Framework
Custom agents
46,364 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
46,364 agents · ranked by popularity · refine in the directory →
Custom agents — page 37 of 464
Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard, references, generation, editable first cut on a real timeline. Local-first: projects, prompts, and keys stay on your machine. No account, no telemetry.
Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks
MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build animations, and an independent critic review before delivery.
Clip any video into a narration recap with claude code skill|用 claude code skill 把任何视频剪辑成中文解说视频,支持剪映导出
Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)
[ICLR 2023] Come & try Decision-Intelligence version of "Agar"! Gobigger could also help you with multi-agent decision intelligence study.
[SIGIR 2024 perspective] The implementation of paper "On Generative Agents in Recommendation"
Orchard: An Open-Source Agentic Modeling Framework
A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use
React design system for agentic interfaces. Every free BoardUI component as source, with a working AI chat app on your own model key as the homepage.
Video Search and Streaming Agent 🕵️♂️
Vision-Augmented Retrieval and Generation (VARAG) - Vision first RAG Engine
Scenario-focused sample applications that help you get started with building Microsoft Teams App.
AI short drama & micro-drama video generator — turns any idea into a complete short-form drama using multi-agent AI pipeline (screenwriter → storyboard → frames → video). Seedance 2 VIP, Kling 3.0 Pro, Veo 3.1, Sora 2.
🔥 AI 深度融合 V8引擎 的开源低代码平台。AI 本地 V8引擎 编程(VS Code Copilot/Cursor/Claude + MCP + Skills)、AI 在线编程、AI 数据分析。.NET10 + Vue3 + 跨数据库/跨平台,分布式架构、高性能(L1/L2级缓存)。始于2014年(基于Avalon.js),2018年使用Vue重构,于2025年开源。
A Trusted Human-Multi-Agent Reinforcement Learning Interaction Framework
A curated list of awesome AI agents inspired by OpenClaw
Open-source, channel-native agent gateway for Slack. Route team threads to Claude Code, Codex, OpenCode, Docker, HTTP agents, and custom CLIs with policy, approvals, memory, audit logs, and artifacts.
Claude Code–style dynamic workflows for Pi: code-mode subagents with real model routing, journaled resume, git-worktree isolation, cost accounting, an interactive /workflows TUI, an /ultracode standing opt-in, and deep research.
A precise user agent parser and device detector written in TypeScript
Task management, but AI agents do your tasks. Self-host on Cloudflare.
AgentX is a GPU-accelerated, cross-platform desktop application that brings AI agents to your workflow. 跨平台、原生 Agent 桌面。
Install agent skills from npm
大愚Agent
TUI and CLI for browsing AI models, benchmarks, coding agents, and statuses for AI providers.
Open-source agent skills for generating editorial-style information cards from natural-language input.
Learn agent fundamentals from scratch in one day (about 9 hours)! I wrote this tutorial to show that agents are actually very simple. 零基础一天 (9小时)学完agent!写这个教程就是想告诉大家,Agent其实非常简单!
The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex & OpenCode from your browser or any chat app.
Agent behavior clone for browser using, targeting general GUI using and distributed trajectory collecting.
A collection of agent skills for designers who prototype and build with AI coding tools. These skills encode design process so AI follows a structured path instead of producing random output.
Official DESIGN.md files published by companies themselves. First-party design systems that AI agents read to generate consistent UI.
Web UI for Pi Coding Agent that keeps sessions alive in real workspaces.
Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.
A context and memory system for AI coding agents. Persistent memory, personal rules, skills, and scheduled observations
⚡️ A curated library of Agent Skills focused on Jetpack Compose performance.
PMG protects developers, AI agents from malicious open source packages using proxy, sandbox and SafeDep's threat intelligence feed.
Full agentic runs for Slay the Spire 2. A mod that exposes in-game state, and the MCP server for the mod.
A graph-native memory system for AI agents and context graphs. Store conversations, build knowledge graphs, and let your agents learn from their own reasoning — all backed by Neo4j.
The practical implementation of Aspire using Microservices, AI-Agents
An 8-stage vulnerability-discovery agent.
[EMNLP 2024 Demo] TinyAgent: Function Calling at the Edge!
World model reinforcement learning for multi-turn VLM agents. RL for vision framework (NeurIPS 2025).
KohakuTerrarium is a general-purpose AI agent framework and batteries-included app for building, running, and composing self-contained agents and multi-agent teams, with built-in tools, sub-agents, persistent sessions, TUI, and web UI.
A tmux sidebar that monitors AI coding agents across all windows and sessions in real-time
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
Your AI engineering org, governed. Ship agent-built code safely to production.
Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.
An agent to hotpatch the log4j RCE from CVE-2021-44228.
Manifold is an experimental platform for enabling long horizon workflow automation using teams of AI assistants.
A dynamic docker->redis->traefik discovery agent
vArmor is a cloud-native container hardening system that leverages AppArmor/BPF/Seccomp and NetworkProxy technologies to enforce access control from system calls to application protocols — protecting workloads including AI Agents.
Jail your AI agent
Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
Open-source task management for the agentic era. The command center for solo entrepreneurs who delegate work to AI agents.
"CatchMe: Make Your AI Agents Truly Personal"
Gift your VS Code agent a real debugger: breakpoints, stepping, inspection.
专业影视导演 Agent,基于剧本完成导演定调→节奏规划→剧本微调→分镜拆解,最终输出标准九列分镜表(xlsx); 深度融合世界顶级导演视听理论,内置数十种影片类型导演风格模板库,支持类型交叉组合; 覆盖概念超短片/短片/长片全格式,将文字剧本转化为可落地的专业拍摄方案。
Agentspan is now part of Orkes Conductor
One CLAUDE.md to make your coding agent ship like a senior engineer. Drop-in for Claude Code, Codex, Cursor, Gemini.
Android device control for hermes-agent — bridge app + Python toolset
Kun's dotfiles for agentic engineering
Extensions for pi, the terminal-based coding agent
A curated list for Self-Improvement in Foundation Model Based Agentic Systems.
中文优先的企业 RAG 知识库:可控解析、治理、切块、混合检索、重排、引用、图谱、评测与 Dify 接入。
Inter-session communication extension for pi coding agent
Agentic CAD for 3D printing
Aware - Deep Code Research Agent for Complex Codebase & Knowledge that “Act As Your Agentic Principal Engineer”
A bridge between Obsidian and Github Copilot
k8e.sh - OpenSource Agentic AI Sandbox Matrix
根据 opencode 源码编写的 agent 开发教程
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
Give your AI coding agent a design system. One command installs 400+ quality-graded company DESIGN.md references + skills into Claude Code, Codex, Cursor, and OpenCode. Free, MIT, zero AI calls.
Mantis Hack
Agent-driven creation of editable, tastefully crafted visual artifacts.
Real-time decoded feed of AI agent actions — monitor multiple Claude Code & Codex sessions, see exactly what each agent is doing, and coordinate swarms efficiently
A set of tools to connect to AI agents, to allow them to use Todoist on a user's behalf. Includes MCP support.
Openclaw多智能体协同系统 | Multi-Agent OS for Decision Makers — 基于 OpenClaw (Clawbot) + Slack,让 AI 团队各司其职、自主稳定迭代。
A Linux based operating system hardened and purpose built for AI agents
她不一样 恋情分析室 — 微信聊天记录恋爱分析 Agent Skill (曾用名:她爱我吗?)
An SSH tool dedicated to addressing all pain points · (macOS/Windows/Linux/Android/iOS)
The verifiable coding agent runtime. Define your coding agent's process in natural language with stages, checks, and approval gates instead of hoping it follows your instructions.
An SSH tool dedicated to addressing all pain points · (macOS/Windows/Linux/Android/iOS)
A set of coding style guidelines for Vibe Coding or SWE-Agents that maximize efficiency and improve human readability.
The model, data and code for the visual GUI Agent SeeClick
Agent skills to help you build products your users love.
토스증권 CLI·MCP 서버. 공식 Open API의 계좌·시세·주문에 WTS 전용 수급·AI 시그널·배당·관심종목을 더해, 터미널과 AI 에이전트에서 조회·자동화합니다. 비공식 프로젝트.
智能渗透Agent Manager/Observer/Solver 多角色架构,基于 pi-mono SDK。
📄→💡 Paper2Patent:面向科研成果转化的论文转专利智能模板库,提供 Flash/Pro Prompt、专利附图生成与 Agent Skills,辅助规范生成中国发明专利申请文本。
Local-first browser AI video editor with WebGPU and agent skills helps to create any videos
Orca is a DeepSeek-native coding agent.
Official Code Repo for UniVA: Universal Video Agents
"Unit tests" for your agent skills
🚀 BunkerM: Eclipse Mosquitto MQTT management platform, featuring dynamic security, MQTT ACL management, monitoring,and AI integrations
Interactive brainstorming UI for OpenCode agents - multi-question forms, decisions, and real-time feedback
The official "Long-Term Memory" for Godot 4.7+ AI Agents. A high-density library of 97 expert skills and 27 genre blueprints, providing audited, strictly typed GDScript patterns, automated persona orchestration (Analyst, Auditor, Builder), and production-grade game engineering.
暴走皮皮虾之代码发布系统,是现代的持续集成发布系统,由后台管理系统和agent两部分组成,一个运行着的agent就是一个节点,本系统并不是造轮子,是"鸟枪"到"大炮"的创新,对"前朝遗老"的革命.
A Java agent that rewrites bytecode to instrument allocation sites
Official implement of paper "AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation" [EMNLP 24']