claude_timings_wrapper Tracks idle, typing, and agent work time across Claude Code sessions using PTY wrapping an | 10 | Claude Code, Codex, OpenCode | 2 | 343 tok |
| aws-samples/sample-claude-code-multi-model Run Claude Code with any foundation model on Amazon Bedrock (43 models) or a self-hosted m | 10 | Claude Code, Codex, OpenCode | 6 | 527 tok |
| superduck-ai/open-managed-agents Open Source version of Claude Managed Agents. Anthropic SDK compatible. Supports agents, | 10 | Claude Code, Codex, OpenCode | 3 | 6,363 tok |
| jeremylongshore/perception-with-intent perception-with-intent.web.app AI-powered news intelligence with 8 Vertex AI agents monitoring 50+ sources. Real-time exe | 10 | Claude Code, Codex, OpenCode | 2 | 3,243 tok |
| shan8851/hermes-console Local-first web dashboard for Hermes Agent — runtime health, sessions, cron, skills, memor | 10 | Codex, OpenCode | 1 | 534 tok |
| cyberia-temple/singularity cyberia.church Open-source Cyberia stack: EVM L1, bridge, DEX, launchpad, analytics, explorer config, and | 10 | Claude Code, Codex, OpenCode | 2 | 35,752 tok |
| 82deutschmark/arc-explainer arc.markbarney.net ARC-AGI Prize Explainer (Includes ARC-AGI-3!) | 10 | Claude Code, Codex, OpenCode | 10 | 10,831 tok |
| chrisLoweDev/AthleteOS Claude code powered personal trainer to plan, and reflect on workouts for the week | 10 | Claude Code, Codex, OpenCode | 13 | 8,311 tok |
| konflux-ci/konflux-devlake-mcp MCP server that bridges AI assistants with DevLake databases for natural language data que | 10 | Claude Code, Codex, Cursor, OpenCode | 3 | 3,636 tok |
| Aether-Grid/openticker openticker.com OpenTicker is a multi-crate Rust workspace for configurable spot-trading across equities a | 10 | Codex, OpenCode | 1 | 1,204 tok |
| google/chrome-enterprise-premium-mcp chromeenterprise.google Reference implementation for a Chrome Enterprise Premium MCP server | 10 | Codex, Gemini CLI, OpenCode | 2 | 1,021 tok |
| pa-arth/cc-audit promptster.ai Local-first CLI that audits Claude Code transcripts for spend by model, avoidable context- | 9 | Claude Code, Codex | 1 | 2,869 tok |
| wandb/weave-claude-code Claude Code plugin that traces sessions, tool calls, and subagents to W&B Weave for observ | 9 | Claude Code, Codex, OpenCode | 2 | 1,141 tok |
| lim5max/poolstatis poolstatis.xyz Agent-native product analytics for coding agents | 9 | Claude Code, Codex, OpenCode | 6 | 4,612 tok |
| dmitryprg-ai/cursor-develop-autorules | 9 | Claude Code, Codex, Cursor, OpenCode | 28 | 2,082 tok |
| 100yenadmin/boardstate 100yenadmin.github.io Your dashboard is data. Any AI can build it; any human can edit it. A protocol + runtime f | 9 | Claude Code, Codex, OpenCode | 3 | 2,557 tok |
| smithersai/webui smithers.sh A skill + CLI that lets agents render React + MDX in a browser window — for plans, diffs, | 9 | Codex, OpenCode | 1 | 828 tok |
| kpbray/power-bi-agent-skills A comprehensive set of agent skills excellent at creating Power BI reports in PBIP format, | 9 | Claude Code, Codex | 10 | — |
| Avierovich/openpitch avierovich.github.io Open, real-time, fully-sourced intelligence on AI startups — MCP-native, zero-cost. A free | 8 | Claude Code, Codex, OpenCode | 3 | 4,511 tok |
| 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 |
| haenara-shin/codex-hud Claude Code plugin that displays OpenAI Codex usage and rate limits | 8 | Claude Code, Codex | 1 | 477 tok |
| EricAndrechek/Pacer ericandrechek.github.io Native macOS app for tracking Claude Code usage — tokens, cost, rate-limit pacing, per-pro | 8 | Claude Code, Codex, OpenCode | 2 | 10,285 tok |
| feiphoon/pydata-london-2026-mcp-server-tracing-with-open-telemetry | 8 | Claude Code, Codex, OpenCode | 2 | 1,177 tok |
| TomMaSS/PRDforge AI-powered Product Requirements Document manager — MCP server, Next.js dashboard, Claude c | 8 | Codex, OpenCode | 1 | 5,161 tok |
| IngTian/witness Turns any text stream into a dated history of how its subject changed. Point it at your Cl | 8 | Claude Code, Codex, OpenCode | 2 | 2,013 tok |
| organvm-iii-ergon/public-record-data-scrapper organvm-iii-ergon.github.io 50-state UCC public-records intelligence — fresh, enriched, scored MCA / financing leads v | 8 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 6 | 7,756 tok |
| altmetric/altmetric-mcp MCP server for Altmetric APIs - retrieve citation metrics and research output data for AI | 7 | Claude Code, Codex, OpenCode | 2 | 3,292 tok |
| hellogxp/skill-runtime-intelligence Evidence-graded runtime panorama and diagnosis for Agent Skills | 7 | Codex, OpenCode | 1 | 270 tok |
| odrasile/ai-usage-widget odrasile.github.io Floating desktop widget for monitoring local AI coding CLI usage across Codex, Claude Code | 7 | Codex, OpenCode | 1 | 1,575 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 |
| PiwikPRO/mcp Piwik PRO MCP server | 7 | Codex, OpenCode | 1 | 828 tok |
| bcharleson/smartlead-cli CLI and MCP server for the Smartlead.ai API — 142 commands for campaigns, leads, email acc | 7 | Codex, OpenCode | 1 | 2,096 tok |
| KyaniteLabs/Epoch kyanitelabs.github.io Time estimation MCP server for AI agents: PERT, COCOMO II, Monte Carlo, sprint forecasting | 7 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode | 4 | 1,957 tok |
| ChainBench/OpenChainBench openchainbench.com Open, reproducible benchmarks for crypto infrastructure: aggregators, bridges, blockcha | 7 | Claude Code, Codex, OpenCode | 3 | 472 tok |
| MetriLLM/metrillm metrillm.dev Benchmark local LLM models: speed, quality, and hardware fitness scoring. CLI, MCP server, | 7 | Claude Code, Codex, OpenCode | 2 | 2,834 tok |
| SunrisesIllNeverSee/sigrank-app signalaf.com SigRank SignalAF — AI operator evaluation leaderboard. Ranks how efficiently you use AI by | 6 | Claude Code, Codex, OpenCode | 4 | 3,652 tok |
| debugbundle/debugbundle debugbundle.com DebugBundle product source and runtime code. | 6 | Claude Code, Codex, OpenCode | 7 | 2,890 tok |
| softcane/codex-blackbox Codex CLI session supervision: see failed or incomplete turns, token use, model changes, c | 6 | Codex, OpenCode | 1 | 1,559 tok |
| wei-b0/codexbar-lite getcodexbar.xyz A tiny native macOS menu bar app for monitoring Codex usage - no browser extensions, no Ch | 6 | Codex, OpenCode | 1 | 914 tok |
| FavioVazquez/mollify Deterministic codebase intelligence for Python | 6 | Claude Code, Codex, Cursor, Gemini CLI, OpenCode | 24 | 4,352 tok |
| srbryers/slope SLOPE — Sprint Lifecycle & Operational Performance Engine. Golf-metaphor sprint scoring fo | 6 | Claude Code, Codex, Cursor, OpenCode | 11 | 4,052 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 | — |
| essentialproject/essential-view-builder-mcp This MCP (Model Context Protocol) server provides tools and resources for building high-qu | 6 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 373 tok |
| chadru/assessor-lookup-public API-first county assessor record lookup, MLS discrepancy checks, and a local MCP server fo | 6 | Claude Code, Codex, OpenCode | 9 | 7,714 tok |
| SRX9/UsageAtlas usageatlas.com Track all your AI coding usage and limits, Claude Code, Codex, Cursor, OpenCode and more. | 6 | Codex, OpenCode | 1 | 41 tok |
| mgh3326/auto_trader LLM agent trades KR/US stocks & crypto behind a deterministic safety layer — approval gate | 6 | Claude Code, Codex, Gemini CLI, OpenCode | 6 | 24,471 tok |
| PlunderStruck/scip-query npmjs.com Evidence and verification for AI coding agents: map code, reuse concepts, finish migration | 6 | Claude Code, Codex, OpenCode | 4 | 2,131 tok |
| dodobrands/ai-hub | 6 | Claude Code, Codex, OpenCode | 25 | 2,512 tok |
| malda231125/TradingAgents-KR Korea-market multi-agent equity research framework (KOSPI/KOSDAQ) — CLI-first LLM executio | 6 | Claude Code, Codex | 2 | 1,553 tok |
| maelrx/Zugzwang Pushing general-purpose LLMs to their chess limits — no fine-tuning, no specialized models | 6 | Claude Code, Codex, OpenCode | 21 | 1,161 tok |