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 90 of 376
(ACL 2026 Findings) Learning on the Job: An Experience-Driven, Self-Evolving Agent for Long-Horizon Tasks
Always keep your codebases ready for Agents. Improve any coding workflow by atleast 2x by maintaing a live, pluggable context layer per repo that creates and maintains Agents.md
8-layer defense-in-depth security for agentic AI. Covers OWASP ASI Top 10 across ingestion, storage, context, planning, execution, output, inter-agent, and identity layers.
A Chrome side-panel browser agent
A comprehensive Python SDK for interacting with UiPath's Automation Platform
The UI5 MCP server improves the developer experience when working with agentic AI and the UI5 framework.
Your CLAUDE.md stopped working at 200 lines. Generate scoped skill files from your import graph, auto-sync on every commit. Claude Code and Codex.
Microsoft Graph Skill for Agents
5 Claude Code skills for product managers. Drop them in your .claude/skills/ folder and go.
Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases. Triggers on: new/empty project setup for AI agents, AGENTS.md or CLAUDE.md creation, harness engineering questions, making agents work better on a codebase.
Ship with less chaos. Flux is a fast, simple Kanban board with MCP integration so your LLMs can help run the show.
Production-ready multi-agent academic illustration system with Chinese GUI, background generation, plot workbench, and portable result bundles. Extended from PaperBanana.
Open-source Claude Code skills and Codex skills for AI-first work. Audit, re-engineer, and bootstrap projects with AI-first design principles.
An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27 "sandboxes" scored.
PCLA: A framework for testing autonomous agents in the CARLA simulator
MCP server for scraping LinkedIn, Facebook, Instagram profiles and Google search.
AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.
Skardi is an agent data plane that gives AI agents data autonomy.
Autonomous AI backend for deep research AI applications.
Self-improving Agent orchestrator for all knowledge work
Codex IDE integration for Emacs
agent skills, starting w/ context engineering
AI驱动的系统性学术文献回顾工具 | AI-Powered Literature Survey Tool with 8-Phase Workflow & Agent Swarm Architecture
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
从数据到智能:企业级数据平台的构建、演进与 Agentic BI 实践。一个数据开发的八年数据工程手记:从 0 到 1 构建企业级医药数据平台,再到 Data + AI 转型下的 Agentic BI。
Infra for computer agents and software factories
Open Source panel to orchestrate agents, terminal, and git
Fast, self-hostable sandboxes for agents
把 SillyTavern 角色卡迁移成 pi coding agent 可运行的文字游戏。
Shape rough requests into evidence-backed /goal completion contracts — an Agent Skill for Claude Code and Codex
My submission to the ARC-AGI-3 Developer Preview Agent Compitition.
メモリ機能が強力なhermes-agentと、日本語検索に強い外部メモリvecmemoriを活かし、長文に耐える小説を企画/プロッティング/執筆するためのskills.md
The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. Industrial protocols (OPC-UA, Modbus) on the roadmap.
Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Gemini, Kimi, and more) through a QA agent and grades them on workflow compliance against scenario criteria and deterministic post-checks.
基于 LLM 的智能求职助手:AI 岗位匹配 + 千岗千面招呼语 + 自动投递(Edge/Chrome 扩展)
Run a team of AI coding agents. On your machine. Local-first orchestration for Claude Code, Codex, OpenCode, Antigravity, and Copilot.
让任何 AI agent 变身个人 IP 打造策略师的开源 skill · 耳总个人实战经验沉淀 · 诊契行盘闭环 · 不碰剪辑
ADE — an agentic development environment for macOS. A roster of persistent coding agents, each with its own repo, runtime CLI, and memory.
All-in-One Desktop Agent Skills Utility. Welcome to the Skill Zoo, where all your skills live!
##Note: this is really old now, and the janky pseudo methods are probably only working out of sheer coincidence. This was an early experiment in how jargon & combinations of artificial weights in pseudocode can influence LLM behaviour without retraining. This was probably ahead of its time
Ready-to-use Fine AI agents for automating development workflows
[NeurIPS 2024] MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
开源人工智能,基于开源软硬件构建语音对话机器人、智能音箱……人机对话、自然交互,来宝拥有无限可能。特别说明,来宝运行于Python 3!
An Interface for AI built for cybersecurity professionals
AI Tour Build Your First Agent with Azure AI Agent Service
Code for the talk on coding the ai coding agents
jemma & her ai agents that build software
Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.
WeCom (企业微信) channel plugin for OpenClaw - AI agent integration with WeChat Work
LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents (ICLR 2024)
MTConnect Agent for Fanuc CNC Equipment using Focas over Ethernet
API proxy for calling endpoints using `agent` cli from Cursor
All-in-One Harness Agent Terminal
Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"
A simple example of how to implement vector based DQN using PyTorch and a ML-Agents environment
AI RC Car Agent that using deep reinforcement learning on Jetson Nano
7x24 AI Agent that saves and makes money autonomously.
Clawome - AI Agent Browser | Smart Web Browsing Tool Give your AI agent eyes and hands on any website. Open-source smart browser tool for AI agents to efficiently browse, read, and interact with web pages.
Brain Agent for Large-Scale and Multi-Task Agent Learning
DART-GUI: Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
Identus Cloud Agent
基于Agent技术实现的Java内存马查杀、防护工具。
Open-Source AI-powered web browser. Browse the web with your own LLM API key. Alternative to Dia / Comet.
Deploy and manage AI agents in seconds.
Single-File AI Chatbot UI with Multimodal & MCP Support: An All-in-One HTML File for a Streamlined Chatbot Conversational Interface
A Claude Code project template with pre-configured specialist agents, living documentation, Conventional Commits conventions, and placeholder-based structure — copy, fill, ship.
Demos and sample apps using Chroma
Anything Copilot enables you to open any sites in a multi-tab sidebar or popup, enhancing accessibility and productivity while maintaining privacy and flexibility.
Code for training embodied agents using IL and RL finetuning at scale for ObjectNav
Open-Source data analyst your team actually owns. Ask in Slack, on Mac, or via MCP. Byaan learns your business. Read-only by design
Alfred: An open-source Data Assistant for domain adoption, powered by agent skills, semantic knowledge graphs and relational data.
Minimal pi coding-agent re-implementation in Zig
Claude Code plugins & extensions - Hooks, commands, and agents for developer productivity and workflow automation
ClawdSecbot is a professional AI Bot security protection solution, providing security capabilities including real-time threat detection, prompt injection protection, and security auditing to comprehensively protect your AI applications. ClawdSecbot 是一款专业的 AI Bot 安全防护解决方案,提供实时威胁检测、提示词注入防护、安全审计等安全能力,全方位保护您的 AI 应用安全。
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
[ACL 2026 Findings] Repo for paper "Agentic-R: Learning to Retrieve for Agentic Search"
Craftsman is an powerful generic coding Agent for GitHub Copilot. It provides a Plan agent that does extensive interview to understand the need and a Ralph implementation loop to implement most plan in a single premium request.
Bridge OpenCode, Ferrum, and other ACP-compatible agents to Matrix, Slack, Mattermost, WhatsApp, Discord, Telegram, and Web—with permission-based security.
给 AI 一篇文章,自动生成一款可以玩的 RPG Maker MZ 游戏
Vue AI Chatbot Template made with Nuxt UI, Vercel AI SDK, Vite and Nitro.
一个基于 Hermes 的 agent skill:每天自动从 arXiv 抓取论文,用 AI 生成中文摘要和作者单位,推送到飞书,并提供本地静态阅读网站。
Collection of pi-mono extensions
Microsoft 365 Copilot APIs Client Libraries
The self-evolving coding agent that learns from your entire team and codebase. Less syncing. Less waiting. Deliver at the speed of thought.
🚀 Way Back Home
"Never send a human to do a machine's job" - Open Source AI hacking agent
Seedance2 视频创意技能包:100+ 镜头词库、Seedance 2.0 全模态 API CLI,兼容 OpenClaw / Cursor / 任意 Agent 平台。AI Agent skill for ByteDance Seedance video generation. Creativity gate (memorability / surprise / emotion / narrative), zero-copy ideation from images, 100+ cinematography terms, Seedance 2.0 multimodal API CLI. Works with OpenClaw, or any agent platform.
AgentHER: Hindsight Experience Replay for LLM Agents
Project context for AI coding agents — lazy-loaded per project, with an agent-native Kanban, idea canvas, and spec-driven task creation. For OpenClaw and external agents.
Curated list of Agent Skills for AI coding agents like Claude Code, Codex and Cursor.
Official repository for SaaS-Bench: realistic, locally deployable SaaS workflows for GUI agent evaluation.
Agent Development Life Cycle — Build, deploy, test, and optimize Agentforce agents using Claude Code skills and Agent Script DSL.
AI Agent Skill for automated vlog editing. Feed raw footage, get a finished video. Powered by ffmpeg + Whisper + Vision API.
MCP server that lets Claude Code and other AI agents work through large PDFs, and whole folders of them, without overflowing context: hybrid semantic + keyword search, selective page reading, tables, images, OCR, chart data, and multi-column/CJK layouts.
OSINT Skill for AI agents (Claude Code, OpenClaw, Codex, OpenCode) — from a name to a scored dossier with psychoprofile, career map, and confidence grades. 55+ Apify actors, 7 search APIs, swarm mode. Early Beta.
Standalone MCP server for cross-pane AI agent communication via tmux. Lets Claude Code, Gemini CLI, Codex, and Kimi CLI talk to each other through tmux panes.
OMem (Office Memory) — local-first memory that automatically ingests your real work (mail, calendar, notes, files) from where it already lives, into a Markdown wiki any AI agent can query. macOS today; Windows coming.
A TRPG Agent with a UI for a better solo gaming experience.
Forge a working, testable, publishable MCP server in 30s. TypeScript or Python, with example tools, the Inspector and tests included.
A unified anti-dead-loop toolkit for LLM agents — loop detection, budget ceiling, state stasis guard, and circuit breaker in one library.