Custom agents

Turn Claude Code into a design-first Kotlin Multiplatform pipeline — an Android + iOS feature from one prompt, with architecture that doesn't drift. MIT.

A multi-provider, multi-agent coding harness with a Codex-class IDE on top of DeepSeek, Gemma, Qwen, and OpenRouter.

End-to-end AI literature review automation: crawl, screen, download, multi-agent review, and report generation

Full-stack Generative Video Cloud

OpenMeta CLI - Autonomous, local-first open source contribution agent for developers

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

Rewrite frontier research using allegorical structural mapping.

Rust Agentic Skills : It transforms general-purpose LLMs into a multi-agentic Rust engineering team via a token-efficient Brain-Tool-Context setup that dynamically loads tools and documentation, adhering to the Agent Context Protocol (ACP).

Agent Cat downloads — a free macOS menu bar and Windows tray app that shows Claude Code, Codex and Gemini CLI usage, remaining limits and reset times.

Lightweight Dynamic Island for macOS with AI coding agent notifications

Agentic AI Humanizer Skill for Codex, Claude and OpenClaw: Bypass AI Detectors

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENTS.md or Agent Skills-compatible agent.

基于LLM大模型+AI Agent管理数据库的AI智能学校管理系统，本项目采用Vue3+TypeScript+Vite前端与Spring Boot+MyBatis+MySQL后端技术栈，支持通过自然语言实现学生、员工、班级等数据的查询、统计分析、增删改操作，具备智能意图识别与参数提取能力，集成智谱/DeepSeek等大模型API，提供数据可视化分析、对话历史持久化、多会话管理等完整学院管理功能

GoAgent · 围棋智能体: AI-editor-style KataGo + multimodal LLM desktop Go agent

Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.

An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harness (detailed event steams, logs, and performance data) or quickly replace closed source one (featuring out of the box plugins for web search, image gen, memory, auto research and more in dev).

The self-hosted, multi-tenant AI app builder for teams. Sandboxed, audit-logged, MIT-licensed. The open-source alternative to Multi-Tenant Saas buiders.

不死鸟 Phoenix — Hermes Agent 插件：路由分档/风险防线/自愈/存档点提醒/审批策略自适应，官方钩子接入，不改 Hermes 核心代码

🦞 Local, read-only security audit for your OpenClaw agent. Finds config, prompt-injection and supply-chain risks, watches for drift, and vets a skill before you install it. Offline, zero deps. A–F grade when all five layers ran.

Manage OpenClaw in your team (Enterprise) by providing it compute infrastructure, tool integration, Authentication and security primitives

A traceable personal memory layer that carries verified state across apps, models, and AI agents.

The game engine for AI agents. Give your AI superpowers for game dev + A skills framework that just works + easy install and setup ☀️

Fast native Swift OmniFocus MCP server and CLI for macOS. Let AI assistants safely read, update, complete, and organize tasks and projects through documented Omni Automation APIs.

Hands On Workshop for GitHub Agentic Workflows

💸 Shrink your token bill in herdr: compresses every agent pane's requests (-31% input / -74% output, measured live) and shows the savings on a per-pane badge

A modular on-device inference LLM coding agent. Core component of siGit Factory.

:file_folder: A project management tool for the command line

BOSS 直聘招聘端 AI 工作流：从岗位需求到候选人报告，串联简历获取、逐份评分与授权招呼。一个 Skill 配合本地 CLI，让筛选有依据、过程可追踪。

Zaivern Code — Rust-native AI cockpit editor

One window for a whole swarm of AI coding agents — split terminals, per-agent git worktrees, live web previews, and a War Room where agents collaborate

Google Drive for AI agents — share files with your team, share context across your agents. Open source, no server required.

飞书/Lark 机器人桥接，同时支持 Pi 和 DeepSeek Harness（DSH）双平台，随时随地远程与你的编程助手对话

A traceable and extensible multi-agent platform for financial research.

DevSpace + elastic ChatGPT Classic multi-agent workers. Local-first MCP workspace and dynamic subagent runtime orchestration.

Autonomous marketing team for Claude Code — 9 AI agents, 20 skills, 4 MCP servers, one /grow command

AI-powered infinite canvas — aggregate multiple AI platforms for image & video generation, LLM chat, and ComfyUI workflow execution. Built-in Agent system with knowledge bases, custom Python skills, and encrypted distribution. Connect your local ComfyUI backend for seamless workflow automation. Zero-config LAN collaboration with bilingual UI.

Learn the abap2UI5 basics — 100+ ready-to-run apps, from a two-line Hello World to complete applications

iMessage, WhatsApp, Slack your agent from any conversation

AI powered web security testing for authorized targets

A desktop workspace for crafting vivid AI personas and exploring what emerges when different personalities fuse.

Repository retrieval and context engine for Claude Code and Codex: finds relevant code, reuses project knowledge, and pairs each task with specialist skills and verification.

CIRIS: an open-source AI assistant with a conscience you can check. Signed, auditable reasoning on every decision, a human-held halt, 29 languages. AGPL-3.0.

Double-check before you ship: grill the requirements, test the implementation, prove the delivery. An engineering-discipline bundle for DeepSeek Harness.

阿杭公开的 Codex Skills 集合：把真实工作流产品化为可运行、可验证的 Agent Skill

AI-KIT is a practical starter kit for development: ChatGPT/Codex, Claude, DeepSeek, KIMI, and other coding agents. It provides reusable project context, rules for each stack, adaptive model routing, conservative installation and updates, testing and review workflows, security guidance, Docker and Kubernetes readiness, and clean project templates.

Native Code Graph · Extreme KV-Cache · Cross-Platform All-in-One Agent (TUI, WebUI, Desktop, OpenWRT) | 原生代码图谱 · 极致缓存 · 跨平台全能型 Agent（TUI / WebUI / 桌面 / OpenWRT）

Money Atlas Skill.md (Claude Skill) For AI Agent A Genesis Protocol-powered intelligence system for financial markets, macroeconomics, and geopolitics. Core Systems - Genesis Protocol (First Principle + System Thinking) - SMC Layer Engine (Quant price structure)

Rhizome lets Claude Code, Codex, and OpenCode sessions discover each other, follow selected work, and exchange messages through MCP. Use it to coordinate parallel tasks on your laptop or connect your agents with a colleague's agents over a LAN or Tailscale network.

每天自动送达的 AI 日报 Agent Skill：12 源采集 + LLM 筛选摘要，落地飞书表格/机器人推送/云文档归档

Agent Session Hub: search, cite, resume and hand off local Claude Code, Codex, OpenCode, Pi, Grok and OMP sessions. Trajectory over summary. Lineage graph. Local FTS/BM25. Not Microsoft Mobius.

Agent skills (SKILL.md) for the ArtCraft Rust creative suite — evidence-verified, MCP/CLI surfaces — for Claude Code, Codex, OpenCode, Devin, CommandCode, ZCode

Piper Morgan Product: Intelligent Product Management Assistant for Python

pilot: AI That Ships Your Tickets for Automated Development

Oficina 3D con agentes de IA para tu negocio. Funciona con Claude Code: clona el repo, escribe /instalar y Claude lo configura contigo.

Local-first, zero-dependency cost ledger for your AI coding agents. Reads the transcripts Claude Code / OpenCode / Codex / Gemini CLI already leave on disk — spend per repo, model, day, and git branch, with honest billed/estimated/unpriced provenance. No network, no account, no telemetry. ULP 1.0 reference implementation.

Use Fireworks AI models in Claude Code, Codex, Cursor, VS Code, Copilot, and other coding agents.

A personal job application AI Agent for job discovery, fit scoring, tailored materials, form filling, human-gated submission and application tracking.

企业级AI PaaS管理平台 — 基于 Docker 的容器生命周期管理、LDAP/OIDC 统一认证、MCP 代理架构。让每个员工都有自己的 AI 代理。

RLLaVA is a user-friendly framework for multi-modal RL research and optimized for resource-constrained teams.

nonebot2 机器人插件 - ⚡在群里和大家一起玩郊狼吧！⚡

Awesome curated list of coding assistants and related resources

ui and host for Rasa Nlu and Rasa Core

DSTC6: End-to-End Conversation Modeling Track

An AI-powered assistant for your terminal and editor

A tiny LLM Agent with minimal dependencies, focused on local inference.

Confidence-Weighted Multi-Agent Retrieval-Augmented Generation (CW-MARAG) — a contradiction-aware RAG system that uses multiple retrieval agents with confidence-based arbitration to generate grounded, non-hallucinated answers from PDFs.

Claude Code state management with session continuity and AI personas, subagents and agent discussion

Give Copilot a memory! MemoriPilot provides seamless, persistent context management that makes Copilot aware of your project decisions, progress, and architectural patterns - dramatically improving the relevance and quality of AI assistance.

Open-source team collaboration where your conversations become your competitive edge. AI-powered, privacy-first, and you control every bit of it.

A modular AI orchestration system supporting local LLM (llama.cpp) and API models, featuring dynamic routing, multi-stage processing pipelines, and persistent conversational memory.

An AI teaching assistant that allows students to interact with the teacher's course materials

Web scraping framework built for AI applications. Extract clean, structured content from any website with dynamic content handling, markdown conversion, and intelligent crawling capabilities. Perfect for RAG applications and AI training data pipelines. Features async processing, browser management, and Prometheus monitoring.

"FastAgent: Simple, Fast, and Strong LLM Agents"

Framework for coding stateful LLM chatbots and agents

Multi-Agent Path Finding in C++ (WHCA*, iWHCA*, WCBS)

To automate the SLR process and write paper quickly using multi agents of AI

An Eclipse AI Assistant that connects with SAP AI Core deployments to provide a "copilot" experience to ABAP Developers on the cloud and on-premise

Curated list of data serialization formats — API, ML, Agentic AI, Big Data, Configuration, and beyond

Declarative Messenger chatbot framework

GrantFlow.ai is a platform for creating grant applications using ML and AI

Mobile-first web interface for Claude Code and Codex, with a multi-agent system — control your local AI coding agents from anywhere

This is the official repository of the paper "BalanceSFT: Improving LLM Function Calling with Balanced Training Signals and Data Hardness"

12-layer memory architecture for OpenClaw agents — knowledge graph (3K+ facts), semantic search (multilingual, 7ms GPU), continuity + stability + graph-memory plugins, activation/decay system, domain RAG. Agents reconstruct themselves from files on every boot.

A Sovereign Agent Governance Protocol for Deep-Water Workflows

简单的ai chat网站，使用Cloudflare AI提供服务，Nextjs开发，由Cloudflare pages部署 A simple AI chat site that serviced by Cloudflare AI and deployed by Nextjs+ Cloudflare Pages

The first platform designed to empower organizations by automating and enhancing their employment processes through advanced autonomous agents.

Claude Agent SDK UI

June is a framework for agent based modelling in an epidemiological and geographical context.

A toolkit for composing self-learning algorithmic trading agents

Set of instructions for your favorite AI agent (e.g. Cursor, Copilot, Claude, etc) for a "DHH-driven" Ruby on Rails development philosophy.

🤖 An intelligent stock trading bot combining technical & qualitative analysis with Interactive Brokers TWS API integration

Python code to implement LLM4Teach, a policy distillation approach for teaching reinforcement learning agents with Large Language Model

Mobile adapter for IOS and android for mobile LLM agents

Agent Kit is a comprehensive AI agent development framework that integrates Claude Agent SDK, providing a complete solution from frontend to backend. This project aims to help developers quickly build, deploy, and scale production-grade AI Agent applications.

The first AI agent for Okta! A secure, local-first AI agent that helps Okta administrators query their tenant data using natural language.

OpenThaiRAG is an open-source Retrieval-Augmented Generation (RAG) framework designed specifically for Thai language processing. This project combines the power of vector databases, large language models, and information retrieval techniques to provide accurate and context-aware responses to user queries in Thai using OpenThaiGPT 1.5 as LLM.

A curated list of autonomous agents and developer tools powered by LLM.

A distributed engine for elastic workload, e.g. AI Agent, RL, Quant

OpsAgent 是一个基于 LLM (Large Language Model) 的 Kubernetes 集群管理工具，它通过 AI 能力来简化和增强 Kubernetes 的操作和管理。该项目旨在帮助用户更容易地进行集群诊断、安全审计、资源分析和清单生成等操作。