Framework
Custom agents
57,684 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
57,684 agents · ranked by popularity · refine in the directory →
Custom agents — page 90 of 577
FreeBuddy: desktop chat workspace for local CLI agents (codex / claude / opencode)
把 dsh 会话变成合规、可复现、可追责的 AI 投研工作台:ai-hedge-fund 回测 + risk-gate 风控 + cron 盯盘 + 记忆复盘 | compliance-first AI investment desk
本地优先的视频→结构化笔记服务:B站/抖音/本地视频,平台字幕+本地离线转写,LLM 生成带时间轴笔记;桌面应用 / MCP / Agent Skill 三种接入。
A Lean quality system for AI-assisted work — every defect becomes a permanent countermeasure. Built by a manufacturing operator.
Add one word, `lit`, to an Antigravity CLI (agy) prompt and get a planned, tested, reviewed workflow, plus a handoff note for the next session. Formerly antigravity-swarm.
讓 AI agent 讀懂台灣醫療:63 個 MCP 工具,涵蓋 FHIR R4 / TW Core 驗證、ICD-10、SNOMED CT、LOINC、TFDA 藥品與臨床計算器。MCP server for Taiwan healthcare data.
A personal agent that works on your life around the clock, on a Mac you own. One sentence to Claude Code installs it.
AlumNet - AI-powered intelligent school history exhibition & alumni management system | AI 智能校史展示系统 — 校友星图
A Python Telegram bot powered by Google's gemini-pro LLM API
Seamlessly integrate Grok AI into Laravel applications with an elegant, developer-friendly package. Leverage powerful AI models for chat, automation, and NLP, while maintaining Laravel's expressive simplicity.
A JavaScript library that brings vector search and RAG to your browser!
Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files
Build an AI Agent from Libraries of Functions -- My most advanced agent framework
Heterogeneous Hierarchical Multi Agent Reinforcement Learning for Air Combat
AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query file structure, dependency graphs, and change impact. Built for Copilot, Cursor, and any tool-calling LLM. 面向 AI 编程助手的代码库感知技能——生成持久化知识图谱,精准查询文件结构、依赖关系与改动影响半径。
An Multi-Modal LLM Powered Agent to automatically solve Captchas
[EMNLP2025] LLM-KG4QA: Large Language Models and Knowledge Graphs for Question Answering
This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'
A goal-specification file for autonomous coding agents. Generalizes Karpathy's autoresearch to domains with constructed metrics.
Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs
Agentic ✧ Gemma Inference for Android System Intelligence
Bridge Claude Code CLI with Feishu/Lark via WebSocket. 飞书 × Claude Code 实时对话。
Comprehensive AI agents, skills and rules toolkit for 1C:Enterprise development in Cursor IDE
Hatice is an autonomous coding agent orchestration system.
Ultimate Harness Automation for Github Copilot on VS Code. It provides 28+ specialized agents, 30+ reusable skills, hooks, guardrails, and etc.
An OpenCode plugin that integrates OpenSpec, adding a dedicated 'openspec-plan' mode for creating and editing spec files.
A Large-Scale Knowledge Graph for Automated Scientific Research
A React component library for rendering AI-generated markdown — LLM streaming, LaTeX math, Mermaid diagrams, GFM, syntax highlighting, CJK-friendly typography, and cross-chunk reference coordination.
[ICLR 2026] Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
Claude Code context engineering & planning system for individual AI development workflows
A mobile vibe-coding cockpit — built on tmux: drive your live session, Claude Code / Codex — anything a terminal can run — from your phone. 移动 Vibe Coding 驾驶舱 —— 基于 tmux 实现,可在手机上驱动你的会话、Claude Code / Codex、任何终端能实现的东西。
全球酒店预订&低价监控提醒Skill,200万+精选酒店,独家优惠价格,让你的Agent轻松预订品质酒店,支持支付宝下单+查询历史订单,24 小时客服支持,全天候响应。
小红书图文内容工作台:把账号定位、热点研究、选题、原创文稿、品牌配图、预览和人工确认组织成一条可控流程。
Allow your agents to see your LLM subscription quota windows.
Independent multi-model review for AI coding agents
《从零开始玩转 DeepSeek Harness》——DeepSeek Harness 实战指南
ERC-8004 Trustless Agents for TypeScript and Rust
协程、高性能、灵活的聊天机器人 & Web 开发框架(炸毛框架)
Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google AntiGravity, and MCP-enabled assistants
Ultra-fast methylation calling and event alignment tool for nanopore sequencing data (supports CUDA acceleration)
The implementation of "Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4"
Minimal typescript agent framework that keeps it simple and gives you control - no BS
[EMNLP 2024] CryptoTrade: A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading https://aclanthology.org/2024.emnlp-main.63.pdf
Remote MCP Server that securely connects Enterprise context with your LLM, IDE, or agent platform of choice.
An open-source Python SDK and CLI Starter Toolkit for deploying AI agents to Volcengine AgentKit Runtime.
Open-source video processing core and CLI. Search and annotate local videos with your own model endpoints.
Author, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, evaluate skills, lock and sign dependencies, and publish bundles. CLI, MCP server and Go API.
Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms via MCP. STDIO or Streamable HTTP.
本项目提供一套专业的法律检索 Agent Skill,可用于 Cursor、Claude Code、OpenCode 等 AI 编程工具。无论是非法律专业人士需要了解法律知识,还是法律从业者进行法律检索,都能提供系统性的法律规范查找与整理服务。
Mozaik is a TypeScript framework for multi-agent collaboration.
The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 14 agents · 21 skills · 8 workflows. Fail-closed gates, test honesty, anti-anchored review.
Fulloch - The Fully Local Home Voice Assistant
AI生图工作台 (AI Image Generator)、视频工作台。支持 Agent 与工作台模式、无限画布、素材管理、提示词反推/广场及 PWA,支持外链式配置;可接入 Grok、GPT Image 2 等自定义模型生图。自适应手机端。
68 installable Star Trek-inspired profile distributions for Hermes Agent
基于 RAG 的 AI 智能笔记助手「云尚」:FastAPI + LangGraph + ChromaDB + Redis 构建。ReAct / Plan-and-Execute 双 Agent 模式、深度思考、图片/视频多模态、MCP 联网搜索与网页抓取、DeepL 翻译 / Wolfram 计算 / Edge TTS 语音、PPT 生成、记忆压缩、知识库重排序、笔记回收站与邮件导出、Token 用量追踪。后续版本会持续优化并添加Skill功能
Turn any tutorial video into a verified, installable AI-agent skill. Reads the screen, not the transcript. Runs locally. MIT.
HTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.chat.
Model-neutral AI workspace for macOS with multi-provider models, extensible tools, and inspectable deliverables.
Production-oriented Spring AI platform prototype for RAG, tool calling, async ingestion, JWT/RBAC, and observability.
Ollama AI front-end using Windows Forms as a Copilot Application
LLM powered agent that analyses SQL databases.
👀🧠 GPT-4 Vision x 💪⌨️ Vimium = Autonomous Web Agent
Self-hosted auto clustering AI agent OS for consumer hardware like the computer you already own, an Orange or Raspberry Pi or a Mac Mini etc. Full desktop, app store, agent deployment, distributed compute cluster. Memory by taOSmd.
Algolia + Angular = 🔥🔥🔥
Open-Source RAG app with LLM Observability (Langfuse), support for 100+ providers (LiteLLM), Dockerized, Full Type-checking, 100% Test coverage, and more...
Blink is a self-hosted platform for building and running custom, in-house AI agents.
An application that allows you to interact with ChatGPT on your old iDevices.
Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University
ConcoLLMic: the first language- and theory-agonistic concolic execution engine via LLM agents
BreadFree-Simu 是一个基于大语言模型(LLM)的 A 股智能量化回测系统。它利用多智能体协作(Multi-Agent)架构,模拟机构投资者的决策流程(分析-风控-决策),旨在探索 AI 在中国特色金融市场(T+1、涨跌停板)中的应用潜力。
AAHL's Agent Skills. 汇集了多种实用的智能体技能,涵盖Home Assistant智能家居控制、微软Edge TTS和智谱GLM-TTS文本转语音、DuckDuckGo搜索、DeepWiki文档检索、加密货币行情、天气预报、Lark/飞书、影视搜索、商品比价等功能
MCP server that lets Claude Code and other AI agents read and search large PDFs, one file or a whole folder: agentic RAG with hybrid semantic + keyword search, selective page reads, tables, images, OCR, chart data, and multi-column/CJK layouts.
AKB — Agent Knowledgebase. Organizational memory for AI agents: vault-scoped docs / tables / files unified by URI graph, served over MCP.
Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs
Moved to OfficeIMO. Development, releases, issues and pull requests: https://github.com/EvotecIT/OfficeIMO
A local web UI for the beads (bd) issue tracker — board, epics, dependency graph, drag-and-drop.
Zeline — an open-source agentic AI framework developed by Zerolinear.
Keeps coding agents on your design system: catches palette colors, native elements and APIs your system lacks, at every edit and pull request, with the fix. Set it up once in your design-system package; every app in your monorepo gets it.
Discord ChatGPT bot
Attention-based Deep Reinforcement Learning framework for portfolio allocation on S&P 500 equities. Includes custom environment, policy architecture with cross-sectional attention, PPO/A2C/REINFORCE agents, training/evaluation pipeline, and fine-tuning grid search.
It's like Auto-GPT met Brew. The easiest and fastest way to get started with AutoGPT with any backend of your choice & whatever plugins you may need
Structure-aware Multi-Index RAG System
Framework for learning dialogue agents in a two-player game setting.
Open-source VS Code AI agent that combines the best of Roo Code, Cline and kilo code, with advanced AI capabilities, multi-model support, and seamless development workflow integration.
Infra-agnostic hosting framework for browser agents.
[ICLR2026] NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
A generative Minecraft structure tool for the Cynia Agents framework.
🐘 Give AI assistants full PostgreSQL DBA superpowers — 30+ tools for performance analysis, bloat detection, lock/deadlock monitoring, autovacuum & schema inspection. No extensions required. PG 12-18.
Automated system for LLM evaluation via agents. Doc as below:
🌼 ShoppingGPT 🛒: AI-powered Shopping Assistant - RAG + LLMs + Semantic Router +Vietnamese
Guides, courses & reading lists for learning to build autonomous LLM agents
NXTG-Forge orchestrator: an MCP server for Claude Code with task orchestration, file locking, knowledge capture and drift detection. Rust. Alpha (source-available, FSL-1.1-ALv2).
Transform YouTube videos into a compounding knowledge base with transcripts, vision analysis, and agentic search. Works as an MCP server for Claude, Copilot & more.
Self-hosted AI customer-support platform — per-KB RAG on Qdrant, 13 LLM providers, SSE streaming, embeddable chat widget. FastAPI + Vite + SQLite, all in Docker Compose.
The video editor built for AI. Create videos with React + TypeScript — designed for AI agents, LLM pipelines, and automated production. Fully open source.
VectorRAG.Net is a .NET-native high-performance vector database library for semantic search and RAG (Retrieval-Augmented Generation). Core search is based on Random Hyperplane LSH candidate generation with exact rerank by dot/cosine.
The OpenClaw Dashboard 🦞
Remote control for Antigravity — manage AI conversations, workspaces, and agents from any device. One command to set up, one URL to access.
A reference operating model for organizations where any role can be filled by a human or an agent, every process is built for agents first, and every flow can be paused, adjusted by a human, and resumed.
Curated collection of AI agent skills for Hermes and other agent frameworks