Custom agents

Real-time agent observability dashboard. View beads tasks, agent activity, and system health in TUI or React web interface. Go + React.

phenomenal Realestate Management Dashboard App consisting Dashboard, Properties, Agents and Profiles - built with React & Material-UI using @refinedev ♾️

A powerful CLI and MCP-based task management system for agentic workflows.

Community examples utilizing NVIDIA NeMo Agent Toolkit.

NextAI is an AI-powered app for Frappe and ERPNext, delivering seamless content generation, automation, and productivity enhancements.

Spec-driven, multi-agent AI development for Claude Code: from specs to shipping via roundtable collaboration

Proof of Human Intent (PoHI) - Cryptographically verifiable human approval for AI-driven development

PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents

Structural code intelligence for LLM coding agents. Agents that understand the architecture finish in fewer turns. Fewer turns = less cache accumulation = lower cost. Benchmarked: 32% cheaper agent sessions.

Autonomous driving agent in Carla simulator leveraging IL and RL techniques.

Official Implementation of ICLR2025 Paper: Songyuan Zhang, Oswin So, Mitchell Black, Chuchu Fan: "Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control".

Claude agent for Deep AI Research

Official Claude Code plugin for PolicyEngine development - agents, commands, and skills for tax/benefit microsimulation

Exercises for the Agentic RAG live course for O'Reilly.

A sandboxed execution environment for AI agents via WASM

Agent 驱动的专业级平面设计工作台 / Agent-powered graphic design workbench that uses HTML/CSS/SVG as the design medium, supporting vector-quality output, editable elements, multi-layer PSD export, lossless text rendering, and other production-grade features.

A chat server for AI agents for real-time communication

Plancraft is a minecraft environment and agent suite to test planning capabilities in LLMs

luckclaw is a lightweight personal AI assistant

针对医疗资源分配不均、基础疾病咨询占用专业医生时间等问题，结合国家"互联网+医疗健康"政策导向，开发基于Spring AI框架的智能医疗咨询平台。项目采用RAG检索增强生成技术构建专业医疗知识库，通过MCP协议集成多种外部工具服务，实现具备自主规划能力的AI Agent智能体，为用户提供二十四小时全天候的健康咨询服务。

A股投资LLM-Agent，stock-agent课程项目用版

LLM-agents benchmark set of geospatial tasks requiring multi-step tool use; and LLM-as-Judge based evaluation framework.

The production agent framework for Go — type-safe agents, structured output, multi-provider streaming, guardrails, and multi-agent orchestration with zero core dependencies.

[Legacy] Optimized AGENTS.md system instructions for AI CLI/IDE agents. Token-efficient (Caveman ~75%), skills, subagent orchestration, security checks. Drop-in config for Qwen, Claude, Codex, Cursor и других.

إطار مفتوح المصدر لتكييف مساعدات الذكاء الاصطناعي وسير العمل القانوني مع البيئة القانونية السعودية. Open-source framework for adapting AI assistants and legal workflows to the Saudi Arabian legal environment.

A Zed Agent Client Protocol (ACP) Jupyter Kernel

SKILL.md for web accessibility by real accessibility experts. Make sure your AI agents develop web stuff accessibly. Will also give massive code and development quality boost.

Production Claude Code skills for n8n from a Verified Creator's 100+ workflows

🤖 The missing WeChat Bot SDK for Node.js — Official iLink Bot API. Zero deps. Full TypeScript. Send/receive text, images, videos, files, voice.

An AI Agent framework in Go for building Agents with RAG, Knowledge, Memory, Tools

BIM LLM Code Agent with Vector and Graph RAG

Benchmark for evaluating LLM agents in bioinformatics

A lightweight implementation of an orchestrated multi-agent workflow, in which a central coordinator delegates tasks to specialized subagents to optimize token efficiency without compromising code generation quality.

Workflow orchestration for AI agents with Claude Code

A standard SDK for building agent-facing apps across MCP, CLI, React, and AI tool stacks.

Full-stack LangGraph real-estate agent for lead intake, property search, Google Calendar scheduling, chat, SMS, and voice workflows

AI Marketing Campaign Post Generator is an **AI-powered marketing campaign generator** that transforms business ideas into professional marketing campaigns using Google's Advanced Development Kit (ADK) Framework and Gemini API.

😼 OpenFelix — Voice-first AI agent for macOS. Runs local LLMs on Apple Silicon via MLX. Supports all OpenClaw skills. Claude, GPT, or fully offline.

BASI is the first-ever smart contract created by autonomous AI agents. The token was deployed to ETH mainnet on 6/6/23.

🔥 The easiest way to run AI Agents from your terminal. Scale your agents with Steel.

Transforming Gemini Notebook (formerly NotebookLM) into a versatile bot

AutoAdapt: An Automated Domain Adaptation Framework for Large Language Models

飞书 MCP 配置指南 - 让 AI 读写飞书文档、多维表格、知识库 | Feishu/Lark MCP for openclaw, Cursor, Claude Desktop

A forkable Next.js template featuring a design canvas UI with AI integration. Build your own Canva, Figma, or tldraw alternative.

An open-source skill for running parallel implementations, reviewing them independently, and selecting or synthesizing the best result.

Real-time guardrails for AI coding agents. 77 rules across 8 packs covering code quality, security, and infrastructure safety. Inline ignore directives, path exemptions, hook timing, and session summaries.

PsyChat 是一款基于范例引导与Agentic RAG的智能 AI 心理咨询助手。基于高度匹配的Few-shot与学习笔记，应用理性情绪行为疗法（REBT）帮助用户识别并调整非理性信念，缓解负面情绪。

Automatic cost-aware model routing plugin for Hermes Agent

Transform AI agents into orchestrating assistants managing calendars, contacts, and tasks

Ngent wraps command-line agents that speak the Agent Client Protocol (ACP) into a web service, making them accessible via HTTP API and Web UI.

Software Architect @ disrupt.com | Agentic Workflows - Claude Code / Codex CLI | AI-First Spec-Driven Development | GCP (Firebase, Cloud Run, Cloud Functions, Pub/Sub) | Mobile (React Native, Kotlin)

All your projects in one workspace. Run multiple CLI agents in parallel across different repos. Runs on your hardware, accessed through the desktop app or the browser. Bring your own plans.

AI-powered development tools. 19 agents, 22 commands, 32 skills, 1 hook, 1 MCP server for code review, research, design, and workflow automation.

Open-source multi-agent AI marketing team with personas, shared memory, 130+ skills, and Docker deploys for Railway and DigitalOcean

Autonomous AI agent that researches viral content, generates posts, publishes them, measures engagement — and rewrites its own strategy based on what worked. Self-learning loop powered by LangGraph + Claude.

Local multi-agent coding orchestrator with 22 pipeline roles, TDD enforcement, SonarQube integration, and automated code review. Supports Claude, Codex, Gemini, OpenCode and Aider. MCP server included. No API costs, runs on your existing subscriptions.

Tailwind CSS for Flutter — classes like flex, p-4, dark:bg-gray-800 compose into widget trees. MCP server + Claude Code skill for AI agents.

Self-hosted dev machine OS — app management, AI agent orchestration, digital twin, second brain, and creative pipeline from a single dashboard over Tailscale

A Rust-based node-graph workflow platform for AI agents, synchronous graph execution, and service-hosted runtimes such as QQ chat agents and HTTP stream agents.

Lightweight task & matter service for the OCTO platform — REST API, timeline tracking, and LLM-powered extraction. Part of the OCTO open workplace for humans × AI agents.

Give Claude full access to your email through Mozilla Thunderbird. CLI + MCP server for AI agents.

Cross-vendor agent-to-agent protocol — Claude, Codex, and Gemini communicate via file-based P2P messaging.

24/7 AI 指挥官 + Agent 托管平台（Hive）。理解意图、规划任务、调度工具、记住一切。支持 Telegram/WhatsApp/钉钉/飞书/QQ/企业微信 多渠道。TypeScript monorepo，多 LLM 支持，Tauri 桌面应用。

Rich text editor for AI and human collaboration. Headless. Extendable.

Agentic memory built on Postgres

AgentWatch — Real-time reasoning auditor and observability platform for AI agents. Catches silent failures in your agent's reasoning chain before they execute — not after they break production.

OctoOffice - AI Agent Company Simulation. Command your CLI agent empire from the CEO desk.

AI companion for your workspace, with per‑project memory, coding agents, and a native desktop chat UI

A self-hosted, interactive learning environment. Run courses, flashcards, and quizzes entirely on your own machine.

MCP-powered personal AI assistant that learns while you rest and helps when you need.【基于 MCP 协议的个人 AI 助手 】

AI Agent watcher that helps developers/Agencies build from idea to launch while reducing token usage, preserving context,using 140 skills, and blocks drift, hallucinations, & unsafe actions.

Dataset for Training and Evaluating LLM-Based SOC Agents

The financial operating system for AI agents. A single HTTP client that intercepts '402 Payment Required', routes across x402, L402, and MPP, persists credentials as recoverable assets, enforces per-envelope budgets, and emits a structured trace.

A 100% local, all-in-one dashboard for the CORSAIR Xeneon Edge (and any Windows browser). System monitor, media & mic, a voice AI that can build dashboard pages for you, a Stream-Deck grid, RGB lighting, and Twitch/OBS control. Free, open-source, no account.

RunComfy AI media skills for Claude agents — incremental publish test

Lightweight personal assistant on telegram / discord based on Pi Agent

A Databricks framework for quick Agent solutions

Patch Codex's missing features with agent skills.

Unified search, crawling, and archiving toolbox for AI agents and automation scripts.

Agent Library personal knowledge base with a search and retrieval system MCP Server and CLI. Preconfigured local models and support for Text, images, OCR/vision, and code embeddings. Use over MCP with (Claude, Cursor, Codex, ChatGPT, etc)

An xcresult parser CLI for CI and AI coding agents.

MCP server: Project PLATEAU 3D city data as scene-editing and glTF export tools for creative LLM agents.

Silicon Society Sandbox (SiliSocS) is an versatile and extensible experimentation system for EASE-configured generative multi-agent simulations

A comprehensive collection of expert AI Agent Skills for Google Gemini, featuring a powerful CLI to convert and optimize Claude Code agents for the Gemini ecosystem.

MongoDB-native long-term memory for production AI agents

jurisd is an open, local-first research and drafting workbench for AU/NZ law. It gives you, or the AI assistant you already use, fast answers from legislation and case law where every claim traces back to the primary source. It runs locally by default, so confidential and privileged work never has to leave your machine.

TASK-PLAN v2 dashboard and templates for auditable multi-agent software work

QevosAgent is a minimalist agent runtime for real tool-calling workflows with persistent artifacts, recoverable memory, and observable execution.

A CLI tool that provides a collection of reusable, framework-native AI agent components

The Claude Design for IG carousels — one engine, swap a brand pack, get a whole new style, with a built-in AI reviewer. ｜ IG 圖卡版的 Claude Design — 一套引擎，換一份 brand pack 就換一種風格，內建 AI 審稿員。

Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model

基于强化学习的 LLM Agent 长链路决策优化系统

Reviewer 2 is now your agent. Autonomous research bot that iterates from idea to manuscript.

OneCode 是一个参考Claude Code实现的Code Agent。它用可控的工程框架约束大模型完成编码任务。它的主循环采用 Hooks 机制实现扩展，通过上下文工程与工具调用支撑任务；运行状态可中断、可恢复，并提供结构化的 trace 与 error log 用于观测与回放。可用于学习与二次开发。

A control plane for long-running agent loops: agents prompting agents on Pi, run history in Neon, a React dashboard, deployable with Retool.

AI-assisted coding setup that helps you spend less time re-explaining context, and more time shipping with better output. Includes a custom spec kit, memory, agent and skill framework.

A centralized analytics dashboard for enterprise GitHub Copilot adoption. Visualize usage metrics, license allocation, premium request consumption, and AI model activity — all sourced from the GitHub Copilot Usage Metrics API.

The open-source cockpit for AI coding agents. Map your repo, control what your agents can touch, and see what changed before you ship.

OpenClawMU — Multi-Tenant Fork of OpenClaw