Framework
Custom agents
37,503 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
37,503 agents · ranked by popularity · refine in the directory →
Custom agents — page 56 of 376
The Kubernetes operator for K8ssandra
Testing WASM-powered AI agents
Work seamlessly with Notion from the command line. Full Notion API coverage in a single binary.
LLM based Literature Search Agent. 一个面向研究者的文献发现工具，支持用自然语言发起检索、自动迭代查询、扩展候选论文、排序结果并导出可复核的文献列表。
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.
Ringer — parallel AI-agent swarm orchestrator. Ringside — its native mission-control HUD. Fable-quality output without Fable-level burn.
Make Payments Crypto Native. MugglePay makes merchants and AI agents accept crypto and sell more with it.
Hyperledger Aries Framework Go provides packages for building Agent / DIDComm services.
Pixelize the real world on-chain
a collection of NLP projects&tools. 自然语言处理方向项目和工具集合。
A skilled virtual assistant for Obsidian.
Sample implementations of AI Agents and MCP Servers running on AWS Serverless compute
Benchmark CLI for comparing AI coding agents on TypeScript workloads.
open source assistant hybrid using small models (2b - 5b) and gemini , with image and agentic tool capabilities and integration of RAG with effiecient memory. android support using adb
A template for building WhatsApp agents using LangGraph and Twilio. This project enables you to deploy AI agents that interact with users via WhatsApp, process messages and images, and invoke custom graph-based agents. It integrates with MCP and runs on the LangGraph Platform.
A collection of AI agent skills for Clawdbot, Claude Code, Codex
让 Agent 直接操作真实 Chrome 的 MCP 服务，支持页面扫描、CDP、截图与物理输入
Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.
Community collection of Apify agent skills for AI coding assistants
让101个Agent合作为你打工：调度 Claude Code、Codex、OpenClaw 的 Agent Company 工作台。
BrandDocs is a set of agent skills that learn your existing Word, PowerPoint and Excel templates and generate new on-brand documents from them. Unlike generic AI document generators, it preserves brand, structure, styles and formulas by construction. Built for Claude Code, Codex and compatible AI agents.
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
Bot framework for Max messenger — router, middleware, context
[ACL 2024] AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning
Baseline rules files to improve the security of AI-generated code (Claude, Cursor, Copilot + more)
OpenClaw 中文实战库：192 个可复制使用场景，从部署到5分钟上手到完全精通。案例覆盖自动化、内容创作、运营增长与安全使用。
A visible workspace for AI agents to collaborate as a single team.
🪞 Make your agents recursively self-improve
Mission control for the One Person Studio — run a fleet of AI coding agents in parallel without losing your mind. Kanban + git worktrees + tmux for Claude Code, Codex, Gemini CLI, OpenCode and any shell agent. Not an IDE.
PrismOS Local-First Agentic Personal AI Operating System | Spectrum Graph + Refractive Core + Multi-Agent Collaboration | Patent Pending US | 100% Local, Zero Cloud | Tauri 2 + React + Rust
A governance harness for AI coding.
Consulting firm-style PowerPoint design system for AI agents. 70 layout patterns, flat design, python-pptx. 麦麸风格PPT设计系统。
Mimeograph an expert into a SKILL.md or AGENTS.md for your agent.
The first self-evolving AI agent. Rewrites its own source code in real-time. 6 AST mutation strategies. Absorbs GitHub repos autonomously. 7 autonomic drives. Standalone CLI. Works anywhere.
Vibe Pentest（AI 渗透测试）是一款基于 AI Agent 架构的自动化渗透测试工具，采用多 Agent 并行执行架构，能够对 Web 应用、API、管理后台等进行全面的黑盒渗透测试（包括业务逻辑漏洞评估），输出稳定可靠的安全报告，并提供可落地的整改建议。
MAX API Next 社区是由来自科研机构和高校的 AGI 爱好者组织发起、维护和运营的研究驱动型技术社区，聚焦 AI Models 与 Agents 治理方向，致力于建设面向 AGI 应用时代的开放基础设施。社区关注多模型与多平台接入、国产模型持续适配、AgentOps 工程实践、成本审计、权限与安全边界、私有化部署和长期运营优化，目标是把模型服务、Agent 应用、用户组织和上游平台之间的共性治理问题沉淀为稳定、可复用、可持续演进的工程能力。
🧠 Cortex - Universal AI Agent Memory Service
Give Claude its own dev team: one supervisor, four specialists, and bulletproof plans/builds without losing context.
Client and server-side state management library
OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.
Code search MCP for Claude Code. Make entire codebase the context for any coding agent. Embeddings are created and stored locally. No API cost.
🚀 Desktop tool for extracting code context to enhance AI-assisted development. Visualize project structure, export multiple files with one-click, and get more accurate suggestions from AI assistants while keeping your code private.
谷歌推出25天AI Agents课程，作为 2025 年最昂贵圣诞节礼物！
Computer-Use SDK for E2E QA Testing
Give your AI coding agent a personality. Composable persona + style + skills for Claude Code, Codex, Gemini CLI & OpenClaw. Ships Tech Persona Card v1.0 spec.
CLI tool for Linear.app with JSON output, smart ID resolution, and optimized GraphQL queries. Designed for LLM agents and humans who prefer structured data.
All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, TRON), web/API security, and submission-ready reports for HackerOne, Bugcrowd, Intigriti & Immunefi.
Structured data gathering from any website using AI-powered scraper, crawler, and browser automation. Scraping and crawling with natural language prompts. Equip your LLM agents with fresh data. AI Studio JS SDK for intelligent web data gathering.
The Commercial Action Layer for AI Agents. Tools, Payments & Compute in OneShot.
Self-hosted AI code reviewer with indexed PR reviews, walkthroughs, vulnerability scanning, dependency graphs, custom rules, and a learning loop.
✨ A beautiful UI for ChatGPT and other conversational models
Gives AI agents access to React DevTools ⚛️🤖
Source code teardowns of 15 AI coding agents. What is actually inside Claude Code, Dify, OpenHands, Cline, MemPalace, oh-my-codex, Goose, Codex CLI, and 7 more. Architecture diagrams, design patterns. Every claim fact-checked.
Open source and self-hosted AI-powered customer service platform. Single-tenant, no multi-account, no per-user charges — you run the complete stack on your server.
AI writing skill that eliminates detectable AI patterns. Works with Claude Code, Codex, Cursor, Gemini CLI, and 8+ other agents.
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.
Second brain for Forward Deployed Engineers: engagement memory + execution skills across discovery, delivery, and handoff.
💬 AI-Powered Pair Programming Friend!
NFTI AI — NFTI your AI Agents & Virtual IP. Bridging intelligent agents, MCP protocols, and RWA to create a new era of digital sovereignty.
A persistent local memory for AI, LLMs, or Copilot in VS Code.
An AI Agent for Fully Automated Multi-omic Analyses
BlacksmithAI is an OPEN-SOURCE advanced penetration testing framework that leverages multiple AI agents to automate security assessments. The system orchestrates specialized agents through a complete penetration testing lifecycle, from reconnaissance to post-exploitation using professional security tools in a controlled environment.
Give AI coding agents the context they need to ship production-quality software.
Cross-agent session resume skill for Claude Code, Codex, Antigravity, and OpenCode.
Office AI Native Plugin，Support Excel/Word/PPT/WPS（Office AI intelligent agent plugin based on Visual Studio+VSTO+VB.net (compatible with WPS).）
Multi-agent collaboration engine — AI agents that work as one
Telegram ↔ tmux/herdr bridge for Claude Code, Codex CLI, and Gemini CLI. Monitor output, respond to prompts, manage parallel sessions. Control AI coding agents from your phone.
Terminal-Bench Science: Evaluating AI Agents on Complex Real-World Scientific Workflows in the Terminal
SAfactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
OmniFusion — a multimodal model to communicate using text and images
Semia, security audit for AI agent skills.
Build an AI Telephony Agent for Inbound and Outbound Calls
OriginTrail Decentralized Knowledge Graph network node
Carry context across coding agents/editors/IDEs - Cursor/Windsurf/Claude Code/Antigravity
Multi-Agent Constrained Policy Optimisation (MACPO; MAPPO-L).
ai agents for trading
The OpAgent framework is used to automate web browser operations, achieving State-of-the-Art (SOTA) performance on the WebArena benchmark.
从零走向AGI之路！！！旨在深入了解通用人工智能（AGI）的发展路径，从最基础的概念起，逐步构建完整的知识体系。涵盖AI Agent、RAG、MCP、具身智能、大语言模型、多模态、数字人、AI绘画、AI视频等！！
Source code of LogicRAG at AAAI'26.
生产级 AI Agent 技能集，辅助AI Harness应用于企业开发，覆盖代码审查、代码安全审计、TDD、需求工程、实施计划与子代理编排、架构设计、调试、前端开发与技能创建全流程。
Generate design system documentation for your UI components, directly from your AI agent. Renders into Figma or a portable .md file. Works with Cursor, Claude Code, and Codex.
An MCP server for academic paper search that integrates with AI assistants (e.g., Claude Code, Cursor), enabling them to search and retrieve academic paper metadata.
X-ray vision for AI agent sessions — a transparent HTTP proxy and dashboard for Claude Code
Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, 14 supported tools.
An agent design team you control: 10 agents that run an inclusive design process while you direct.
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
ReactBench is an evaluation for coding agents on realistic React work
a comprehensive and critical synthesis of the emerging role of GenAI across the full autonomous driving stack
Deep Learning / NLP tutorial for Chatbot Developers
Python client for Antarys vector database, optimized for large-scale vector operations with built-in caching, parallel processing, and dimension validation.
[unmaintained] Make seq2seq for keras work
🤫 AI-native secrets manager. Agents use secrets without seeing them.
[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
An Excel AI agent that uses MCP tools to let LLMs read, edit, and automate Excel spreadsheets.
AI agent skill for Bitget Wallet — token swap, cross-chain bridge, and gasless transactions via Order Mode API. Supports 7 EVM chains + Solana.
🦉 Augur — 多智能体投资分析系统。13位虚拟投资大师独立分析，加权共识机制，Bloomberg风格Web仪表盘。
GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex CLI, and Kilo Code.
Xmem is a India's First open source multi-modal, multi-agentic long‑term memory layer for AI agents.
Agent Skills for Langfuse, the open source LLM engineering platform for tracing, prompt management, and evaluation