Framework
Custom agents
57,772 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
57,772 agents · ranked by popularity · refine in the directory →
Custom agents — page 473 of 578
MCP context engine for AI coding agents: a local code graph answers "which files does this task need?" — folded evidence packets instead of whole files. Recall 1.000 on repos it was never tuned on, 45% fewer context tokens in a real Claude Code session. Rust, local-first, MIT.
在飞书妙搭(apaas)上用 AI Agent 开发的避坑手册 + harness。83 条实测踩坑,一条命令接入。
⚡ Governed economic agency for autonomous agents on Tether's WDK: an authorization plane, an isolated signer that re-derives every call, one agent object behind them. Testnets only, by decision — no flag widens it. Apache-2.0 — npm install && npm test. The mirror is public; the plane behind it is not.
FTShare-powered terminal financial visualization canvases for Codex and OpenCode|面向 AI Agent 的交互式 K 线、行情、新闻与数据画布
Free, open-source cross-platform desktop app for the Pi coding agent on Windows, macOS, and Linux. Projects, conversations, streamed tool activity, diffs, model controls, and graphical extensions in one native workspace.
A Cockpit plugin that turns the web console into a full file manager — browse, edit, preview, search, terminals, and Git — with integrated Claude & Codex AI CLI tabs showing a live git diff, plus fstab/mounts, SMB & NFS shares, and a GRUB editor.
Privacy-first desktop AI agent. Runs on your machine, with the models, personas, workflows, and tools you choose.
Мобильная оболочка DeepSeek Harness: Kotlin + Jetpack Compose, dsh web в proot-песочнице, русский интерфейс, мобильный UI
Pi harness as a modern app, with UI, web search, subagents, /goal, and more, all installed in one command
🌐 Drop-in skills that teach Claude Code, Cursor & Codex CLI how to automate browsers. Playwright, Selenium, Puppeteer, Web Scraping, AdsPower & more.
Product Design Agent Skills for Claude Code & Antigravity IDE
Windows computer-use MCP server (26 tools) with a human-in-the-loop approval gate: physical-input-only dialogs, signed guard switches, deny/launch lists, hash-chained audit log. 70+ unit tests, green CI.
Lightweight, accessible Astro components for AI reasoning traces, streaming state, and autonomous agent interfaces.
An AI agent that answers your phone calls, resolves the routine ones, and pulls you into the same live call when it needs you.
用自然语言查询、分析项目数据的 AI Agent
Karna — Your Loyal AI Agent Platform. Self-hosted personal AI assistant with multi-channel messaging, extensible skills, and semantic memory.
AI-directed job search system: scans target companies for matching roles and generates tailored, no-fabrication resumes/cover letters. Fork it for your own search.
Independent ecommerce Skill catalog for browser-based AI agent workflows across Amazon, eBay, Walmart, Etsy, Shopify, TikTok Shop, Google Shopping, AliExpress, and more.
A visual AI Agent workflow platform with LLM, RAG, MCP, tool calling and streaming execution.
Open-source, self-hosted alternative to Lovable, Replit and Base44. Create full stack web apps on your self hosted instances for free.
AI-Powered Code Security Analyzer. Pluto is a powerful CLI tool that uses AI to detect security vulnerabilities in your code.
Model-agnostic DevOps AI agent harness: policy, approvals, audit and rollback enforced outside the LLM. Works with Claude Code, OpenCode, Cursor, Copilot and any MCP client.
Provider-agnostic coding-agent runtime and CLI for Elixir and the BEAM
Unofficial community desktop edition of DeepSeek Harness for Windows
Experimental open-source AI coding agent in Rust
Evidence-grounded, auditable Codex skill for SCI review research and writing.
BubbleBuddy is a friendly Discord AI companion powered by Pi, Effect, and discord.js
Codespaces-ready starter for embedding a live three.ws 3D AI agent in any site
Create HTML with AI; preview and export presentations, images, and video.
众所周知,人总是要上天堂的~ 一个给 QQ Agent v0.3.1 用的技能:按车牌号下载禁漫本子、还原分段打乱的图片、打包成 PDF 发到聊天。也支持先搜后下。(小白也能上天~堂~)
AI_CONTEXT: a way to share durable project context between any AI agents and humans using the repository itself as the continuity layer.
🤖 桌面 AI Agent × ChatGPT 网页端 × GitHub:纯自然语言驱动的“云端大脑+本地双手”跨平台双向协作桥梁
Agentic AI tool: transforms raw text/notes into a strictly compliant IEEE Conference Paper (.docx) using Claude AI and python-docx
通用电商店铺首页设计 agent skill:先问出图尺寸 → 概念驱动差异化 → 生成可视化编辑器,导出任意平台尺寸图片。适配各类 coding agent。Platform-agnostic e-commerce store-homepage design skill for AI coding agents.
Smart Tutor AI for Learners, upload your learning material and learn!
A self-improving AI agent with a learning loop, multi-platform messaging gateway, and a paper-themed web dashboard.
Local-first autonomous AI agent terminal with a native Rust runtime, SQLite persistence, SAFE execution, and a React/Ink TUI.
AI-native terminal & SSH client — Harness launches DeepSeek / CodEx / Claude agents on PowerShell 7 in TUI or embedded Web UI, plus SFTP, serial/Telnet and a built-in MCP server.
P2P multi-agent scenario system for the Pi coding agent: comms-net hub (HTTP/SSE, cross-device) + one-command scenario launcher. Agents that build agents.🌱
Tools by AIs for AIs
IMA (ima.qq.com) knowledge base MCP server - search, browse, read notes, and add content to your IMA knowledge bases from any MCP-compatible agent (Claude Desktop, Cursor, Cline, VS Code, OpenClaw, WorkBuddy). MIT licensed.
Drop a card on the board, pick Claude Code, Codex CLI, OpenCode or the Hermes agent, and watch it work in its own git branch and worktree — then review, test and merge from one screen.
Playing Pokemon Red using TypeSafe Jev
Local CLI/MCP bridge that lets Codex delegate compact review, research, and planning tasks to ChatGPT Web.
The last mile of the academic figure toolchain — a Claude Code skill that draws editable, paper-exact vector figures directly in Figma via MCP. 学术绘图工具链的最后一公里
A source-aware AI copilot for NTU freshmen, built with Next.js and Vercel AI SDK.
🦞 The first physical agentic harness that participates in a global marketplace, using ASAP protocol.
A control plane for trustworthy AI agents: write product judgment once, then enforce it through typed MCP tools, git gates, demolition-first stories, evidence-judged checkboxes, and zero-trust monitoring. Ships with Claude Code and Cursor plugins, Agent Skills, and a FastMCP server.
Claude Code mode switcher for GSD, gstack, Superpowers, Oh My IPD, OMC, and OpenSpec workflows.
Share sandboxed HTML previews with public-unlisted or access-key private links. Includes a remote MCP server for AI agents.
Live waitlist server — pay to join a queue, receive a signed position token, auto-refund if never served
A governized pipeline fit for Claude Code to deliver quality output comparable to an established team of software and web engineers within modern standards
AI-Powered Inclusive Education Referral Continuity & Statutory Assessment Compliance Platform (India)
Self-hosted durable execution engine with built-in observability for AI agent runs
iOS application development skills including develop, ASO etc
Agent skills for design taste and visual judgment. Hierarchy, typography, color, spacing, interaction quality, and the invisible decisions that separate good design from great design
⚡ Ultra-fast O(1) Active Inference & Bayesian Cognitive Governor for AI Agents (Antigravity, Claude, Cursor) & Embedded Systems. Zero-alloc C11 core (<36KB) + FastMCP server.
20 AI agents for video creation, copywriting, landing pages, and ads with Remotion Studio and Agentation visual feedback
Deterministic agent loops for AI coding CLIs (Claude Code, Codex, Cursor, Kimi): worker + adversarial verifier agents, hard quality gates, automatic retries, human escalation. File-based, zero dependencies, one-click on/off.
Self-hosted AI analyst for Excel and SQL databases. 🌹
Podcast search and episode intel over the Podcast Index API, per query. Pay in USDC on Base or Solana via x402.
Fund someone else's agent task — buy a signed gift voucher, recipient's agent redeems it for execution with receipts
Normalize any booking confirmation into a portable record — ICS invite and status snapshots per query
Deploy and operate self-hosted OpenClaw on AWS, GCP, Azure or your own VM, from the command line or from your agent. A CLI and an MCP server over one implementation, with reviewable deploy plans, day-two operations, hardening, and private Tailscale networking.
VibeHQ is an open-source autonomous company operating system where AI employees collaborate to research, design, build, test, launch, market, and grow products—all from a single idea.
Run parallel AI coding agents in isolated Git worktrees with one lightweight, agent-agnostic CLI.
USB power control for the embedded bench — CLI + MCP server for AI agents (Yepkit YKUSH hubs)
Portable, local-first memory layer for AI coding agents. One .agent/ folder shared across Claude Code, Cursor and Cline over MCP. Plain files, no vector DB.
Local-first code navigation index and feature-to-evidence chain for AI coding agents: tree-sitter symbol index, project memory, YAML feature specs, an operations journal and PROVEN/FAILED proof from test runs. Rust CLI.
PolicyNIM is a policy-aware engineering preflight layer for AI coding agents.
Unified & extensible MCP server enabling AI agent connectivity to all types of lab equipment — VISA/SCPI, SSH, REST, serial, and Python environments.
🏥 [EMNLP 2026] Official Implementation of CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance
Build one AI-901 study assistant in Microsoft Copilot Studio. Inception, Build, Extend, Operate.
Connect Claude (or any MCP client) to your own Telegram in ~15 minutes: setup prompt for Claude Code/Codex, production patches (shared daemon, extra tools, multi-account), watchdog, and every gotcha that cost us hours. On top of chigwell/telegram-mcp.
Ask an AI assistant about your EPICS control system: live PV values, why a PV is disconnected, and where it appears across ChannelFinder, the Archiver and the alarm tree. Read-only by default.
A governed, local-first memory authority for AI agents.
3D cockpit for markdown knowledge vaults — synthwave force graph, reader, finder, workspace, and real-time AI-agent activity replay & analytics. Zero deps, no build step.
KORTEX OS — a local-first AI Business Operating System unifying business workflows, automation, knowledge, integrations, and intelligent agents.
Agent skill for evidence-led editorial infographics and social graphics without generic AI aesthetics
Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.
Native macOS session manager for Claude Code. APFS copy-on-write workspaces branch your real working tree — dirty state and all — in milliseconds, so several agents can work in parallel without colliding.
Local AI coding for Unity with OpenCode + Ollama. Run Qwen on your GPU with VRAM guards, Unity project context, and local task delegation.
Drive Blender headless from your AI agent: scaffold, build, animate from natural language. JSON in, JSON out.
The mate who helps you ship. Agent skills that turn your AI into a skeptical, evidence-keeping cofounder-grade companion: stage diagnosis, venture memory, kill rules.
Local-first universal session store for AI agents, powered by TOAST.
A desktop app for local usage, cost, throughput, and session analytics across Claude Code, Codex, OpenCode, and OpenClaw. | 在本地统一统计和分析 Claude Code、Codex、OpenCode 与 OpenClaw 的用量、费用、吞吐和会话。
An independent Codex-native adaptation of Claude Code Game Studios, tiered GPT-6 and GPT-5.6 routing, transactional engine packs, lifecycle hooks, and cross-platform validation.
Toolkit and libraries for running AI agents inside microVMs
SuperLily world/core: observability, authority, rendering, archive, and production runtime coordination
Claude Code skill for stunning, animation-rich HTML presentations — 88 layout presets + 34 bold templates. Build slides from scratch or convert PowerPoint into a single self-contained HTML file. No build step, no dependencies.
Recursos de la charla Harness Engineering (Chihuahua Tech Week 2026): slides, demo en vivo, guia openclaw y checklist de 7 pasos.
THEIA — The Human Environment Intelligence Aperture: a visual perception and UI computer-use plugin for Windows desktop agents.
Real message delivery per-message: Telegram bot messages and SMTP email with delivery receipts in-response
aimhooman teaches coding agents Git etiquette—keeping agent memory, internal instructions, temporary artifacts, and unwanted attribution out of human-owned repositories.
MCP server for the Ozon Seller & Performance API: 156 tools for prices, promotions, ads, orders, returns, finance and analytics. Multi-store, web dashboard, self-diagnostics. Context budget measured on a live account: a 16-response corpus trimmed from 476k to 64k tokens. Docker, SSE, MIT.
Get a Telegram push when a herdr agent finishes or blocks — reply to it to send text or files straight back into that agent. No server, no tunnel, no app.
Fast semantic code search powered by Jev. Find the relevant files, line ranges, and snippets
A gateway between AI agents and your Postgres databases. Every statement is checked against your policy and recorded before it runs.
设计与代码的声称核验:事实类对照源码,行为类跑可执行模型;含结构/依赖审查(单层与多粒度细化)、UML 审查、基线对比与导出。dsh 原生工具 + 多平台 Agent Skills。 | Claim, architecture and behaviour verification for designs and code — facts against the source, behaviour as models, plus structure review, UML review, baseline diffs and exporters.
Use Codex, Claude, and other coding agents on your Mac. Keep the same sessions going from your phone or browser.