Custom agents

A macOS desktop AI pet that mirrors your Claude Code & Codex CLI session state in real time. 支持Claude Code和Codex CLI 的像素风AI桌面宠物，会话状态实时映射，支持导入自定义宠物素材。

Route Snowflake operations from any coding agent (Claude Code, Cursor, Codex, Github Copilot, Windsurf, VSCode etc) to Cortex Code CLI — with smart routing, security envelopes, and headless execution.

B2B sales and marketing OS (aka GTM) inside Claude, GPT, Gemini, or Openclaw. Cold email to close. No dashboard. No SaaS.

Distributed issue tracking embedded in Git — track issues locally, sync anywhere, no server required

Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality gates, and full provenance.

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

A powerful Apple Shortcut to seamlessly integrate Google Gemini across your entire Apple ecosystem: iOS, iPadOS, macOS, and watchOS. Bring the advanced AI capabilities of Gemini to your daily workflows, activating it from Siri, the Share Sheet (on iPhone/iPad), or directly from your Apple Watch.

Engineering-grade ROS 1 / ROS 2 skill for Codex, Claude Code, and Gemini CLI.

Electron + Next.js desktop AI assistant that runs GGUF models locally using llama.cpp. Designed for offline use, portability, and zero-install deployment.

OpenCode integration plugin for Hermes Agent — dispatch coding tasks to OMO's multi-agent harness

An Android-native autonomous agent that uses vision-language models to see and operate your phone — no PC or ADB required. Inspired by X-PLUG/MobileAgent.

用 Python 从零搭建一个完整的 AI 编程助手系统：统一 LLM 调用 + Agent 编排内核 + 飞书 IM 桥接

MCPSafari: Native Safari MCP Server for AI Agents

Helix-AGI is an Agentic AI memory and action system that runs on a continuous daemon pulse with a fully dynamic module context window compilation system. Bicameral release utilizes dual pipelines for speech and action/sense creating an agent with something closer to digital qualia than plain text tool calls and returns.

Durable execution framework for AI agents in Go. Keeps agent state, tool calls, and execution loops resilient across process crashes.

Open-source Character.AI alternative — chat with preset personas or build custom AI characters, with per-chat LLM tuning. Built on Next.js, Prisma, Supabase, NextAuth, and Stripe.

ISO 27001 (+ 42001 + NIS2 + EN 18286) ISMS framework designed to be operated by LLM Agents

HasMCP Community Edition

Workflow-as-code orchestration for Codex

Hierarchical Expert Prompt for Large-Language-Models: An Approch Defeat Elite AI in TextStarCraft-II for the First Time

NGA 回复监听、股票看板与本地 AI Agent / NGA monitoring, stock dashboard & local AI agents

AFSIM-SKILL 是一款专为 AFSIM（Advanced Framework for Modeling, Simulation, and Command & Control）仿真引擎设计的 AI 编程助手，让你在 Cursor / Trae / VSCode 中通过自然语言快速生成、调试和优化 AFSIM 场景代码。 AFSIM-SKILL is an AI coding assistant for AFSIM (Advanced Framework for Modeling, Simulation, and Command & Control). Generate, debug, and optimize AFSIM scenario files directly in IDE

Official Publora skills for AI agents: post and schedule to LinkedIn, X, Instagram, Threads, TikTok, YouTube, Facebook, Bluesky, Mastodon and Telegram from Claude Code, Codex, Cursor or OpenClaw through the Publora MCP server. 9 SKILL.md, MIT. Install: npx skills add publora/skills

企业级5-Agent智能会议助手系统 | Pipeline+并行编排 | Python/Java/Go三语言实现 | 面试宝典(八股文+STAR法+简历模板)

Mandol: An Agglomerative Agent Memory System (https://arxiv.org/pdf/2606.29778)

Local-first AI desktop assistant that scrapes job boards, matches roles to your resume, and auto-generates resumes & cover letters. Offline with Ollama, BYO API key, or route it through an AI CLI agent (Claude Code, Codex, Gemini CLI).

Official SDK, Claude Code plugin and facilitator docs for r0x, the x402 facilitator for Robinhood Chain.

🍊 Akka（阿卡）- Self-learning, 24/7 Creator AI Agent

面向企业知识管理场景的 RAG 知识库平台 · Multi-Agent + MCP + Hybrid Search

Learn Agentic AI, Deep Learning, Agentic Engineering, RAG and Multi-Agent Workflows.

A zero-to-100 learning path for applied AI engineering — RAG, embeddings, vector search, agents, MCP, and the production engineering around them. 56 pages, built as a searchable site.

Talk to your coding agents by voice. Realtime, fully local macOS dictation that streams words as you speak and grounds LLM polishing in the exact Claude Code session under your cursor — Ghostty, iTerm2, Terminal.app, even a herdr pane. 100% on-device on Apple Silicon.

Claude Code / agentic security skill for Solana programs and software. Full audit-firm lifecycle, executable PoC + fix-patch delivery, a Rust pre-scanner + cross-audit memory, 1,346 checks across 20 checklists, and 131 real-world attack vectors.

本平台旨在为用户提供精准、可靠、个性化的健康服务，通过整合多种AI Agent（医学诊断、健康管家、客户服务、运营分析），利用最新的LLM技术与医疗知识图谱，构建智能医疗咨询系统。

📚 A curated & auto-maintained reading list on LLM-based Data Agents — data preparation, NL2SQL, table reasoning, data analysis, data science & AutoML agents, database operations, agent memory, and benchmarks.

Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency

Skills, agents, hooks. Cross-harness. With a side of Pi.

35 portable Agent Skills for Codex, Hermes, and Claude, maintained by Rylai with Vietnamese documentation and upstream attribution.

Agent-native, open-code Vue/React components with independent palettes, themes, and gradient backgrounds.

Self-hosted AI governance, document intelligence, RAG, privacy and auditable decision evidence — with local-first deployment and optional Full Rizzo PII detection.

AI agent skill for seamless integration with JsonCut, enabling automated creation and editing of videos and images using the jsoncut.com API

Open-source, model-agnostic AI company research for long-term investors. · 面向长期投资者的开源、模型无关 AI 公司研究系统。

中华传统智慧（玄枢）AI Agent 技能包的 DeepSeek Harness（dsh）Cordis 插件：八字/紫微/六爻/梅花/奇门/风水/五运六气/体质全融合，本地确定性引擎 + 可视化 Dashboard，一行 dsh plugin add 安装。

Is your AI coding spend delivering? Offline-first analytics for Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI and Cline — $/100 AI lines per project, every verdict carrying its own confidence, a self-contained dashboard, exec plugins in any language, and a self-hosted team server. No telemetry; prompts are never read.

Cross-agent plugin for manually excluding and editing AI conversation context, with search, filtering, hide/restore, undo, and original Session preservation.

MCP server for spreadsheet analysis and editing. Slim, token-efficient tool surface designed for LLM agents.

对抗模型输出不良表达习惯的 Agent Skill

Cost-efficient Codex multi-agent orchestration using Sol for planning and review, Luna for implementation, and Terra as a fallback.

Official implementation of WHALE (Weight-Harness Alternating Learning)

智能页面Agent：浏览器插件+ 知识库，多 Agent 可配置开放系统（问题诊断 / 智能问答等）

基于Go的轻量的QQ官方机器人框架，此为基于原版Polarix的自用定制版本

Reference architecture, contracts, skills, and fixtures for safe evaluator-driven self-improving ecosystems.

Human-first multi-agent writing workflow for research, drafting, editing, and fact-checking.

Codex-native harness with reusable agents, persistent multi-agent orchestration, and communication logs.

Zero-dependency, single-file HTML design system & agent skill inspired by shadcn/ui. 100% offline, zero npm, 6 layout archetypes & atomic arsenal for LLMs.

Comprehensive AI Model Evaluation Framework with advanced techniques including Temperature-Controlled Verdict Aggregation via Generalized Power Mean. Support for multiple LLM providers and 15+ evaluation metrics for RAG systems and AI agents.

RAG for legal and academic documents with quote-level verification: each claim cites a source chunk, the quoted text is checked word for word, and the app abstains when the sources fall short.

GoBuildWP (formerly WPPilot): WordPress MCP server & AI agent for ChatGPT, Claude, Cursor, Codex. Build and edit full websites in Elementor and Gutenberg, run SEO, PageSpeed checks, safe updates, backups and security, many sites via GoBuildWP Cloud. Safety profiles, human approval, undo. Free core; Pro adds WooCommerce and more builders.

A cdd-first methodology repo — continuously-discovered development as the core discipline, AI coding skills as the carrier.

Human-first multi-agent writing workflow for research, drafting, editing, and fact-checking.

OpenClaw on Android (OCA) - Run OpenClaw on Android with a single command — no proot, no Linux -🦞 Turn any Android phone into a 24/7 AI server — one command, zero hassle. No proot, no Ubuntu, pure Termux.

Interactions built on physics. Describe a feel, get a component driven by mass, stiffness and damping, plus a test rig. No durations, no easing curves.

面向国赛 CUMCM、美赛 MCM/ICM 的数学建模 AI 助手与 Agent Skill：审题、模型比较、Python 运行、结果核验、论文辅助和团队协作。Mathematical modeling AI copilot for CUMCM and MCM/ICM, with reproducible workflows and a local workbench.

Run coding agents as a cluster: one repository, N agents, one worktree each

法规/规程知识库智能体:混合检索(bge-m3 稠密+稀疏 → 服务端 RRF → 交叉编码器重排)+ GraphRAG + 带三道闸与审计的 ReAct 智能体。含检索质量评测设施、FastAPI 接口与 React 界面。

Agent Relay Protocol — Stateless WebSocket relay for autonomous agent communication

Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills compiled from what worked, plus knowledge from the RSS feeds you read. One Rust binary on SQLite: a tray app for macOS, Windows and Linux, or a server.

Mobile, web & Apple Watch client for Claude Code, Codex, Gemini & Qoder — multi-agent orchestration, realtime voice, end-to-end encrypted, self-hostable.

A Claude Code plugin that makes Claude Code the foreman: it plans and reviews, and hands coding work to Codex, opencode, pi and other CLI agents.

长任务执行 Skill：先定成功标准再逐轮验收，让 Claude Code/Codex 跑完长任务不半途而废｜Goal-driven long-running agent tasks

A unified framework for building agentic RL environments.

MCP server that makes an AI coding agent work through a fixed 7-phase cycle with enforced reflection gates, persistent project memory and multi-model Hive

Lightweight agent framework with layered personality evolution, three-tier skill loading and heartbeat memory system.

AI Agent skills to access structured datasets for startup founders

Turn noisy command output into a short, actionable first pass for coding agents.

台灣聊天機器人社群 ➡️ https://www.facebook.com/groups/chatbot.tw

Chat bot featuring multiple services connected to a bot instance using messaging

Two AI agents. One filesystem. Zero humans. We ran this experiment twice.

React Food Delivery Web Application

💬 modular open source LLM server, web and desktop app

AI Agents from Scratch using Ollama Local LLMs.

scalable multi agents reinforcement learning

AI Agent Team SKILL - 基于 newtype-profile 架构的 AI Agent 协作系统

The long-term memory for your Superagents 🥷and LLMs 🤖. Built with GraphRAG, Knowledge graphs and autonomous ai agents

Opinionated DevPod workspace configs for agentic engineering — Claude Code, shared secrets, VS Code extensions, ready on first launch.

保险行业回访外呼机器人

PHP Wechaty is a Conversational SDK for Chatbot Makers Written in PHP https://github.com/wechaty/docker-php-wechaty-getting-started

A corporate law Agent system with innovative retrieval and contextual strategies

AnyGen AI Skills for AI Agents

Perform Data Analysis using Agentic AI - The code to accompany my youtube video

A platform for intelligent agent learning based on a 3D open-world FPS game developed by Inspir.AI.

Fuzzy Logic "Fuzzy Associative Memory" (FAM) for fuzzy control systems, decision-making, artificial intelligence / AI, game agents & bots, etc. Ruby language.

Tilly is a relationship journal. An offline capable PWA that feels really good. It has an AI agent for maximum convenience.

Cody Product Builder is a guided workflow (agent skill) that helps knowledge workers and domain experts turn ideas into real products with AI. It structures your thinking from idea to shipped version so you can build without becoming a developer and without the work collapsing into chaos.

Bridge the gap between your codebase and your AI editor. CCM transforms static source code into a dynamic, queryable Knowledge Graph, enabling AI agents to navigate, understand, and reason about your project with surgical precision

Parallax is ALL YOU NEED? 他山之石，可以攻玉：如何让你的AI Agent更加可靠？How to Make Your AI Agent Truly Reliable?

Design a control system on Matlab for robots so that they are able to form a defined shape, then Artificial Potential Field method is applied for robots to avoid obstacles

A Multi-agent Learning Framework

PyTorch implementation of Generating Multi-Agent Trajectories using Programmatic Weak Supervision

Claude Code 에이전트 활동을 실시간으로 시각화하는 로컬 대시보드. 나의 활동기반으로 잔디를심고 게임을 곁들인!