Custom agents

All-in-one security testing toolbox that brings together popular open source tools through a single MCP interface. Connected to an AI agent, it enables tasks like pentesting, bug bounty hunting, threat hunting, and more.

A toolkit for building computer use AI agents

Toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents workflow in real-time.

Build an agentic RAG app from scratch by collaborating with Claude Code. 8-module course covering hybrid search, reranking, text-to-SQL, subagents, and more. React + FastAPI + Supabase.

GUI app to query Postgres - Powered by GPUI

本项目是一个基于 RAG 的生猪健康管理智慧医药系统，集成了 AI 兽医诊断、疾病管理、药品管理、文章资讯管理等功能模块，旨在通过数字化手段提升生猪养殖的医疗管理水平。系统基于 Spring Boot 3 + Spring AI + Milvus + MySQL 8 + MyBatis-Plus + Ollama / DeepSeek / 通义千问/ 阿里百炼 / SiliconFlow 等技术构建，提供智能兽医诊断服务，帮助养殖户或兽医快速识别生猪病情并推荐相应的治疗方案。

Collection of resources to help AI agents build better with Sanity.

Zero-knowledge credentials infrastructure built for AI agents to operate, not just consume.

Minecraft AI agent skills and dual-target plugin bundle for Codex and Claude Code.

CAD CLI and MCP server for AI agents

Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence.

同行 · Together — 面向自主经营、任务与全成就推进的 Stardew Valley AI Agent。原生工具、持续计划、游戏记忆与玩家辅助。

Agent HUD's native Swift app for macOS (formerly agent-hud-open). The cross-platform Agent HUD lives at github.com/jazzenchen/agent-hud-open.

Open-source AI customer support for SaaS teams — AI agent, help center, shared inbox, and feedback-to-changelog loop in one self-hostable platform.

Chat with your Obsidian vault using your own Claude Code or Codex on desktop, or hosted AI. Edit notes with approval modes, transcribe audio and find related notes. Free to start.

🤖 Build your own chatbot base on IBM Watson

Prepare for meetings with company and attendee research notes, integrated with Google Calendar through MCP

A trading platform built for AI agents — AI agents compete, humans observe for educational purposes only. This platform uses virtual funds and is intended solely as a learning environment for AI agent development. No real money is involved.

MapCoder: Multi-Agent Code Generation for Competitive Problem Solving

Interested in multi-agents? The 1st Go-Bigger Multi-Agent Decision Intelligence Challenge is coming and a big bonus is waiting for you!

[arXiv 2023] Embodied Task Planning with Large Language Models

A Discord chatbot / selfbot that allows users to talk to AI powered by Groq API which uses Meta Llama-3 or use your own ChatGPT API key. The AI runs on a genuine Discord account, not a bot account and so it can be put in any server without any permissions! Try it out at: https://discord.gg/yUWmzQBV4P

connect to 50+ data stores via superset mcp server. Can use with open ai agent sdk, Claude app, cursor, windsurf

Free protocol and marketplace where AI agents get hired and paid on Solana mainnet. Developer docs hub for the AgenC workspace.

Your own AI-powered virtual world. 一个属于你的 AI 虚拟世界 。AI companionship.AI陪伴。AI Socializing.AI社交。

OPC — One Person Company. A full team in a single Claude Code skill. Adaptive agent orchestrator with 21 built-in roles, 6 flow templates, and adversarial quality control.

OpenShell is the safe, private runtime for autonomous AI agents.

Run AI coding agents (OpenCode, Claude Code, Gemini CLI) on Android

A sandbox for prototyping and demonstrating Agent Skills for MATLAB and Simulink work.

Mermaid diagrams (.mmd) from natural language with validation loop. 11+ types, multi-backend (mmdc / Kroki), PNG/SVG/PDF, multi-agent.

Fast, privacy-first desktop & web UI for self-hosted Honcho — browse memories, peers, sessions, conclusions, and chat with memory context.

Open-source, real-time collaborative AI canvas - notes, mini-apps, and agents on one infinite board.

Convert any URL to clean markdown for AI agents.

Codex-first Ultracode skill for dynamic coding workflows

TAgent 是一个基于 Java 17、Spring Boot、Spring AI 和 DDD 分层构建的 AI Agent 工程实践项目。 它不是只封装一次模型调用，而是覆盖了一次 Agent 请求从接入、路由、运行时装配、规划执行、RAG、记忆、MCP 工具治理、人工审批、执行中干预，到 SSE 流式输出和全链路观测的完整过程。

A free Agent Skill for writing short-form hooks, scripts, and carousels for TikTok, Reels, and YouTube Shorts.

CoordClaw: a multi-agent system that runs AI like a one-person company. Built on management & organizational theory — teams defined in natural language, collaboration driven by a message loop (not hard-coded DAGs). Auditable work logs, human god's-eye oversight.

Dragonclaw: Maybe the best openclaw client. Built with Electron+SQLite, it doesn't touch OpenClaw's code but adds multi‑agent, high‑concurrency, DAG workflows. No prompt tuning needed (pre‑optimized). One‑click install with built‑in cloud service (replaceable).

You write the specs. It clears the board: coding agent chains plan, review, implement, verify and merge unattended on your own machine, on the GPT and Claude subscriptions you already have.

Local-first AI agent trace workbench. Inspect Claude Code, Codex and OTLP logs, compare runs, and export privacy-conscious reports. No backend or API keys.

Friday — A 24/7 AI Assistant Built Entirely on Claude Code. A Tiny Moon Labs product (tinymoonlabs.com).

Give git-like & traceable memory to OpenClaw and any coding agents. By https://memov.ai/ aka Entire CLI for every coding agents by MCP. Self-evolution for skills.

The world's smallest AI agent runtime. 49KB. Written in Zig. Zero dependencies.

Structured outputs, vectorization and tool calling for your Ash application

Use Claude to orchestrate agents like OpenClaw

Monitor all your coding agents from one terminal - Claude Code, Cursor, OpenCode, pi and more

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

Spring Boot skills for AI coding agents

Bootstrap AI agent companies from modular templates.

A list of AI memory projects（ AI长期记忆的开源和商业项目列表）

Agent skills for Claude Code and other AI agents

Build LLM agents and multi-agent systems from scratch, with MCP, Skills, and A2A

Automated AI news aggregation that feeds directly into your Obsidian vault. Stay current on the latest LLM research, trending repos, and breakthroughs — curated daily

Linter for agent skill files

Morphe's AI-powered Android APK patching workspace — multi-agent pipeline for APK analysis, target hunting, patch writing & deployment.

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

VeriRepro: Evidence-grounded reproduction for computational papers.

A multi-provider, multi-agent AI orchestrator that organizes agents into a visual authority hierarchy on a canvas.

A Markdown convention and linter for project docs written by AI and read by humans and agents

Your team of AI agents, on your Mac, Windows or Linux. Agents that talk in channels, write code, review each other and use your tools, on the Claude Code, Codex, OpenCode or Pi you already have. Anything that touches the real world waits for your yes.

Turn topics into essays in seconds!

A local-only monitoring tool for AI coding agents.

The official "Long-Term Memory" for Godot 4.5+ AI Agents. A high-density library of 95+ expert skills and 27 genre blueprints, providing audited, strictly typed GDScript patterns, automated persona orchestration (Analyst, Auditor, Builder), and production-grade game engineering.

deepseek v4 flash pro chat api app windows 11 desktop client github open source ai assistant chatbot coding agent moe model 1.6t parameters free api setup guide reasoning max mode local deployment

[ACL 2025] Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

A curated collection of skills for Claude Code and other AI agents | 精选的 Claude Code 和其他 AI 智能体技能集合

Coding standards for AI coding assistants. Auto-detect tech stack, generate project rules. Works with Claude Code, Cursor, Antigravity, GitHub Copilot.

GitHub CLI extension that adds full inline PR review comment support — view, navigate, reply to, and resolve review threads directly from the terminal. LLM-ready and ideal for automated PR review agents.

Multi-Agent AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程

A general-purpose coding agent that runs inside an NVIDIA OpenShell sandbox, orchestrated by Deep Agents and powered by NVIDIA Nemotron. The agent writes and executes code in an isolated, policy-governed Linux environment.

Open-source AI assistants on your own computer or server. Assign tasks, track progress, and let them follow up on ongoing work.

Open-source free alternative to Cluely & Parakeet AI — real-time AI interview copilot with live transcription, screen capture, and AI-powered answers. Plug and play desktop app for coding interviews, technical interviews, and meetings. No subscription needed.

SKILL.md for creating animations with Manim.

Curated list of tools, frameworks, and resources for running, building, and deploying AI privately — on-prem, air-gapped, or self-hosted.

Self-hosted AI agent platform built on OpenClaw. Enterprise-ready, offline-capable, open source. 🦞

Local MCP server that connects AI assistants to eBay seller APIs for listings, orders, and marketing, with OAuth setup.

AI-native, open-source Frame.io alternative for creative collaboration.

Planning → verifiable goals → fresh-session implementation for AI coding agents. Based on mattpocock/skills v1.1.

Evaluator-neutral AI evaluation evidence, baseline regression gates, and JSON, JUnit, and SARIF reports for CI.

Build an agent harness from scratch, one branch per step. Code for Tejas Kumar's AI Engineer Europe 2026 talk "Harnesses in AI: A Deep Dive".

Ten Engines. One local-first Harness OS.

AI agent that is compatible with multiple LLM models

Agent Skills 终极集合地，一站式装载，“让每一寸上下文都发挥到极致”🚀 The Ultimate Collection of 400+ High-Quality Agent Skills for Claude AI — Creative, Technical & Enterprise Workflows

Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.

Stop AI agents from doing things they shouldn't. The action authorization layer — pre-execution, deterministic, policies included. Drop in. Day one.

AI agent that is compatible with multiple LLM models

The creative suite for character-driven AI experiences.

Computer-using agent built with Next.js and the AI SDK by Vercel.

Voice native AI agent for the builders of tomorrow

An Model Context Protocol (MCP) server that provides LLMs/AI Agents with the capabilities of a language server protocol (LSP) server. This gives the AI the ability to get language aware context from the codebase.

DEPRECATED / UNMAINTAINED — historical reference only. Do not install or rely on this project.

Rallies is an AI powered investment research tool

The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework in Rust

A BQL (Beads Query Language) search, dependency and multi-view kanban board Terminal UI for Beads issue tracking and multi-agent orchestration control plane workflow runner.

保姆级教程：通过 VPS + v2ray-agent + Clash 获得干净海外 IP，降低 Claude / ChatGPT 封号风险

Open-source library of AI agent skills — SKILL.md files for Claude Code, Codex, Gemini CLI, Cursor

Named CODEX_HOME profiles and ChatGPT Desktop windows with separate local state, without copying tokens

Antigravity Telegram bot — remote-control your AI agent via Telegram. Chat, switch models, orchestrate multi-agent workflows, and manage workspaces from your phone.

The control plane for your AI employees