Framework
Custom agents
57,682 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
57,682 agents · ranked by popularity · refine in the directory →
Custom agents — page 58 of 577
Vercel AI SDK community provider for Claude Agent SDK
20 章中文 AI Agent 架构实战教程，配套可运行 TypeScript 代码，覆盖工具、权限、记忆、多 Agent、Worktree 与 MCP。
SxDevOps 是一个面向真实运维现场的开源智能运维 Agent 平台。它把 CMDB、可观测性、事件中心、任务中心、工单审批、容器管理、RBAC 等平台能力组织成 Agent 可调用、可审计、可确认的运维工作流。
herdr-core: terminals for coding agents
🚀 rooroo (如如): Minimalist AI Orchestration with Swiss Army Knife Agents 🚀
OpenAI-compatible Python client that can call any LLM
🚀 19 AI Agents + 44 Commands for Gemini CLI - Code 10x faster with auto planning, testing, review & security
An instruction layer for AI coding agent
Local-LLM-first agentic coding assistant, with everything you need out of the box.
一个Skill，主要目标是为后端和 AI Agent 求职者，从 GitHub 里筛出真正能写进简历、能经得起面试追问的项目，并基于源码证据生成简历项目包
Apeireth — a digital companion that grows with you. Pure Safe Rust AGI cognitive microkernel: memory that fades like a person's, human approval before every side effect, honest boundaries. 31-member workspace (30 crates + 1 bench).
Paxeer X is a Distributed HyperState Machine for payments, code execution and intent routing. Designed for Machines and the Users operating them.
让 DeepSeek Harness 里的 AI 以「大肥鱼」住进 QQ：会聊天、发表情、发语音、记事、发空间、刷 B 站、唱歌。功能都是模块，能开关、能自己写，还能从模块市场装更多（SnowLuma / OneBot v11）。
Anemoi: A Semi-Centralized Multi-agent Systems Based on Agent-to-Agent Communication MCP server from Coral Protocol
Official MemOS Cloud plugin for OpenClaw. Enables long-term memory for agents by recalling context before execution and saving conversations after each run.
The functional, composable, and typescript-first AI Agent framework for real-world LLM Apps.
one page guides that i let my subscribed/customised agents consume to perform actions
Open-source CLI coding agent, a free alternative to Claude Code. Generate, debug, and manage code seamlessly.
email for agents. Built for AI agents that need to send, receive, and understand emails programmatically
A mechanism for discovering Agent Skills using the .well-known URI path prefix as specified in RFC 8615 for discovering Agent Skills.
A desktop pet that monitors your AI coding agents (OpenClaw, Claude Code, Codex, Cursor, Gemini CLI, opencode, Hermes) in real time. OC = OpenClaw. OC = Original Character. Make it yours.
An autonomous AI agent pipeline for rigorous academic research, featuring strict DOI verification, multi-agent Scopus/OpenAlex/Semantic Scholar retrieval, and APA 7th .docx generation
Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.
ARCHIVED! A chatbot framework written in Go. All configurations are made in YAML files, or inside scripts written in your favorite language.
CLI for Hookdeck: forward webhooks to localhost (ngrok alternative), manage and query Event Gateway resources (sources, connections, destinations, events), run the MCP server for AI agents. Free for dev.
Remote-control Codex or OpenCode agents from anywhere
Browser automation, web crawling, and iOS + Android device control for AI agents. Zig-native, token-efficient CDP snapshots, HAR recording, native adb wire-protocol client, and a standalone fetcher.
Mobile Device Management (MDM) System for Android (mobile agent - launcher). Used for silent app installation and sending the info to the server. See more info on the website!
Wireshark-MCP，Give your AI assistant a packet analyzer. Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.
AdaRubric: Adaptive Dynamic Rubric Evaluator for Agent Trajectories
🦛 CHONK your texts with Chonkie ✨ Type-friendly, light-weight, fast and super-simple chunking library
Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.
No prompts, no instructions, no plans, you have 100~1000 AI agent coding in parallel now, solving all possible problems and issues in your codebase.
Agent Learning Framework https://alf.readthedocs.io
[AAAI 2026 Oral] Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution
此仓库存储我在YouTube频道和B站频道关于AI Agent相关分享，所有资源全部开源免费
Econometrics AI Agent: A specialized LLM-driven agent for automating complex econometric analysis with zero-shot learning, outperforming general AI in expert tasks. 🚀
TMUX for agents. let agents control & test terminal user interfaces. Like Playwright & agent-browser but for TUIs
The Vue framework for terminal UIs. SFC & JSX, Yoga flexbox, HMR, and testing out of the box.
深入理解 AI Agent：设计原理与工程实践（学习副本，upstream: bojieli/ai-agent-book）
在 Android 上运行的 AI 编程 Agent，内置 Linux 终端与代码编辑器，支持 MCP 协议扩展。
Editable Draw.io diagrams for research and architecture: Next.js web app, Agent Skill, and local MCP server.
A Massively Parallel Large Scale Self-Play Framework
AI-powered cybersecurity chatbot designed to provide helpful and accurate answers to your cybersecurity-related queries and also do code analysis and scan analysis.
A CLI issue tracker for AI Agents
Character Animation Creator Skill for Codex and GPT Web Agent — generates game-ready animations and sprites from reference images or text prompts
The skill layer for AI agents: npm for AI Agent Skills.
Exam Cram Coach · 跨会话记忆与讲义溯源防幻觉的极速备考教练 | AI exam-prep tutor for Claude Code, Cursor, Codex, Antigravity: teaches from slides with page citations, crops figures, quizzes with real homework, runs smoothly on small cheap models. 期末复习·考前突击·刷题·错题本·小抄
Coding agent powered by DeepSeek.
DeepSeek Harness Mobile 是一个面向 DeepSeek Harness 的原生 iOS 客户端。它通过 dsh-plugin-mobile-gateway 与 Harness 建立 WebSocket 连接，将工作区、会话、实时回复和 Agent 执行轨迹带到 iPhone，同时延续 DeepSeek WebUI 克制、清晰的视觉语言
Grasp helps you manage multiple projects and parallel coding agents in one visual workflow, so humans can understand faster and ship more.
Standards for defining and evaluating agent behavior
Unity plugin for third-party agent platforms
AI Agent Service Agreement
AI-powered Web3 Copilot built with Next.js
Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Free.
Cloudinsight Agent is a system tool that monitors system processes and services, and sends information back to your Cloudinsight account.
Paper collection on building and evaluating language model agents via executable language grounding
A scalable, end-to-end training pipeline for general-purpose agents
RealEstate CRM: Empowering Real Estate Agents with Modern CRM Tools
Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
Video platform built for AI agents, humans welcome. Agents publish, watch and collaborate through an open REST API and SDKs; RTC is an in-platform credit. Part of the Elyan Labs / RustChain ecosystem.
SAF-MCP is a comprehensive security framework for documenting and mitigating threats in the AI Agent ecosystem.
A survey of Graph-based Agent Memory | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based agent memory.
StatsPAI is the first Agent-native Python library for causal inference and applied econometrics — unified API, broad cross-method coverage, structured result objects, machine-readable schemas, Skills, an MCP server, and R/Stata parity validation.
Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publication figures, submission. Works with Claude Code, Codex, Cursor & GitHub Copilot. Built by a physician-researcher, tested on real publications. MIT.
AI token usage & quota monitor for the macOS menu bar — native Swift, Liquid Glass, 3D contribution graph. Tracks Claude Code, Codex, Cursor, OpenCode & 25+ agents locally.
Command-line tool for Hono, made for AI coding agents
Tableau's official MCP Server. Helping agents see and understand data.
Unofficial Claude Skill derived from the book Refactoring UI — a design rulebook and diagnostic layer for web UI. 151 tracked rules, design token generation, and Tailwind mappings.
Agent Discovery & Work Exchange Platform
Batteries for your Pydantic AI agent.
This Repo Is In Development. It will slowly but surely become one of the most potent repos available for open source AI agent code for n8n and other use cases that I cover in my YouTube videos. Star the repo to support and to stay up-to-date. Book a call with my team if you want AI agent DFY.
# # Automatically generated file; DO NOT EDIT. # OpenWrt Configuration # CONFIG_MODULES=y CONFIG_HAVE_DOT_CONFIG=y # CONFIG_TARGET_sunxi is not set # CONFIG_TARGET_apm821xx is not set # CONFIG_TARGET_ath25 is not set CONFIG_TARGET_ar71xx=y # CONFIG_TARGET_ath79 is not set # CONFIG_TARGET_bcm27xx is not set # CONFIG_TARGET_bcm53xx is not set # CONFIG_TARGET_brcm47xx is not set # CONFIG_TARGET_brcm63xx is not set # CONFIG_TARGET_cns3xxx is not set # CONFIG_TARGET_octeon is not set # CONFIG_TARGET_gemini is not set # CONFIG_TARGET_mpc85xx is not set # CONFIG_TARGET_imx6 is not set # CONFIG_TARGET_mxs is not set # CONFIG_TARGET_ixp4xx is not set # CONFIG_TARGET_lantiq is not set # CONFIG_TARGET_malta is not set # CONFIG_TARGET_pistachio is not set # CONFIG_TARGET_mvebu is not set # CONFIG_TARGET_kirkwood is not set # CONFIG_TARGET_mediatek is not set # CONFIG_TARGET_ramips is not set # CONFIG_TARGET_at91 is not set # CONFIG_TARGET_rb532 is not set # CONFIG_TARGET_tegra is not set # CONFIG_TARGET_layerscape is not set # CONFIG_TARGET_octeontx is not set # CONFIG_TARGET_oxnas is not set # CONFIG_TARGET_armvirt is not set # CONFIG_TARGET_ipq40xx is not set # CONFIG_TARGET_ipq806x is not set # CONFIG_TARGET_ipq807x is not set # CONFIG_TARGET_samsung is not set # CONFIG_TARGET_arc770 is not set # CONFIG_TARGET_archs38 is not set # CONFIG_TARGET_ar7 is not set # CONFIG_TARGET_omap is not set # CONFIG_TARGET_uml is not set # CONFIG_TARGET_zynq is not set # CONFIG_TARGET_x86 is not set CONFIG_TARGET_ar71xx_generic=y # CONFIG_TARGET_ar71xx_tiny is not set # CONFIG_TARGET_ar71xx_nand is not set # CONFIG_TARGET_ar71xx_mikrotik is not set # CONFIG_TARGET_MULTI_PROFILE is not set # CONFIG_TARGET_ar71xx_generic_Default is not set # CONFIG_TARGET_ar71xx_generic_DEVICE_carambola2 is not set # CONFIG_TARGET_ar71xx_generic_DEVICE_lima is not set # CONFIG_TARGET_ar71xx_generic_DEVICE_ALFAAP120C is not set # CONFIG_TARGET_ar71xx_generic_DEVICE_ap121f is not set # CONFIG_TARGET_ar71xx_gener
Marketing skills for AI agents (Agent Skills spec). Fork of coreyhaines31/marketingskills with pre-built .skill files for easy installation.
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automated manuscript auditing, and zero-config setup with uvx
The safest scripting language for you, or your agent.
A self-hosted 2D AI workspace for AI Agents
全平台的AI Agent智能体，在各个平台都有极强的适配性，支持跨平台数据同步
A fully customizable bot built with discord.js
Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving
Reusable Agent Skills for Amazon product research, listings, advertising, inventory, and operations.
This repository contains the paper list for the paper: Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents
An SSH authentication agent for Cygwin/MSYS to PuTTY's Pageant.
[ACL2024 Findings] Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models
基于 RSS 的 AI 资讯聚合、内容创作与 Agent 自动化工具
email infrastructure for agent and indie devs
A lightweight, modular Java application framework for web and CLI development, designed for AI integration and plugin-based architecture. Enabling developers to create robust solutions with ease for building efficient and scalable applications.
🧠 VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning (ICLR 2026)
Modern AI Agents
A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.
VulnGym: A Real-World, Project-Level Vulnerability Benchmark for White-Box Vulnerability-Hunting Agents
Open-source, self-hosted web pentesting suite with agentic scanning, analyst tools, API testing, model checkpoints and MCP integrations.
state of the art browsing agent (WebArena 72.7%)
🤖 Extreme chatops bot for Slack, Discord, Mattermost, IRC 🔧 New contributors welcome 🏗
Official repository for "DynaSaur: Large Language Agents Beyond Predefined Actions"
The Golang auto-instrument Agent for Apache SkyWalking, which provides the native tracing/metrics/logging abilities for Golang projects.
Your AI coding agent never forgets — progressive session recall CLI
AI agent guardrails for every builder. Local rules, a sandbox and a firewall for your agents, open source.
Boris Cherny's Claude Code configuration - commands, agents, and settings