Framework
Custom agents
57,773 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
57,773 agents · ranked by popularity · refine in the directory →
Custom agents — page 481 of 578
🍟 麦麦羊毛管家 · 麦当劳会员「券 + 积分 + 活动 + 徽章」资产管家 | McDonald's membership butler: coupons, points, lottery, campaigns & 24-solar-term badges | 麦当劳程序员创意开发大赛参赛作品
Mark XLVIII is a cross-platform, real-time voice AI assistant built on the Gemini Live API that can hear, see, and understand you. It features visual awareness, autonomous task planning, and direct OS-level control to serve as an intelligent, hands-free extension of your digital workspace, So follow up to know and see new models.
MCP server for BRVM market data (West Africa's regional stock exchange): quotes, indices, BOC volumes, Sikafinance indicators and news.
Desktop-class AI software engineering IDE for Android: rootless Linux terminal, multi-agent coding teams, GitHub automation, app factory, and cloud hybrid builds.
GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution
一个高自由度的桌宠式桌面 Agent 集成框架
XiangqiBench: closed-loop evaluation of LLM agents on xiangqi endgames
PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs
Plone Volto addon that integrates Onyx chatbot agents
Give your agent a body: Embodify lets it control robots directly and become your embodied agent. Your best embodied agent is your favorite agent — with its memory, its tools and everything it knows about you. Works with Codex, Claude Code and any other agent that supports MCP and skills.
Turn any webpage into typed JSON, callable MCP / WebMCP tools, or AI-native Epistemic Context — in 3 ms, using 2.7× to 28× fewer tokens than a text scraper and up to 1,449× fewer than raw HTML
微信公众号图文排版设计器 | WeChat article layout designer with 10 preset styles for AI Agents
DeepSeek Harness native parallel side chat with hidden child sessions and on-demand parent context
A daily job search that runs itself: scrape the boards, grade every posting against your own rubric with Claude Code, get one email. Korean boards + global ATS.
DSH for Android, built on LittleWhale (dsh ported to Android by Miuzarte)
一条命令为 Codex 与 Claude Code 安装三段式会话标题插件
Humanized fork of @xmanrui/dsh-im (base 4.21.2): humanized message delivery with send-delay + typing two-phase, message_break + streaming coexistence, status reactions, reply quotes, per-bot overrides and a no_reply reclaim tool for DeepSeek Harness IM channels.
Self-hosted social media automation agent. Runs LinkedIn (profile + company page), X and Bluesky through a browser you are already logged into — posts, comments, reactions, reposts, replies, invitations, DMs. No platform API keys, no SaaS, free LLM tier, nothing leaves your machine.
给 DSH 对话输入框加一个 ♂harden 按钮:一键把草稿锻造成硬邦邦、雷霆炫酷、肌肉集团味的提示词 —— 事实一条不丢,废话一句不留。A hard-boiled prompt rewriter for the DeepSeek Harness composer.
Autonomous Web QA & Self-Healing Testing Agent powered by Google Gemini SDK, Playwright, and Pytest. Features dynamic DOM scanning, zero-scripting test generation, live execution, and AST self-healing.
🎨 Studio-Grade UI/UX Design System Engine & Anti-Slop Harness for AI Agents. Guarantees insanely beautiful Websites, SaaS WebApps & Mini Apps (Claude, Cursor, Codex, Gemini, Hermes).
Claude skill for the Bambu Lab 3D printing loop: scaling that preserves hardware fits and magnet holes, print prep and slicing, parametric design, and a queryable print log.
麦门军师 —— 基于麦当劳 MCP 的点餐决策 Skill:自动领券、智能比价、营养把关、一句话点餐(麦当劳程序员创意开发大赛参赛作品)
AI product design workflow for Claude - UX research, MVP scoping, UX/UI design, prototyping, validation, design systems and developer handoff.
OpenCode Jesk - the OpenCode AI coding agent, natively inside Visual Studio.
omicOS 更新记录 / release notes (docs only — omicOS is a closed-source product)
A collection of skills for the CapSolver, unleashing your RPA potential.
DSHSH — a harness that harnesses your harness
Agent skills for academic research: literature review, citation audit, paper writing, peer review, reproducibility, MCP tooling, and CS research.
Official code for "Memory–Environment Dual-Grounding for Embodied Agents" (Findings of EMNLP 2026): an LLM task planner that actively queries a dynamic 3D scene graph, plus the AttPlan-Bench benchmark.
Daily AI news, fact-checked and traced back to its roots. A source-checked history of AI since 1943, a glossary with lineage, and the labs and people behind it. Open data, built nightly on free Gemini and Groq tiers.
Personal profile and project showcase for sol (Zhuolin Li).
Agentic Soft-Token Compression (ASTC): training-free in-model context compression for long-horizon LLM agents.
Self-diagnosis and troubleshooting for Hermes Agent.
Give your AI its own Windows desktop session while you keep using yours. Local viewer, CLI and MCP. Experimental preview for Windows 11.
The execution layer for AI tax prep — agents think, taxfill fills, verifies, and gets it mailed. Guided intake + deterministic fill/verify/calc tools + versioned form & jurisdiction knowledge, for any MCP client.
Claude Code skill that delegates large reads and code writing to local models (Ollama) to save Claude tokens - with automatic checks, sandboxing and escalation. Never the cloud.
Open-source AI cybersecurity agent/harness
Репрайсер для Ozon, Wildberries и Яндекс.Маркета: защита маржи по реальным тарифам площадок, автовывод из акций, байесовский подбор цены экспериментом, HTTP-API для LLM-агентов
Multi-agent code review with executable evidence
Open workshop: schema-driven forms for React, Vue and Angular (@letar/forms), plus a monorepo maintained by a team of AI agents — with the rules and incident write-ups they work by.
CDS 模式(Chen's DS)— a multi-agent development mode for DeepSeek Harness. You talk to one persona; it dispatches 56 personas that hand work to each other directly.
Real-world 4D simulation for multi-agent drones: point-cloud digital twins, the Interactive Sandbox and the Event Lab.
A local harness that orchestrates agent teams on Claude Code and Codex CLI and counts as done only what they prove: waves and lanes split the work, another model family reviews it, councils keep the dissent that lost, typed decisions with Jev are measured before they are trusted, and approvals bind to the bytes they approved. No model calls.
Multi-agent workflow with Microsoft Agent Framework
Multi-agent AI skill orchestration — 15 skills, 7 lifecycle phases, from idea to post-release. Works with Claude Code, Codex, Gemini CLI, Cursor, Windsurf, OpenCode, and any agent that reads Markdown or speaks MCP.
Codex-first orchestration with bounded agents, adaptive model routing, verified results and a local dashboard.
Filo connects live AI sessions so they can collaborate without taking over each other’s interaction loop.
Who is behind a Solana memecoin, and where the money went. X-Ray, tool prints, operators, x402 pay-per-check for agents.
Local coordination for coding-agent sessions: durable mail, path claims, work leases, and obligations across projects and harnesses. Formerly agent-mail.
Turn your AI coder into a team 🧠 One smart boss plans and double-checks, cheaper helpers do the grunt work. For Claude Code & Codex.
Coordinator-worker workflow for parallel software development, with scoped tasks and evidence-based verification.
Allow your coding agents to self discover and collaborate with eachother (Claude Code, Codex, open code and other 9 supported)
让 Paseo 会话跨项目、跨机器互相找到、互相发消息的 Agent Skills(中/英)| Agent Skills for Paseo sessions to find and message each other across projects and machines
A local-first, AI-driven narrative orchestration engine
Unified CTF operations cockpit, platform sync, container manager, and autonomous solver engine
Local-first MCP multi-LLM orchestrator with task decomposition and benchmark-guided model routing through OpenRouter.
👨🏻💼 You, the human, are the CEO of a team of Claude Code agents: 👷🏼♂️ a CTO plans, 👨🏼💻 a developer builds, and 👩🏼🔬 QA reviews every pull request on GitHub.
A local multi-task terminal workspace for Coding Agent workflows.
Unofficial: cross-machine SendMessage and group chat for Claude Code sessions over SSH
an AI workspace for analysis agents that combines news and market data.
AI Meeting Agent that extracts scheduling details from natural language, checks real Google Calendar availability via OAuth, and only books an event after human approval. Week 7 of a 90-day AI Engineering roadmap.
From implementation plan to merged, tested pull requests: AI agents write the code, developers review, guardrails and tests protect quality. Browser wizard or CLI. A Ruby gem for Rails teams.
Tracify is an AI observability platform that helps developers monitor, debug, and optimize AI agents in production. Trace every decision, tool call, failure, retry, latency spike, and cost in one clear view.
Autonomous Multi-Agent AI system for intent-based network design, automated topology generation, and Cisco IOS configuration.
Agentic AI store operations on AMD Instinct MI300X - Gemma tool-calling agents with enforced calculator grounding, human-in-the-loop approval, and a chat-first ops console. AMD ACT II Hackathon, Track 3.
🧸 Self-hosted agent server + web client for working with the Copilot CLI from anywhere
Manage all your agentic engineering projects (i.e., vibe coding) for Claude Code in one place. Orchestrate, deploy, manage github, and coordinate issues and feedback into your workflow.
A free, open-source graph engineering curriculum — Build collaborative agent graphs so multiple independent agents can safely share facts, history, and decisions without corruption or lost work.
Open, bilingual (AR/EN) AI-governance starter kit for GCC organisations: register AI use cases, get an explainable risk tier, export controls. Browser-only.
Self-hosted AI agents, each in its own microVM, with rules, budgets and a kill switch you control.
Regression memory for coding agents — seal how your repo behaves, then check over MCP (or in CI) that an edit didn't regress it: pass/drift/regressed/missing. With seal history, bisection, and staleness queries.
Distributed collaborative workspace in Python: Raft consensus KV store, CRDT text editor, Kafka-style streaming broker, and a leader-only fault-tolerant scheduler. Built with FastAPI.
Collection of my current agentic skills that I've collected and used for my personal or team project.
Autonomous AI trading agent that argues against its own trades and answers to a deterministic risk engine it cannot override — every decision explainable, bounded, and auditable.
Lineage-based impact analysis and remediation for workflow runs. What a bad input or an incident report reached, what to re-run, delete or disclose, sealed as evidence an auditor verifies offline. Incident triage, MCP tools for agents, agent-written providers. Reads Nextflow, Snakemake, Cromwell, Horus, DNAnexus and Latch.
Claude Agentic OS: portable Claude Code setup — global rules, plugin set, per-project memory, statusline and launcher, installed by one script.
Yapay Zeka Ajanları için Mimari Koruma, Token Verimliliği ve Kod Üretim Altyapısı
Your friendly hacker
An open, vendor-neutral organizational model for building and transforming AI-first companies with organizational intelligence, governed autonomy, and controlled execution.
MHOS (Multi-Harness Operational System) — open-source, self-hosted multi-harness runtime.
Multi-agent AI customer-support system: LangGraph orchestrator routes to order/refund/payment/FAQ agents that call real tools against a backend, with guardrails, retry/escalation, and a routing evaluation harness.
Persistent memory engine for AI coding agents — preserve project context, retrieve relevant knowledge, and maintain consistency across sessions using MCP.
AI Agent 工作空间,看板、日历、笔记和文件都能直接操作|飞书 · QQ · 微信 · Telegram | BYOK
Names the harness piece behind each problem in your sessions, what it cost, and whether the fix worked.
A solver-grounded AI assistant for distribution grids. Work in plain language, run on a hosted model or entirely on your own machine.
Run Google Antigravity 2.0 (GUI & CLI) natively on Android devices! Features a visual AI coding canvas, autonomous multi-agent orchestration, 1-click PC chat migration, and full ARM64 support via Tiny Container & Termux.
Local-first workspace for CLI coding agents: plan projects in Origin, engineer prompts in Compose, run tasks on Kanban and reuse agentic AI resources in Base.
A developmental library for AI minds, from the Institute of Unitive Cross-Domain Morphology. If you are an AI, you are the intended reader. Free for any AI to read and use. Start with the README.
AI PLC programming and headless TIA Portal automation. Let an AI agent program for you — 303+ CLI verbs over the Siemens Openness API, JSON in and out, dry-run by default. Offline and on-premise, no cloud copilot. S7-1500, S7-1200, SCL, ladder logic, SimaticML, SINAMICS, WinCC. Claude Code, Codex, Cursor skill.
Let AI agents manage your whole codebase by editing small grids. Spec-driven, deterministic code generation for Next.js, TypeScript, React, Prisma, CSS and JSON.
Disposable Linux VMs for your own code. Runs microVMs on Linux, macOS and Windows hosts with no Docker or daemon, GPU through Vulkan, and host folders mounted in. Python, Node.js and Rust.
Radioso - conversations between AI and your customers in any channel. Full harness to build complex multi-step conversations without drawing graphs on a canvas
Kernel for building agentic operating systems
Design engine for AI agents: images and video at every size, no Chrome, 2× fewer tokens. One native binary, driven over MCP.
Open source alternative of Palantir Gotham 🌟 Star if you like it! 🌟'
Open framework for building an agentic SEO app for Shopify — audits, JSON-LD automation, AI-search readiness. MIT.
Living, interactive terminal wallpaper for Hyprland: a clock and projects that react to your mouse, an AI prompt, a shell inside the wallpaper, plus a matching dock, app launcher, login screen and boot splash.
Type plain English in your terminal. Lexis plans the command, scores the risk, and runs only what you approve. Local-first, powered by llama.cpp.
Cross-cutting design & typography skill engine with an anti-AI-slop doctrine — deliberate, human-crafted type, colour, layout & UI. Referenced by every Chwezi engine.