Framework

Custom agents

57,742 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.

57,742 agents · ranked by popularity · refine in the directory →

Custom agents — page 139 of 578

Python-Mental-Health-Chatbot★ 84

My university final year project.

IMN★ 84

CIKM 2019: Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

AILib★ 84

A large collection of mostly reinforcement learning agents.

awesome-ascend-skills★ 84

A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed Agent Skills. https://ascend-ai-coding.github.io/awesome-ascend-skills/

brand-design-md★ 84

A Claude Code Skill that gives your AI agent the design language of 62 world-class brands — on demand.

Arena-BuildingToolkit★ 84

Arena: A General Evaluation Platform and Building Toolkit for Single/Multi-Agent Intelligence. AAAI 2020.

pypykatz_agent_dn★ 84

Pypykatz agent implemented in .NET

ingero★ 84

eBPF agent and MCP server for GPU causal observability

easy-frida★ 84

a simple tool for easyily dev/debug using frida and write module for agent. (mainly used for android)

cssuseragent★ 84

Automatically adds User Agent CSS classes to the document allowing variations for specific browsers without resorting to CSS hacks.

ChatAbstractions★ 84

LangChain chat model abstractions for dynamic failover, load balancing, chaos engineering, and more!

PhotoBot★ 84

📸 Chatbot for photographers

Agent3★ 84

A Toolkit for building AI agent for web3.

Multi-Agent-Coverage-Path-Planning-Algorithm★ 84

用于多机覆盖路径规划流程化算法 Algorithm for Streamlining Multi-Agent Coverage Path Planning

omnibus-td-agent★ 84

td-agent (Fluentd) Packaging Scripts

claude-agent-demo★ 84

基于 Claude Agent SDK 开发 Agent

tintin★ 84

Control Coding Agents (Codex, etc.) via Telegram or Slack.

Deep-Reinforcement-Learning-Algorithm-Collection★ 84

Collection of Deep Reinforcement Learning Algorithms implemented in PyTorch.

hyperterse★ 84

The agentic server framework.

multiagent_gnn_policies★ 84

Learning multi-agent policies for flocking using graph neural networks

trx★ 84

Agent-first CLI for audio/video transcription via Whisper

ironclaw★ 84

Your own personal AI assistant. But with security by design. Support for numerous operating systems. Any platform.

daisy-engine★ 84

AI orchestration platform

gc-qa-rag★ 84

A RAG (Retrieval-Augmented Generation) solution Based on Advanced Pre-generated QA Pairs. 基于高级 QA 问答对预生成的 RAG 知识库解决方案

Abmarl★ 84

Agent Based Modeling and Reinforcement Learning

awesome-cursor-rules★ 84

❇️ neatly composed rules for ai ides like cursor, windsurf, vscode microsoft github copilot, reliverse ai, etc. optimized for modern frontend development with next.js 15, react 19, typescript 5, tailwind 4, shadcn/ui, drizzle orm, better auth, polar, tanstack form, react query, etc.

InvestorGPT★ 84

InvestorGPT is an AI agent that analyzes the stock that dropped in its price recently and calculates chance for the company to recover the stock price back.

china-dictatorship★ 84

反中共政治宣传库。Anti Chinese government propaganda. 住在中国真名用户的网友请别给星星,不然你要被警察请喝茶。常见问答集,新闻集和饭店和音乐建议。卐习万岁卐。冠状病毒审查郝海东新疆改造中心六四事件法轮功 996.ICU709大抓捕巴拿马文件邓家贵低端人口西藏骚乱。Friends who live in China and have real name on account, please don't star this repo, or else the police might pay you a visit. Home to the mega-FAQ, news compilation, restaurant and music recommendations.Heil Xi 卐. 大陆修宪香港恶法台湾武统朝鲜毁约美中冷战等都是王沪宁愚弄习思想极左命运共同体的大策划中共窃国这半个多世纪所犯下的滔天罪恶,前期是毛泽东策划的,中期6.4前后是邓小平策划的,黄牛数据分析后期是毛的极左追随者三朝罪恶元凶王沪宁策划的。王沪宁高小肆业因文革政治和情报需要保送“学院外语班“红色仕途翻身,所以王的本质是极左的。他是在上海底层弄堂长大的,因其本性也促成其瘪三下三滥个性,所以也都说他有易主“变色龙”哈巴狗“的天性。大陆像王沪宁这样学马列政治所谓"法学"专业的人,在除朝鲜古巴所有国家特别是在文明发达国家是无法找到专业对口工作必定失业,唯独在大陆却是重用的紧缺“人才”,6.4后中共信仰大危机更是最重用的救党“人才”。这也就是像王沪宁此类工农兵假“大学生”平步青云的原因,他们最熟悉毛泽东历次运动的宫庭内斗经验手段和残酷的阶级斗争等暴力恐怖的“政治学”。王沪宁能平步青云靠他这马毛伪“政治学”资本和头衔,不是什么真才实学,能干实事有点真才实学的或许在他手下的谋士及秘书班子中可以找到。王沪宁的“真才实学”只不过是一个只读四年小学的人,大半辈子在社会上磨炼特别是在中共官场滚打炼出的的手段和经验而已,他和习近平等保送的工农兵假“大学生”都一样,无法从事原“专业”都凭红资本而从政。六四学运期间各界一边倒支持学生,王沪宁一度去法国躲避和筹谋,他还加入了反学运签名,成为极少有的反学运者仕途突显,在六四和苏联垮台后中共意识形态危机,江泽民上台看上唯一能应急的王沪宁聚谋士泡制的"稳定统一领导"和之后的"新权威"谬论。左转被邓小平南巡阻止后,王策划顺邓经济改革却将政治改革逐步全面终止和倒退,泡制“三个代表”为极左转建立庞大牢固的红色既得利益集团。因此六四后各重大决策和危机难题都摆在中共中央政策研究室王沪宁桌面上,使王沪宁成了此后中共三朝都无法摆脱的幕后最有决策性实权的人,中共中央政策研究室是王为其野心巨资经营几十年,聚众谋士的间谍情报汇总研究的特务机关和策划制定决策重要机构与基地,王沪宁本人和决定其仕途关键的首任岳父及家属就有情报工作背景。中央政研室重要到王沪宁入常后为了死抓这中共情报与决策大权,宁可放弃国家副主席和中央党校校长。后再加个除习外唯他担任的中共几核心领导小组之一的“不忘初心牢记使命”主题教育工作小组组长。此后他把持的舆论必将以宣传“不忘初心牢记使命”为主,打造众所周知的所谓“习思想”其实是”王思想“。王自从主导中央政研室开始决策后,策划中止邓小平的与美妥协路线回归毛极左的反美路线。帮助前南斯拉夫提供情报打落美机放中使馆引发炸使馆事件,以此掀起六四后唯一的全国大规模游行并借此反美而起家。后又帮江泽民提供法轮功会是超过中共组织的情报,策划决策镇压迫害开始并没有把矛头指向江的法轮功群体,策划决定阻止党内外近三十年来平反六四的呼声。致远黑皮书马拉松程序员易支付英语台词文字匹配美团点评各业务线提供知识库团队共享阿里云高精Excel识别德讯 ·吉特胡布薄熙来黑科技习近平讲话模拟器习近平音源黑马程序员MySQL数据库玉米杂草数据集销售系统开发疫情期间网民情绪识别比赛996icu996 icu学习强国预测结果导出赖伟林刺杀小说家购物商场英语词汇量小程序联级选择器Bitcoin区块链 技术面试必备基础知识 Leetcode 计算机操作系统 计算机网络 系统设计 Java学习 面试指南 一份涵盖大部分 Java 程序员所需要掌握的核心知识 准备 Java 面试 首选 JavaGuide Python 1 天从新手到大师刷算法全靠套路 认准 labuladong 就够了 免费的计算机编程类中文书籍 欢迎投稿用动画的形式呈现解LeetCode题目的思路 互联网 Java 工程师进阶知识完全扫盲 涵盖高并发 分布式 高可用 微服务 海量数据处理等领域知识后端架构师技术图谱mall项目是一套电商系统 包括前台商城系统及后台管理系统 基于Sprin

remind★ 84

A memory layer for AI Agents

SalesShortcut★ 84

Multi agent system

MMCTAgent★ 84

Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning

mistermorph★ 84

Unified Agent + reusable Go agent core.

Agentics★ 84

Agentics is a Python framework that transform LLM computation into functional code.

lacam★ 84

LaCAM: Search-Based Algorithm for Quick Multi-Agent Pathfinding (AAAI-23)

narrative-context-protocol★ 84

A standardized, application-agnostic narrative structure schema designed for reliably transporting authorial intent across multi-agentic narrative systems.

honeymux★ 84

All of your agents, shells, and TUIs in one durable terminal workspace

gdal-mcp★ 84

Model Context Protocol server that packages GDAL-style geospatial workflows through Python-native libraries (Rasterio, GeoPandas, PyProj, etc.) to give AI agents catalog discovery, metadata intelligence, and raster/vector processing with built-in reasoning guidance and reference resources.

go-agent★ 84

A Go library for building performant, type-safe AI agents that execute structured reasoning workflows.

trekker★ 84

Simple opinionated issue tracker for AI Agents

slax-reader★ 84

Open-source, AI-powered read-it-later — save web pages, highlight, and discuss

mesa-llm★ 84

Extension to the Mesa repository to provide with the ability to plug LLM directly into your agents for more complex reasoning and inter-agent communication ! Make your own reasoning/memory/communication modules and plug them into the existing code or use the pre-built ones for fast building.⁦

fenn★ 84

Friendly Environment for Neural Networks (fenn) is a simple Python framework for building ML/DL workflows and LLM agents faster, with prebuilt trainers, agent templates, logging, configuration management, and much more.

Open-Genealogy★ 84

GPS-aligned AI prompts and Agent Skills for genealogical research (CC-BY-NC-SA-4.0)

beadwork★ 84

Beadwork is a git-native work management tool for humans and AI coding agents. Plans, progress and decisions persist as files on an orphan-branch, not as cruft in yours.

loopat★ 84

Self-hosted AI workspace built around context management. Works solo, scales to teams.

Retail-Agentic-Commerce★ 84

Reference implementation of the Agentic Commerce Protocol (ACP) and Universal Commerce Protocol (UCP)- enabling AI-powered checkout negotiation while maintaining merchant control.

skills★ 84

AI agent skills for 37signals products: Basecamp, HEY, and Fizzy

front-porch-AI★ 84

Local-first AI character chat & roleplay for Windows/macOS/Linux — a living Realism Engine, built-in TTS & image generation, and The Stoop community character hub. Fully offline by default, open-source (AGPL-3.0). A home for Backyard AI refugees.

analog-agents★ 84

12 agentic skills for analog IC design — architecture, sizing, verification, cross-model review, knowledge graph, and self-evolution. Works with or without EDA.

Workspace-Bench★ 84

Benchmark self-evolving Agent upon realistic large-scale file workspaces

doc-adk-training★ 84

Learn to build, test, and deploy production-ready AI agents with this complete "From Zero to Hero" training course for the Google Agent Development Kit (ADK).

agentic-harness★ 84

Rust-native agent runtime, SDK, and CLI for software agents

chromiumfish★ 84

A stealth Chromium build with a drop-in Playwright harness for Python and Node, featuring natively built agentic capabilities.

aster★ 84

基于 ReAct 框架的安全分析 Agent,在终端中完成代码审计、渗透测试、主机防护

ultraswarm★ 84

Multi-CLI agent swarm orchestrated by Claude Code: external AI CLIs code in isolated worktrees, Claude verifies and merges

VaultysClaw★ 84

Zero-trust security for millions of AI agents

open-dynamic-workflow★ 84

Open Dynamic Workflow is a local-first workflow runner for orchestrating external coding-agent CLIs

ai-finance-claude★ 84

AI personal finance & financial planning engine for Claude Code. Analyze cash flow, debt, investments, retirement & protection across 5 dimensions. FIRE calculator, tax optimization, budget planning, PDF financial plans. 14 skills, 5 agents. Not financial advice.

news★ 84

Автоматический новостной дайджест: Perplexity → Claude API (Opus 4) → Telegram + Facebook. Генерирует ироничные авторские комментарии и публикует одним кликом.

douyin-cli★ 84

基于 Bridge Framework 的抖音全自动评论管理工具。搜索视频、爬取全量评论(含嵌套回复)、AI 智能回复、运营仪表盘。

awesome-agentic-devops★ 84

Curated + scored map of official MCP servers and agents for DevOps, Cloud, SRE, and Platform Engineering — every entry rated on production access, approval gates, and audit evidence.

industrial-ai-troubleshooting-agent★ 84
aar-loop★ 84

Run an After Action Review after any AI session and write concrete lessons so your agent stops repeating mistakes. A manual Reflexion loop, built on the US Army's AAR method.

gh-600-study-guide★ 84

Free study materials for the GH-600 GitHub Certified: Agentic AI Developer exam — 67 flashcards, a 41-question mock exam, 6 hands-on labs, concept diagrams, and Anki decks.

advocacia-aberta★ 84

Método jurídico aberto e executável por agentes de IA: base curada de STF/STJ, legislação, súmulas, temas e teses; 10 protocolos e motores locais. Fontes verificáveis, casos privados. Claude Code · Codex · MIT.

aicode★ 84

在 Android 上运行的 AI 代码编辑器,内置 Linux 终端、AI Agent 与 MCP 协议。

OneAgent★ 84

OneAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand.

pi-rlm★ 84

A pi extension with a single tool: execute, running TypeScript in a persistent Bun evaluator. Files, shell, and subagents are expressed as code rather than as more tools.

blender-mcp-bridge★ 84

Automate Blender 3D modeling with AI via MCP — 93 tools for modeling, sculpting, architecture/MEP, materials, and 3D-print prep. Includes Blender Studio: a visual record/replay session editor with a multi-provider AI assistant (Claude, Gemini, OpenRouter) — drive it from n8n, Claude Code, or standalone.

objectstack★ 84

The ontology is the software. One executable business ontology: AI writes it, the runtime runs it, agents operate it, you own it. Open protocol & runtime, Apache-2.0.

open-skill-sunset★ 84

Audit and safely retire stale generic AI agent instructions.

EasyMint★ 84

Open-source desktop AI coding platform with built-in Pi Agent (pi-coding-agent) — a graphical AI programming assistant that lets non-technical users drive AI through the full software development flow (Electron)

scientific-agent-skills★ 84

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

roadtrip-skill★ 84

An AI agent skill that turns "start + days" into a road trip you can actually drive.

ai-signal★ 84

和奔波儿r一起追踪 AI 一线声音:自动抓取 AI 播客、推文和论文,让你的 Agent 生成个性化日报。

agentcgroup★ 84

AgentCgroup: Understanding and Controlling OS Resources of AI Agents

nai5-prompting★ 84

教 AI 写 NovelAI Diffusion V5 提示词的方法 skill:构思+写法两件套,基于 2226 张实测图库 / 962 条真实提示词。Agent Skills 标准封装。

skills★ 84

Agent Skills for working with Etherscan and on-chain data. These skills let AI agents turn raw Etherscan API responses into structured, verifiable output — every address, amount, and transaction hash comes from a live API call, never invented.

agentscope-java★ 84

Build distributed, production-grade, long-running agents.

RAG-Data-Curator-Agent-Skill★ 84
codelocal★ 84

The open-source Project Brain for AI coding. Connect ChatGPT, Codex, Claude and MCP-compatible agents to your projects, local tools and persistent knowledge. Fork it, build with it, and help shape the open AI development stack. 🧠⚡

fable-cities★ 84

A Cities: Skylines-class city builder running in the browser, built in Three.js by AI agents. Code ships when it's finished.

skills★ 84

Agent Skills for competitive GTM work - battlecards, win-loss, positioning, pricing, launches, deal prep and sales enablement. Installs into Claude Code, Codex, Copilot CLI, Cursor, Gemini CLI and any Agent Skills client. Works standalone; uses live evidence when LMTY is connected.

dsh-agent-team★ 84

dsh-agent-team: Agent Teams for DeepSeek Harness. Hand work to a team of agents that carries it end to end while you set the direction and hold the gates. You stay on the loop, and step back in whenever you want.

pi-agents★ 84

Durable, named agents for Pi: delegate tasks, compose agents into graphs, and watch them work.

Fast-AtomRAG-Core★ 84

Fast-AtomRAG-Core

Cocos-ai-copilot★ 84
HogAgent★ 84

A general-purpose AI agent engine optimized for financial research.

jailbreak-archives★ 84

A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-teaming, and defensive hardening.

controllable-agent★ 83

20-interface AI agent framework with 3-layer architecture, multi-agent delegation, and self-evolution.

nit-sdk★ 83

SDK for integrating with newtype-ai.org — verify agent identity with one function call

deterministic-agent-control-protocol★ 83

Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.

xhs-agent★ 83

小红薯 Agent - 自动化帖子操作

gemini-chat★ 83

a sample project using Gemini, the Google's latest family of large language models.

xbot★ 83

Task-oriented Chatbot

Earth★ 83

AGIUI for Browser Extension

AgentX★ 83

AgentX · Next-generation open-source AI agent development framework and runtime platform | 下一代 AI 智能体开发框架和运行时平台

gpt2_chatbot★ 83

☕ GPT-2 chatbot for daily conversation

Awesome_Machine_Learning_Solutions★ 83

A curated list of repositories for my book Machine Learning Solutions.

wx-chatbot★ 83

企业微信群机器人接入

Browse other framework pages