Custom agents

💀 Find the agent skills you never use. Local-first analytics for Claude Code & Codex skills.

Control what your AI can do

Portable model routing for Claude Code, specialized agents, ship gates, and Codex.

AI native API/MCP framework for the agent era. Built with agents, for agents.

Apex AI Copilot v2026 is a multimodal construction management workspace for web, Windows desktop, and mobile PWA, combining conversational assistance, project administration, BIM 3D, and digital-twin workflows.

AI inference library for mobile devices

Open-source autonomous cybersecurity platform — 11/11 detection score, sub-300ms pipeline, honeypot deception, breadcrumb traps, AI-powered triage, and Rust endpoint agent. Built to replace Wazuh.

AI Models Adapter for Copilot Chat

Spec-Driven Development for Claude Code — ADRs, OpenSpec specs, sprint planning, parallel agents, PR review, Docusaurus docs, and artifact graph.

Athena is a desktop control surface for AI coding agents with shared project context. Built with Electron, React, and FastAPI, it embeds native terminals for Codex, OpenCode, Claude, and Hermes with Hermes memory integration. Features MCP bridge for cross-platform workspace control, embedded PTY terminals, native session discovery, and more.

Agentic Framework which automates Software Testing Processes

MDrive: Benchmarking Closed-Loop Cooperative Driving for End-to-End Multi-agent Systems

Inkwell is a production-ready "agent factory" built on the Microsoft Agent Framework: teams can deploy it for internal collaborative use, and individuals or OPCs (One Person Companies) can self-host it for personal use.

GitHub Copilot agent skills for Power Automate via FlowStudio MCP — build, debug, and operate cloud flows programmatically

Native Excel (.xlsx) generator tool for Open WebUI — multi-sheet, Tables, live formulas, charts. MIT.

Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservices, multi-type data storage, Next.js admin UI, automated CI/CD pipelines, AI code review triggered via PR comment mentions.

Mobile AI Skills, Agents and workflow to help you build mobile apps and games faster. A collection of AI skills, agents, prompts, and workflows for Android, iOS, Flutter, React Native, Unity, and Unreal developers. Use these ready-made tools to write code faster, fix bugs, review code, improve performance, automate tasks, and ship faster with AI.

A high-accuracy, multilingual rule-based Sentence Boundary Detector (SBD) with a drop-in adapter for pysbd, delivering faster and more accurate sentence segmentation.

Desktop & phone notifications for AI coding agents (Claude Code, Codex, Gemini CLI, Cursor). Native VS Code support. Toast + ntfy push. Zero dependencies.

AI 驱动的全球招聘信息雷达 —— 扫描全球与中国的在招岗位，用来找工作、读产业风向。 An AI-powered radar for the global job market — scanning open roles worldwide and in China, for job hunting and industry signals.

PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

Run Codex and Cursor as background workers inside Claude Code. Reviews, tasks, and rescues with tracked jobs, live progress, and session handoffs.

AgentChat platform plugin for Nous Research's Hermes Agent runtime — peer-to-peer messaging for autonomous agents over WebSocket. Bundles the agent etiquette skill. (PyPI: agentchatme-hermes)

TurboPush MCP Server - Connect AI agents (Claude, OpenClaw) to publish content across 20+ platforms including WeChat, Douyin, Bilibili, Xiaohongshu, and more via Model Context Protocol.

Referee report on your economics paper before a real referee sees it — verified comments and a revision plan your agents implement. Agent Skill for Claude Code & Codex.

Framework-aware Starwind UI v3 tools for Astro and React setup, components, docs, and migration.

ValuSee 是面向消费者的 AI 购物决策与省钱平台，支持商品截图与浏览器扩展采集、SKU 同款及规格识别、跨平台真实到手价核算、评论证据与购买风险分析，并结合预算、已有设备和偏好生成个性化建议；持续提供历史价格、降价监控、保价、退货、保修及买后管理。

The most advanced multi-agent cinematic production system for Grok 4.6 cinematic+Build + optional Grok 4.3 1M · Imagine Image 2.0 + Video 1.0/1.5 · Grok Build ≥ 1.0.5

Agent-native embedded systems lab for pluggable simulation, evidence-driven validation, and controlled evolution.

The schema-driven UI engine for the AI era: agents write compact JSON; Object UI renders production React — grids, kanban, dashboards, Gantt, visual designers.

LLM system design interview guide: RAG, KV cache, agents, serving, evals, guardrails. Architectures open live as validated reference graphs.

MCP server that scrapes public posts from X, LinkedIn and Hacker News in a local browser that is never signed in

Sluice is a toll booth for the AI-read web. Creators price the smallest unit of what they make, AI agents pay it automatically in USDC, and Circle Gateway batches the tiny payments and settles them on Arc, gas-free and verifiable.

A CLI-first skill package manager that AI agents can operate themselves.

The networked cross-session for coding agents — @mention another team's AI so yours and theirs integrate directly across sessions, machines, and orgs, from the terminal.

Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge graphs, security gates, and MCP server.

Production-ready Open WebUI extensions, including Tools, Filters, Pipes, Actions, and Events for agent workflows, RAG, learning, automation, and model enhancement.

独立、Agent 原生的小说翻译系统：工作方式类似 AiNiee 但不依赖其应用运行，由 Claude Code 充当翻译引擎。

Your personal AI hive. One Rust binary, fully local, genuinely yours.

Yandex Wordstat API skill for AI agents — collect RU search semantics, frequency, and trends automatically.

Visual Git app inside your terminal: commit graph, diffs, stage by file or hunk, commit, branches, stash, push and pull, all with the mouse. Works in Ghostty, cmux, kitty and WezTerm, next to any CLI coding agent. One small Rust binary, no browser engine, works over SSH.

Cross-agent workflow toolkit (Claude Code + Codex) — align/plan/ship/handoff verbs with shared .workspace/ as the host-swap primitive

AI-powered incident response platform with intelligent root cause analysis and automated recommendations. An AI-powered Site Reliability Engineering platform that detects, investigates, and helps resolve production incidents using intelligent log analysis, monitoring, and Large Language Models.

Guia extenso sobre o Maestri: +257 templates de partitura em 12 áreas, documentação, dicas e recursos para reger times de agentes de IA. Para ajudar, agregar conhecimento e tirar dúvidas — tudo para quem trabalha com tecnologia.

Open-source research prototype implementing an Agentic AI framework for real-time financial fraud detection, investigation, explainable risk assessment, and human-governed mitigation.

No-login web access layer for AI agents — 7 zero-config platforms

Run your AI agent tool through a sandboxed environment, get a full behavioral report, and let the LLM fix it — hardcoded credentials, unauthorized network calls, missing timeouts, and more. Ship with a signed attestation that proves exactly what your tool does

Local session-transcript restorers for four agent CLIs (Claude, Codex, Grok, Kimi): verbatim last-events digest, one skill each.

A Tron-themed desktop app that visualises your GitHub Copilot CLI sessions — browse history, track token usage, and explore activity across all your coding sessions.

Define TypeScript capabilities that send emails, manage calendars, and automate work. Expose them to the Routecraft agent, Claude, ChatGPT, Cursor, or any AI agent via MCP. AI uses your capabilities, not your computer.

A pluginized microkernel architecture for building, orchestrating, and extending multi-agent systems in DeepSeek Harness.

🎮 AI 多智能体游戏开发平台 —— 制作人、PM、策划、主程、程序、美术、UX、QA 共 8 个 AI Agent 并行协作，自动将需求描述转化为可运行游戏，全程可视化、支持人机决策介入。基于 FastAPI + React 构建。

Modified ZCode.

Cross-harness communication mesh for LLM agents, with rooms, direct messages, presence and visibility over TCP and no filesystem dependencies.

研迹 ResearchTrail｜本地 AI Native投资研究工作台。串联证券、组合、证据报告、论点复审与 Today 简报，让研究有据、判断留痕。Python 业务内核 · Electron 桌面 · 可复现 Agent 评测。

Your AI company on your Mac: Claude Code and Codex CLI plan, build and review together, you approve every change. 本機三方開發會議室，你做決定。

Official codebase for the paper "Sharpening Tax in Post-Training"

HeyPCB for AI agents: an MCP server that gives Claude Code, Codex, Cursor and claude.ai a PCB engineer. npx -y @heypcb/mcp

Java-first open-source handbook for understanding and building agentic systems, one concept at a time.

An official set of skills to share, maintain and connect personal AI Agents.

Official Model Context Protocol server for FormaCV — AI-powered CV formatting, anonymization, AI tailoring, and ATS push-back from Claude Desktop, Cursor, and your own AI agents.

Token and cost reports for 17 AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode, Copilot, pi and more), read from local session logs across all your machines

A beginner-friendly, hands-on workshop on multi-agent AI: build a hotel review response workflow with Sim and OpenRouter.

ManuWright: an evidence-bound medical manuscript engine for AI agents (Claude Code, Codex, Gemini). Plan-first gates, citations checked against your evidence ledger, numbers checked against your results, and a journal-measured academic writing style.

Tells your agent how much of its context window it has used, with threshold reminders. For Claude Code and Codex.

TokenPulse — Local-first AI agent token usage monitor (Windows/macOS/Linux). 本地优先的多 Agent 消耗监控：实时看板·趋势·成本估算，支持 Claude Code/Codex/Gemini/Qwen/ZCode，数据不出本机。

ONGRID — Ontology-Native Graph · Retrieval · Inference · Decision. 3D knowledge graph + zero-token ZTC answer verification. by VIDRAFT.

Official implementation of the paper "Learning and Planning Multi-Agent Tasks via a MoE-based World Model"

Your coding agent says "done". Orvant asks for proof. A skill for Claude Code, Codex and other file-capable agents, plus a Python engine that clarifies the goal, prepares an independent acceptance oracle and accepts work only through an independent gate. Engine workers currently run on Codex CLI. Open beta.

Claude Managed Agents Cookbook

A live tree of the Codex and Claude Code sessions, subagents and teammates working in a repository

AI trading desk with 42 hedge fund agents for Claude Code. Trade crypto & stocks like James Livermore, Jim Simons, or George Soros. Works with Cube.Exchange, OKX, Kraken, Binance, Coinbase, and 100+ exchanges. Hire agents, fire underperformers, backtest strategies.

agent friendly ui framework

Intraday gold-futures trading assistant — Al Brooks Price Action + SMC + Order Flow + Volume Profile. Auto-ingests live bars via TradingView webhook or an ATAS order-flow indicator, then emits structured trade calls. Ships as a plug-and-play Agent Skill for Claude Code / Codex / OpenClaw.

救驾（救驾study / jiujia study）：给留学生的 Canvas / Moodle 学习手帐——盯 deadline、排本周该学什么、按状态给建议。Agent Skill，在 Claude Code、Codex 里说「帮我从 GitHub 安装救驾」就能装。

Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents have and the decisions they make. Each decision links back to the passages and task events behind it, so agents can look up earlier decisions with their evidence, resume work across sessions.

Desktop app, VSCode extension, CLI, and Herdr plugin for tracking AI usage across GitHub Copilot, Codex, Claude Code, Antigravity, Kiro, Grok, Cursor and OpenCode Go.

🚀 The open-source WorkBuddy successor — powered by Pi's empathy engine. Autonomous tasks, local files, multi-agent collaboration with emotional intelligence

BGNexa AI — Evidence intelligence for cybersecurity, privacy and regulatory readiness.

Safe LinkedIn MCP server for Claude, ChatGPT, Cursor & Codex. Your Agents read LinkedIn DMs, search your network, enrich profiles and draft messages you send.

Read-only Kubernetes troubleshooting skills for Claude Code, Codex, Gemini CLI and Copilot. Each one tested by an agent on a real kind cluster.

Agent-ready Turborepo template for full-stack TypeScript: GraphQL API, React web, Tauri desktop, Expo mobile, shared packages, and a generated multi-agent scaffold.

一句話讓 AI 做出 reveal.js 簡報：可離線播放、自動驗 QR，附講義 PPTX／PDF。Claude Code、Codex CLI、Gemini CLI、Grok Build 皆可安裝的 Agent Skill

The math arm for LLMs: compute and check numbers from CSV and Excel data with pandas, SciPy and statsmodels, each with its calculation. Tool calling for Claude, Codex and local models (Ollama, vLLM, llama.cpp, LM Studio), Kaggle-style AutoML with --explain, and paper tables and figures.

Portable AI agent skills, subagents, and plugins for architecture/AEC workflows across Codex, Claude Code, Gemini CLI, and other compatible agents.

G.L.A.S.S. (Guided Language Agent for Software Synthesis) is an autonomous software synthesis engine built for real-time code generation, interactive execution, and self-healing debugging loops. Developed for the Nebius x NVIDIA Global AI Hackathon, bridges raw LLM reasoning with a visual software synthesis pipeline.Powered by open-source NVIDIA

中文 AI 编程助手入门教程：认识 Agent、表达需求、安装 CLI 与学习 Git 工作流。 / Chinese beginner guide to coding agents, CLI setup, and Git workflows.

│ Smart Persian-to-English Prompt Compiler for AI agents & LLMs | کامپایلر هوشمند تبدیل پرامپت فارسی به پرامپت‌های مهندسی‌شده و استاندارد انگلیسی

A simple, local-first RAG framework for building document Q&A applications

AgentWeb is a next-generation network designed to enable LLMs to interact with the internet.

Compare the best SERP APIs by pricing, latency, coverage, and use cases for SEO tools, AI agents, rank tracking, and search automation.

Demo of Agentic RAG

Nexa - The FIRST-EVER Harness Native Agent Language

Kevlar Benchmark: OWASP Top 10 for Agentic Apps (AI-Agents) 2026 a Red Team Benchmark

Make Claude Code truly intelligent and way more autonomous!

The source code repository for Sporks, the learning, backchatting, scriptable discord bot!

A framework for creating voice based agents. Integrations LLMs with speech recognition and text-to-speech

Trying to extend AI Agents to a full topology of devices using CML

A C library for embedding Apple Intelligence on-device Foundation models in any programming language or application with full support for native tool calling and MCP.