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 68 of 376
Adobe Skills for Agents
Realistic examples of building evals and optimizing agents with Harbor
轻量白盒多智能体平台 —— 可视化编排工作流，多 Agent 协作，高精度知识召回，企业级权限管理，统一对话管理。支持低成本嵌入第三方系统，200MB 低资源即可运行。
How to turn your Second Brain into a living research memory that your agents maintain. Workshop with slides, video and code.
面向 Claude Code、Codex 等 AI 编码助手的 Hook 与 Agent Skill 开源合集。
COVID deterioration prediction based on chest X-ray radiographs via MoCo-trained image representations
Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. Works with Claude Code and OpenClaw.
Provides documentation for calling hundreds of Win32API functions from VFP
简单的 Python 异步多后端机器人框架
Agent-first task orchestration. Persistent memory. Multi-provider coordination.
Shared Memory Storage for Multi-Agent Systems
Real-time on-device text-to-image and image-to-image Semantic Search with video stream camera capture using USearch & UForm AI Swift SDKs for Apple devices 🍏
This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'
😎 Awesome list of Microsoft Agent Framework resources
耗时多年自研高性能golang棋牌AI框架，基于最新主流大模型LLM+多agent协同决策，实测接近真实玩家智力水平。严禁赌博，否则后果自负！！！
An MCP ( Model Context Protocol ) Server for Grafana Loki
Agentic ✧ Gemma Inference for Android System Intelligence
将知乎收藏夹（公开和私密）批量导出为 Markdown 格式文件. 支持配置收藏夹列表并批量下载, 支持基于URL自动去重, 支持下载专栏和图片, 支持自定义保存路径, 支持调试和错误日志. **同时提供 MCP Server**，可被 AI Agent (如 Claude Code) 直接调用，为大模型提供保存知乎收藏夹的能力。
Plug-and-play AI agent skills for OKX — letting any LLM agent trade, manage portfolios, query live market data, and run grid/DCA bots through a single okx CLI, no API wiring required.
🤖 AI Agent-driven Kaggle competition workflow. Battle-tested patterns for score stabilization, submission troubleshooting, kernel workflows, and spec-driven development.
企业级多Agent智能运维系统 AIOps | Python+Java+Go | 面试级全套项目 | 监控告警+根因分析+故障自愈+变更审批
Reverse-engineering AI assistant for the Web
Native macOS orchestrator for coding agents — run Claude Code, Codex, Cursor, Gemini and shells in parallel across git worktrees and remote hosts
Open-source sandboxes for AI agents, untrusted code execution, and durable services.
OriginTrail Decentralized Knowledge Graph (DKG) is a decentralized knowledge infrastructure for multi-agent AI memory — enabling agents to publish, verify, and query shared knowledge as cryptographically verifiable graph assets across a peer-to-peer network.
A RiveScript interpreter for Python. RiveScript is a scripting language for chatterbots.
List of all AI related learning materials and practical tools to get started with AI apps
Local LLM ReAct Agent with Guidance
🚀 The LLM Automatic Computer Framework: L2MAC
Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG. Finds what RAG misses. Zero cloud, zero cost.
Multi-Agent Team for Creating Long-form Videos
Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs
专为闲鱼小商家打造的AI智能客服，经本人真实店铺实战打磨，懂人话不废话，会主动聊出单，支持多模态理解、消息聚合回复、跨会话记忆，支持后台静默运行，边挂机边工作，互不干扰。稳定可靠。（RPA+Coze工作流）
开箱即用、可按项目定制的 AI Coding Agent Skills 框架：提供通用 Workflow、可扩展的项目私有知识、自我学习闭环和问题排查能力，适配任意技术栈和工程场景。兼容主流 Coding Agent。
Self-improving AI agent harness — propose, eval, approve, ship. AHE autonomous loop + MCP + BYOK + eval suite.
Fixing GRPO training collapse in long-horizon multi-tool agents. A lightweight PRM-Lite + LATA joint approach achieves +37% over vanilla GRPO on τ-bench airline (50-task, multi-turn).
Turn your local Claude Code / Codex CLI history into a shareable, anonymized AI-Native developer profile + viral SVG poster. A skill, not a script — 100% local & read-only.
AI Agent 复刻精美网页的提示词合集：每个目录一份 prompt.md + 效果图截图，丢给 Claude/Codex/Kimi 即可生成对应网站
The open-source AI IDE for Claude Code, Codex, OpenCode, and more. Run agents in parallel, locally or in the cloud, and build reusable workflows.
Unilm for Chinese Chitchat Robot.基于Unilm模型的夸夸式闲聊机器人项目。
A guide to using AutoGPT for code generation and prompt engineering.
Universal debugger CLI built for AI agents. Allows Claude Code and Codex to debug much faster. Support Node (Javascript, Typescript), bun, lldb (C++/Rust), python. Fast, token-efficient, no fluff.
🪐 🤖 AI Agents for JupyterLab with 🔧 MCP tools - Chat with notebook interaction and code execution.
Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document processing, vector ops, and cognitive memory systems
🚀 100 hyper-specialized AI agents for Claude Code - Transform Claude into your personal tech army with experts in React, AWS, Kubernetes, ML, Security & more
🐘 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.
Read books the way Feynman did — along with a continuously evolving network of agent-simulated great minds
Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.
The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Bench
Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.
Open Framework for AI Agents to play Red Alert through Reinforcement Learning
[ICML-25] AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
AI-Assisted Reverse Engineering with Ghidra
Official Implementation for EMNLP 2024 (Main Track, Oral) "AgentReview: Exploring Academic Peer Review with LLM Agent."
真正记得住你、认识你、随你成长的 AI 长效认知记忆引擎 Long-term Cognitive Memory Engine for LLM Agents
A Multi-Agent Orchestration Framework
Chat agents for your team, with approvals and sandboxed tools. Slack, Discord, Telegram, webhooks.
Your personal AI server. Full code control. Unlimited possibilities. Powered by MyClaw.ai
LLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmind's PySC2 Learning Environment API as a Python LLM Environment.
Chat with your code
A C# framework to build, visualize and execute event-driven workflow
An AI powered geospatial application that allows you to explore and visualize Earth science data using natural language.
The latest graphrag interface is used, using the local ollama to provide the LLM interface.Support for using the pip installation
An application that allows you to interact with ChatGPT on your old iDevices.
AI-powered browser automation MCP server for Claude Code. Navigate, click, screenshot, test — all from your terminal.
Personal Assistant Wizard for Claude Code — npx pawmode
[ICLR 2025] Benchmarking Agentic Workflow Generation
Git For database Systems
A modular MCP server that provides commonly used developer tools for AI coding agents
AI-driven Yu-Gi-Oh! bot using deep reinforcement learning and LLMs
AIRA-dojo: a framework for developing and evaluating AI research agents
auth for agents–from the creator of `dotenv` and `dotenvx`
Cerul — video memory infrastructure for AI products. SDKs, CLI, MCP, and developer integrations.
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。
ChatIndex: Tree indexing and retrieval for long conversational memory
AI-powered open-source platform for Attack Surface Management (OASM)
Claude Code plugin: multi-agent orchestrator with 10 specialist agents for academic writing review, research, drafting, and polishing
AI-powered video production pipeline for Claude Code, Github Copilot, Codex, Cursor, OpenCode and PI — 6 automated phases from design thinking to final render
Self-hosted API execution layer that sits between your agent and the outside world. Your agent says what it wants to do. Jentic One handles the how — finding the right API, injecting credentials at runtime, and brokering the request
📚 PaperFlow: Dynamic personalized scientific-paper recommendation, reading, and reporting
Route complex Codex tasks to model-specific background workers with bounded concurrency and lead-agent verification.
MIT-licensed PowerShell document automation for Word, Excel, PowerPoint, PDF, email, PST/OST, OneNote, Visio, OpenDocument, and mixed-format Reader workflows.
Open Weight, tool-calling LLMs
Connect to hosted payram helper at: https://mcp.payram.com
(ACL 2025 Main) A Comprehensive Benchmark for Code Information Retrieval.
[EMNLP 2024 (Oral)] Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"
Catch MCP server issues before your agents do.
Comprehensive analysis and documentation of Claude Code’s internal prompt architecture and multi-agent reasoning system.
Compile humans into AI agents — a Claude Code plugin that conducts deep behavioral interviews and generates installable agent plugins
Synthetic Data Generation Toolkit for LLMs
Persistent memory + local AI for coding agents. 2B–27B open-weight LLM fleet, cross-session Mind Palace, cognitive routing, L3 grounding verifier, multi-agent Hivemind. Works with Claude Code, Cursor, VS Code. Offline-first, HIPAA-ready. Free tier included.
ZeroID: Autonomous Agent Identity Management System (AAIMS)
Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper.
Hatice is an autonomous coding agent orchestration system.
思源笔记AI Copilot插件，支持基于思源笔记进行AI问答和编辑，支持agent模式调用工具
Sub-100ms auth switching for AI coding CLIs (Claude Code, Codex, Gemini): swap subscription accounts instantly when you hit usage limits
🧠 Directory of SOUL.md personality files for OpenClaw agents
AgentSeek is an application development lifecycle toolkit for AI ecosystem apps, built by OceanBase OSS Team.