Custom agents

Agentic Reinforcement Learning 101. A pragmatic course for AI/ML Engineers based on "The Landscape of Agentic Reinforcement Learning for LLMs: A Survey" https://arxiv.org/abs/2509.02547

🍌 Autonomous story agent creating illustrated storybooks with Claude Code SDK

Benchmark Everything Everywhere All at Once, a fully autonomous agentic system for benchmark construction and customization.

Multi-agent orchestration plugin for Factory AI Droid CLI. 32 droids, 35+ skills, autopilot & ultrawork modes. Based on oh-my-claudecode.

Learn Claude Code — 基于源码的完整技术分析文档集，15章深度解析 Agent Loop、工具系统、权限系统等核心机制

A Claude Code Agent Skill for Vue.js development with TypeScript, emphasizing testing-first development, functional patterns, and maintainable architecture.

Agent Skills for Robot Framework

A personal AI agent operating environment you self-host on Cloudflare.

AgentScope Golang: Agent-Oriented Programming for Building LLM Applications

让 AI 像真正的团队成员一样参与项目、执行任务、协作交付的 AI Native 工作平台。

Open-source A-share AI research workstation — multi-agent analysis, simulated trading loop, personal knowledge base; runs fully on your machine.

Use Hermes Agent as the control plane for local coding agents like Codex, Kimi Code, Claude Code, OpenCode, and Gemini CLI.

AI 网文长篇小说写作流水线，12 个 skill 包。配套站点 novelcatch.com：番茄每日扫榜 / 拆书 / 情报（免费）

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source

Turn tab overload into a local-first workspace with intent-first AI organization and Agent collaboration through MCP.

SOTA communication-efficient, fast, and robust map merging using 3D point cloud (accepted in IJRR)

Mission control for every Claude Code session on your machine.

Observable diagnostics, failure attribution, metrics, and no-key replay for multi-agent runtimes.

Real-time trustworthiness evaluation and safety interception for AI agents. Semantic analysis, safe alternative suggestions, multi-step attack chain detection, and LLM-as-Judge.

An Emacs Lisp AI coding agent with multi-agent architecture, permission-based tool access, and LLM integration via gptel.

Autonomous red teaming and evidence-backed security evaluation for live AI agents.

Track your AI coding-agent token burn across Claude Code, Codex, OpenCode, Antigravity, and more.

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

Framework for building sophisticated Investment Research AI agents .

Sample solutions leveraging the Microsoft Graph API that provide an inventory of Copilot Agents in a given tenant.

Open-source GraphRAG domain knowledge layer: LLMs continuously distill scattered skill docs into a queryable, evolvable, human-editable two-layer knowledge graph — versioned, hot-swapped and rolled back via a GitOps pipeline like software releases, and served to AI agents over MCP. RAG, but with relational structure.

Excalidraw MCP server with real vendor-icon search & insertion (AWS/Azure/GCP/OCI/Kubernetes) for AI-built architecture diagrams — live canvas, 31 tools

Awesome papers in Large Language Models (LLM). They focus on state-of-the-art LLM methods, such as model, system, Pre-training, SFT, RLHF, Reasoing, MOE, Multi-modal LLMs, Applications (RAG, agent, coding) and so on.

2025 LLM Hackathon for Applications in Materials and Chemistry

CADSmith (formerly AutoFab) is a multi-agent system that generates manufacturing-ready CAD models from natural language by combining LLM code generation with programmatic geometric validation from the OpenCASCADE kernel and visual inspection from an independent vision-language model, iteratively refining until the part is dimensionally correct.

Skills for autonomous agents generating pixel art using SpriteCook

Guest agent for Tart VMs

Agent skill for AI coding assistants — review and build production-grade Claude agents following SDK best practices

Bidirectional sync for Claude Code and Codex — instructions, skills, agents, MCP servers, hooks, permissions.

Nano Claude Code - A lightweight AI code agent in Python, inspired by Claude Code and Kimi-CLI. Now you can give it a try and enjoy it plz~~

本仓库记录了一套以 Obsidian 为知识库核心、以 Claude/Codex/Gemini 等 AI Agent 为分析引擎的研究工作流，适合需要大量阅读文献/资料、整理学习笔记、复现模型/实证的学生党、研究者、工作人员等。

a control tower for your Claude agents

Agent Skill Evaluation and Evolution: Frameworks and Benchmarks

Teaching/learning resources for O'Reilly Live 'How to Create AI Agents Like a Pro': Microsoft Copilot Studio builds for customer service, onboarding, and document automation.

Literature-fetching & citation-auditing skill for LLM agents (Claude/Codex) — 讓 AI 引用經得起追問:找文獻、查核引用真偽與支持度、文獻支撐寫作,防幻覺引用。

Example realtime voice agent built with Google ADK and deepagents

A topic-oriented reading list of ICML, ICLR 2026 papers related to agents, tool use, multi-agent systems, computer-use agents, and agent safety.

Local-first multi-agent market research desktop workspace built with Tauri, Next.js, and an embedded TradingAgents-compatible core.

htop for AI Agents — monitor token usage, costs & tool calls across Claude Code and Codex in real time

Stop copy-pasting from ChatGPT. A beginner-friendly guide to agentic coding tools (Claude Code, Codex CLI, Gemini CLI) for CS students.

AI news tracking skill for Agents like Claude Code, Openclaw, and more. Tracks AI entities across 9 sources and generates daily structured reports.

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

Forkable shell substrate for a single code repository — DB-backed identity, memory, roadmap, content; harness-agnostic boot. We build the data layer, we rent the harness.

Método jurídico aberto e executável por agentes de IA: base curada de STF/STJ, legislação, súmulas, temas e teses; 10 protocolos e motores locais. Fontes verificáveis, casos privados. Claude Code · Codex · MIT.

Control AI Coding Agents From Your Phone

McKinsey-grade market research decks for Claude Code — adversarially verified numbers, 15 McKinsey methodologies as executable workflow, multi-agent pipeline. 一条指令产出敢被挑战的麦肯锡级市场研究 deck。

Self-host AI companion platform — characters with schedules, memory, and a life of their own (BSL 1.1)

Ship AI-agent artifacts, not demo theater — verifier-gated, cross-family runs that learn which model wins.

Checks every AI agent action against your company's real rules before it runs. Git-native, PR-reviewed.

Just-in-time API keys for AI agents - and any other process you route through it: the caller only ever sees a placeholder.

A LLM-powered agent for NetHack

A Rust implementation of LangGraph's state machine framework for building LLM agent applications.

AgentMesh360 Job Agent — agent-native job search CLI for Boss Zhipin, Liepin, Zhaopin, and 51Job. Built for Claude Code, OpenClaw, Cursor, and Codex.

A compact heads-up display for your coding agent. Instruments while it works, the answer when it stops. Claude Code, Codex, OpenCode.

For the Udacity Master of Science in Artificial Intelligence and MBA in AI Product Management! Contains my solutions for various Nanodegree Programs (Robotics, Artificial Intelligence, Machine Learning, Deep Reinforcement Learning, Computer Vision, Sensor Fusion, Flying Cars, Business Intelligence, Agentic AI, GenAI).

AI Agent、大模型、RAG、MCP、微调与强化学习面试八股学习笔记，包含系统化 Markdown 文章和配套流程图。

An autonomous multi-agent IDE for screenplays🎮 & novels📖. One-click to share web performances or drive Unity dialogue systems. Empowering vibe game dev with AI!

基于 Claude Code / Codex 的 SRC 漏洞挖掘 Agent 技能体系 —— 系统级提示词 + 13 个专项安全测试 Skill 知识库

Let's Qitos! A torch-like agent-native framework for researchers.

Blacklight is a cross-platform toolkit for mapping, analyzing, and understanding the local AI agent attack surface across Windows, macOS, and Linux.

Give any AI agent real hands on your Mac. A stdlib-only Python CLI for volume, brightness, apps, browser, media, screenshots and mic tests. No dependencies, no daemon.

Codex skill that turns one image or text concept into a WeChat-ready Chinese sticker pack people will actually send. Sendability-gated, 4-keypose → 16-frame, no model-drawn text.

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

An ML-powered framework for detecting and counteracting sycophantic spiraling in AI chatbots.

Multi-platform ACP client (VS Code + CLI) for connecting AI coding agents — fork of vscode-acp with Windows fixes & improvements.

面向个人用户的轻量化健康管理工具，基于LLM的 Agent 技术，解决用户日常用药安全查询、化验单快速解读、个人就诊记录统一归档的核心需求，全程严格遵守医疗合规要求，不提供任何诊疗服务。

Swarm Intelligence Prediction Engine - Multi-agent AI debate for calibrated forecasting

A convenient framework for developing LLM- and LMM-based web agents. (ACL'24 Demo)

Harnessing AI to Disrupt and Evaluate Security (HADES)

A seq2seq based chatbot built with PyTorch (中文聊天机器人)

Let's RAG it RAW without fancy frameworks

Fully Cooperative Multi-Agent Deep Reinforcement Learning

https://github.com/CryptoMonkey21/AgentGPT.git

Competition and Agent Frameworks for the Trading Agents Competition

Sample dockerized NestJs framework service integration with New Relic Node.js Agent showing how to instrument the app in order to use all the Agent’s features (like Service Maps or Distributed Tracing)

A powerful, modular, and self-hosted AI assistant that combines website monitoring, ERP integration, system health checks, web search, and personal organization into a single Telegram bot and Web Interface. Powered by Ollama for local, private intelligence.

Agent Sven: The Native Peer-to-Peer AI Agent

An abstraction library for building domain-specific intelligent agents based on Large Language Models (LLMs). LLMAgent provides a core architecture and behavior definitions that simplify the development of specialized agents by leveraging the AgentForge framework for dynamic workflow orchestration.

A Claude Code plugin for managing requirement documents, tracking changes, and outputting specs — enabling downstream tools to generate code based on high-quality specs and complete E2E testing.

🦞 Web UI for browsing OpenClaw session tool call history. Zero dependencies, just Node.js.

Scale OpenClaw from one AI assistant to a coordinated fleet — shared knowledge, collective memory, distributed goals.

Reachy Mini MCP | Give your AI a body. This MCP server lets AI systems control the Pollen Robotics Reachy Mini robot. | Speak, listen, see you, and express emotions through physical movement and voice. | Works with Claude, Windsurf, Cursor, or any MCP-compatible AI. | Zero robotics expertise required.

How to guides on web-crawling or scraping

Bespoke agent-to-agent discovery and communication protocol

MARU-Lang is an open-source RAG chatbot engine.

Give your agents real time desktop perception. Stream screen, microphone, and system audio for live context and actions.

This repo is an extension of PostgreSQL MCP Server providing functionalities to create tables, insert entries, update entries, delete entries, and drop tables.

Secure-by-default OpenClaw on Ubuntu, with a verifiable security report

OpenSource Version Of Claude Code (mirrored)

simple yet useful ai agent that just use `bash`

LLM QA, Observability, Evaluation and User Feedback

proof of concept to generate Airbyte low-code YAML connectors from API documentation