Custom agents

Simple AI Agent to answer questions for specific domains based on website docs

Autonomous Qwen3-VL training-code research on the official DocVQA benchmark. main: NVIDIA multi-GPU, mlx: Apple Silicon/MPS.

K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI systems to assist with cluster management, troubleshooting, and deployments

Switchboard plugin for VS Code, enables subscription-based AI agent teams

This is a repository for the course "Agentic AI Engineering" by Towards AI.

A fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other desktop applications just like humans. Based on E2B oss code.

Cross-platform desktop app for agentic chat powered by Claude Agent SDK.

Local-first LLM proxy that meters what every agent run costs and kills runaways before they drain your budget. Free, MIT.

Entity-level code review. Triages pull requests by structural risk using cross-file dependency graphs and LLMs that read for meaning.

Highflame ZeroID: Autonomous Agent Identity Management System (AAIMS)

AI-Assisted Reverse Engineering with Ghidra

398 份 AI/LLM 中文讲义，支持在线阅读、PDF 下载和 LaTeX 源码查看 | Stanford CS336/CS224R/CS25 · Berkeley LLM Agents · 南京大学生成式软件工程 · 月球大叔 · 硅谷101 · 十字路口 · Agent 工程实践

Trend-to-Video Agent Framework for publish-ready short video packages

The Software Factory

AI agent Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, ai agent, and growth engineering, ai agent

A context graph which is based on confidence-aware belief that drives more determinstic reasoning in long-horizon agents.

🦈 2-line install personal AI assistant. 11 AI runtime surfaces (Claude, Codex, Cursor, Gemini, Grok, Antigravity, OpenCode, Copilot), 200+ skills, zero ban risk.

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.

The companion AI agent that learns, adapts and gets the work done no matter the task

Autonomous Qwen3-VL training-code research on the official DocVQA benchmark. main: NVIDIA multi-GPU, mlx: Apple Silicon/MPS.

A curated list of AI copilots and assistants that enhance productivity across various domains, with a focus on coding and software development tools.

It understands your voice commands, searches news and knowledge sources, and summarizes and reads out content to you.

:smiling_imp: An extensible chat bot framework. sactive-bot is an evolution of the open source hubot project. - https://www.shipengqi.top/sactive-bot .

Desktop app for running multiple AI agents in parallel. Each agent gets its own terminal, editor, and git worktree, all in one window.

M2I is a simple but effective joint motion prediction framework through marginal and conditional predictions by exploiting the factorized relations between interacting agents.

Self-hosted AI RAG + MCP Platform

Automating prompt engineering using AI Agents.

Give your OpenClaw AI agent a WhatsApp number. Official Meta Cloud API via Kapso. No ban risk.

File cache with diff tracking for AI coding agents. Drop-in MCP server that cuts token usage by 26%.

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

AI integration layer for Jido agents with LLM orchestration and reasoning strategies.

On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.

基于 Claude Code 的诉讼法律服务智能分析系统，采用10个 SubAgents 协作的模式，将复杂的诉讼案件分析分解为多个可独立执行的工作流，实现法律文书的工程化生成。

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.

[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Agents & Agentic Graph Engineering).

Using AI to generate 3D models

Public Claude Code skills for Personal Corp, product work, AI operations, and agent-assisted development

Turn human SOPs into deterministic, gated agentic workflows — a Claude Code plugin.

按问题复杂度自动分流的电商客服 RAG：简单问题直接回答；复杂问题经过多跳检索并自我纠错；查单、退改通过工具调用完成，且高风险写操作必须先经人工确认。基于 FastAPI 和 LangGraph，混合检索并附带引用，内置离线评测与 Prometheus 指标。涵盖简历写法和项目面试拷打

An autonomous agent that profiles, optimizes, and validates AI training code.

Enable Claude, ChatGPT, and other AI agents to analyze markets, fetch real-time odds, and execute trades on Polymarket using the Model Context Protocol (MCP).

Amazon Sumerian Hosts (Hosts) is an experimental open source project that aims to make it easy to create interactive animated 3D characters for Babylon.js, three.js, and other web 3D frameworks. It leverages AWS services including Amazon Polly (text-to-speech) and Amazon Lex (chatbot).

Code for Arxiv 2023: Improving Language Model Negociation with Self-Play and In-Context Learning from AI Feedback

Examples of AI Multi-Agent Solutions

ELF provides persistent memory, pattern tracking, and multi-agent coordination for Claude Code sessions without the need for an api key

Runtime Security for tool-using AI agents, with local policies, pre-action enforcement, and forensic audit trails.

Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"

🎯 Read research papers faster with AI. Resophy is an HTML-based AI paper reader with: 🤖 AI Translation & Analysis — instantly understand structure, contributions, and results 🚀 Daily arXiv Recommendations — discover relevant papers with less noise 🛠️ Vibe Coding Oriented — agent-friendly and easy to customize

A simple, easy-to-hack Vector Database

MetaOpenFOAM: an LLM-based multi-agent framework for CFD

Give your AI agent a voice on every chat platform.

Hands-on LLM Engineering including Agentic AI Project

HiCAD,一款AI驱动的CAD建模平台

Local-first skill management platform for AI coding agents: dual SQLite+Git persistence, semantic search, bandit-optimized suggestions, and MCP integration

Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.

A General-Purpose Environment Framework for Scalable Multimodal Agent Evaluation and RL

Developer recipes for Meta Model API — agentic workflows, multi-agent orchestration patterns, and use case examples with cost comparisons. Colab notebooks + standalone Python files.

Open-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skills, a real browser, 4,700+ MCP servers, budgets, approvals and an audit trail. An alternative to ChatGPT Enterprise and Grok Bot. Apache-2.0, built on Pydantic AI.

Claude-type skills for institutional equity research — 25 AI agent skills with SEC filings, XBRL financials, earnings calendars, DCF/comps/LBO models, and PPT generation. Powered by agentii.ai data plane. Works with Claude Code, OpenCode, Codex, OpenClaw, Goose.

Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.

True on-device AI SDK for Kotlin Multiplatform (Android, iOS, Desktop, JVM, WASM). LLM inference, Speech-to-Text, Image Generation, Agent Framework and RAG — powered by llama.cpp, whisper.cpp and stable-diffusion.cpp.

iPhone notifications, approvals, Live Activities, on-call paging and signed-in mini apps for developers and their agents.

An AI framework for building cool things.

Local-first memory layer for OpenClaw, Codex App, and Codex CLI: capture, recall, dedupe, and native sync.

A curated, comprehensive collection of open-source AI tools, frameworks, datasets, courses, and seminal papers.

Your custom 24/7 AI trading agent. Inspired by nof1.ai

An environment for testing AI pentesting agents against a simulated network.

[DEPRECATED] Superseded by systempromptio/systemprompt-template and systempromptio/systemprompt-core. Multi-modal MCP client for voice-powered agentic workflows.

AI Agents with Bedrock

PyTorch implementations of MADDPG, MAPPO (coming)

Immersive workshop showcasing the remarkable potential of integrating SoTA foundation models to enhance product experiences and streamline backend workflows. Leverages Microsoft's Copilot stack, Microsoft Agent Framework and Azure primitives to offer an engaging and comprehensive introduction to AI-infused app development and deployment

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SpringBoot MyBatis实现 采用Docker容器化部署 前台商城系统包含首页门户 商品推荐 商品搜索 商品展示 购物车 订单流程 会员中心 客户服务 帮助中心等模块 后台管理系统包含商品管理 订单管理 会员管理 促销管理 运营管理 内容管理 统计报表 财务管理 权限管理 设置等模块 微信小程序开发资源汇总 最全中华古诗词数据库 唐宋两朝近一万四千古诗人 接近5 5万首唐诗加26万宋诗 两宋时期1564位词人 21 5 首词 uni app 是使用 Vue 语法开发小程序 H5 App的统一框架2 21年最新总结 阿里 腾讯 百度 美团 头条等技术面试题目 以及答案 专家出题人分析汇总 科学上网 自由上网 翻墙 软件 方法 一键翻墙浏览器 免费账号 节点分享 vps一键搭建脚本 教程AiLearning 机器学习 Mach

[ICML 2026] effGen: Enabling Small Language Models as Capable Autonomous Agents

NexAU (AU for Agent Universe), a general-purpose agent framework for building intelligent agents with tool capabilities.

A secure local gateway for AI agents to reliably call approved enterprise APIs, tools, and services.

AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language CatBot assistant, visual DAG workflow engine, HPC job submission. Tauri desktop app with SvelteKit frontend and FastAPI Python backend. Drives VASP, ORCA, CP2K, QE, GPAW, DFTB+, SIESTA, LAMMPS.

lnwjud — local AI-agent runtime & MCP gateway

Multi-agent task orchestration for coding agents. Turn one goal into an ordered plan of tasks (each with its own runner, model and mode), then execute and verify the results.

面向个人（编程小白）、小中型企业，覆盖后端服务、Web 前端和移动端h5、APP、小程序开发

Messages between AI coding sessions in different vendors' clients, such as Claude Code and Codex. Local, open source, no lead agent. https://getacc.dev

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall (keyword/vector/BM25/entity), and a memory panel. 10 model tools, MCP server, CLI.

GeDi: Generative Discriminator Guided Sequence Generation

Resolve the issue of DLLmain function in white and black DLLs hanging when calling shellcode

An Open Source Playground with Agent Datasets and APIs for building and testing your own Autonomous Web Agents

Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery

An AI agent that automates company research and lead prospecting (powered by langgraph and firecrawl)

A workflow harness that helps AI coding agents plan, review, test, and ship safer code.

🤖 AI agents on autopilot. Any model. Runs local, cron, CI/CD, or Docker.

GigaAgent — это универсальный агент-оркестратор для решения широкого круга задач (ReAct + REPL)

OpenSeek - 广度求索: open-source TUI coding agent with multi-provider routing, MCP, LSP, and Plan/Agent/YOLO modes.

Automotive software engineering is one of the most complex and regulated domains in the world. Engineers juggle **ISO 26262 functional safety**, **AUTOSAR architectures**, **MISRA compliance**, **cybersecurity standards**, and **real-time embedded constraints** -- all while shipping on aggressive timelines.

USPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents, automated 35 USC 112 compliance checks, prior art search, diagram generation. GPU-accelerated with skills and autonomous agents.

🦈 2-line install personal AI assistant. 11 AI runtime surfaces (Claude, Codex, Cursor, Gemini, Grok, Antigravity, OpenCode, Copilot), 200+ skills, zero ban risk.

SwiftUI Front-End Design Skills — Six Ironclad Rules Against AI Sloppiness, Design Direction Consulting, Brand Asset Guidelines, and Five-Dimensional Review. Supports all AI agent platforms, including Claude Code, Cursor, Codex, and OpenCode.

🧠 Production-grade memory sidecar for AI agents — gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-tested. | 生产级外挂记忆系统，兼容Hermes/Claude/Cursor等任意AI智能体

How to design, build, and operate AI agents for infrastructure teams — safely. 13 chapters covering architecture, sandboxing, credentials, change control, observability, and more.

Learn AI Agents step by step, from scratch - from function calling to agent loops to multi-agent systems, orchestration, and evaluation.

Run many Claude Code (or Codex) sessions in parallel — across every project — from one screen. Local-first, git-worktree-isolated tasks, no API key.