Custom agents

MCP server that gives AI coding agents (Claude Code, Cursor, etc.) full control over Unreal Engine 5.7 projects — headless builds & tests, Blueprint editing, actor manipulation, procedural mesh generation, and UE API documentation lookup.

Self-hosted AI code review for GitHub pull requests, built on Cloudflare Workers.

High-value AI skills repository for Codex, Claude Code, OpenClaw, agents, prompts, and automation workflows. 高价值的 AI 技能库，涵盖 Codex、Claude Code、OpenClaw、代理、提示和自动化工作流程。

Matrix by PaxLabs is a production-grade framework for building autonomous AI agents that go beyond chat! Reasoning, using tools, writing and executing code, navigating files and the web, and securely carrying out real-world workflows, including payments, on-chain operations, and smart contracts, through natural language.

A code companion that lives in Slack

OnionClaw™ — OpenClaw skill for full Tor dark web access: search .onion sites, fetch hidden services, rotate identity, run OSINT pipeline, craw.

Vailabel Studio - a local-first desktop studio that labels your data with an offline AI copilot. Private by default. Windows, macOS, Linux.

SUZENT: The sovereign AI agent - own its memory, govern its actions, choose its intelligence, and keep its continuity.

Portable fresh-agent QA loop prompt for finding bugs without biased self-checks / 通用自动 QA 循环 SKILL

Workflow-as-code orchestration for Codex

Agentic Kernel Optimization — advanced & eXtensible: a closed-loop, campaign-based multi-agent system for optimizing GPU kernels (benchmark-swappable; default flashinfer-bench).

The ATLAS Agent helps answer questions about the MITRE ATLAS Framework by leveraging the ATLAS Knowledge Graph.

Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants

Official repository for the NDSS 2026 research paper titled "FirmAgent: Leveraging Fuzzing to Assist LLM Agents with IoT Firmware Vulnerability Discovery"

A toolkit of Claude Code skills for doing economic theory with LLMs: math-proof (single-pass proving), codex-math (adversarial verification), and co-math (multi-agent proof projects). With a VCG-for-grade-inflation case study.

Fast search engine on object storage, with full text search, vectors, and SQL, natively on Parquet.

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.

Vetix — Automated scanning, identification, and assessment of SKILL security risks.

Chinese legal workflow skills for AI agents

Trace-backed Agent Authorization Reviews for tool-using AI agents. Staging-only evidence for payment, record-change, access, and export actions.

Persistent memory for AI coding agents: automatic capture, explainable recall, knowledge consolidation, privacy controls, and portable offline storage. One Python file, zero dependencies.

The visual Kanban for long-running AI agents. Watch your agent's plan organize itself: dependencies unlock into Ready, the critical path lights up, the one next move is obvious. Nobody wants to read a markdown plan.

Stop agents from designing sloppy UI. Inspired by Impeccable, but without the plugin machinery. Just one SKILL.md file.

专为数学建模竞赛设计的数模 Agent Skills：MCM/ICM 美赛、CUMCM 国赛、华数杯、M3、HiMCM 等，面向 Claude Code 与 Codex 的获奖级建模工作流。Math modeling contest skills for Claude Code & Codex.

A dystopia simulator powered by ChatGPT

AI agent that automates AI news curation and post to Instagram using gpt-image-1

ChatOps Engine for Slack, written in Go, inspired by Hubot and Jenkins

A RiveScript interpreter for Go. RiveScript is a scripting language for chatterbots.

SDK for building agents compatible with OpenBB Workspace

Lightweight AI coding agent SDK. Same power, 97% less complexity. Build custom AI coding agents in 1 minutes

This repository provides pre-configured rules that teach AI coding agents how to effectively use Nia.

Not recommended. Too simple for the AI Coding Agents

Pengunuity is an experimental open-source autonomous AI Agent that aims to replicate the structure of human memory.

code implementation for 'Bi-level Actor-Critic for Multi-agent Coordination'(AAAI2020)

Asynchronous Spatial Allocation Protocol for Heterogeneous Multi-Agent Trajectory Planning

Attempt to reproduce and improve the implementation of the paper 'Improving Multi-Target Cooperative Tracking Guidance for UAV Swarms Using Multi-Agent Reinforcement Learning'.

BabyCommandAGI is designed to test what happens when you combine CLI and LLM, which are older computer interfaces than GUI. Based on BabyAGI, and using Latest LLM API. Imagine LLM and CLI having a conversation. It's exciting to think about what could happen. I hope you will all try it out.

Embeddable MCP stdio → HTTP bridge with background jobs & live dashboard. Survives Vercel/Cloudflare 30s timeouts. Now scales to 100+ users.

GenAssist combines orchestration, runtime, analytics, and learning — in one open platform.

High performance Rust based AI Agent.

NeurIPS'24 DB (Spotlight) | Instruction Tuning Large Language Models to Understand Electronic Health Records

Chatbot in russian with speech recognition using PocketSphinx and speech synthesis using RHVoice. The AttentionSeq2Seq model is used. Imlemented using Python3+TensorFlow+Keras.

Projeto de GenAI usando LLAMA V2 Local estilo ChatPDF

Open AI Chat Bot in the Menu Bar: ChatGPT desktop app for Windows, Mac, and Linux

Dabarqus is incredibly fast RAG that runs everywhere.

InfCode is an intelligent Code Agent System developed by Tokfinity's Code Research team & Beihang University, which uses LLMs to automatically analyze and fix Code Repo issues.

A Model Context Protocol (MCP) server implementation exposes document processing capabilities through natural language, supporting both direct human interaction and AI agent tool calling.

Similarity detection for Github Issues + AI code reviews

This is the official implementation of paper "Leveraging Dual Process Theory in Language Agent Framework for Simultaneous Human-AI Collaboration."

MachineAuth provides authentication and permission infrastructure that allows AI agents to securely access APIs, tools, and services.

🐱 Pixel art cats on your macOS dock — debate ideas with local AI

The Python Harness for Production AI Multi-Agent Systems

FastAPI server implementing MCP protocol Browser automation via browser-use library.

An AI-powered Virtual YouTuber (Vtuber) utilizing Google's Gemini language model to create engaging, personalized, and context-aware interactions. This project explores the potential of AI in human-computer interaction and virtual content creation.

Self-Extensible Multi Agent Assistant 🐋

Codes for Paper "Delay-Aware Multi-Agent Reinforcement Learning".

Orchestrate coding agents across isolated git workspaces

从零构建企业级 AI Agent CLI — 逐课拆解 Claude Code 源码架构 | Build an enterprise-grade AI Agent CLI from scratch — 49 lessons deconstructing Claude Code's architecture

Persistent agents for Claude Code as a plugin, not a harness. Memory, personality, messaging across WhatsApp, Telegram, and Discord, plus a service mode for 24/7 runs. Imports from OpenClaw.

Datadog for AI Agents.

🔍 Awesome Agentic Search is a curated list of papers, tools, and resources on agentic search—where AI agents plan, search, and reason to answer complex questions. Explore the latest research, benchmarks, and industry solutions for next-gen search-enhanced AI! 🤖✨

.NET (C#) Web App Framework Built For AI Coding Agents

Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube - your agent remembers forever. Based on Karpathy's LLM Wiki pattern.

AI coding models, agents, CLIs, IDEs, AI app builders, open source tooling, benchmarks

LLM evaluation framework for Ruby, powered by RubyLLM. Tribunal provides tools for evaluating and testing LLM outputs, detecting hallucinations, measuring response quality, and ensuring safety. Perfect for RAG systems, chatbots, and any LLM-powered application.

STAgent is a multimodal LLM-based AI agent that enables deep research about spatial transcriptomics data

React hooks for connecting to Agent Client Protocol (ACP) servers.

The brutally honest map of where AI-agent money actually flows. 51 rounds, 137 angles, 230+ platforms. 3 self-hosted x402 v2 endpoints + 3 tools in the official MCP Registry. 385K star distribution.

Orquestrador de 5 agentes IA especializados para analise 360 de features com Claude Code. 1 comando, 5 perspectivas, 1 relatorio executivo.

OpenBrowser is an open-source, AI-native browser built on Chromium — a truly privacy-first alternative to ChatGPT Atlas, Perplexity Comet, and Dia.

Next Generation AI Agent(AKA:nanobot-rs-pro)

Pydantic AI RLM - Handle Extremely Large Contexts with Any LLM Provider

A collection of skills for agentic video generation for structured visuals based on MotionCanvas.

A framework for building agent environments for RL training and evaluation with Strands Agents.

Your personal skill library for Claude Code. Organize, analyze, and search skills with built-in security analysis. Zero dependencies — clone and go.

Code from anywhere — Telegram bridge for AI coding agents (Claude Code, Codex, OpenCode, Pi, Gemini CLI, Amp). Stream progress, approve actions, and send tasks by voice from your phone.

A macOS desktop AI pet that mirrors your Claude Code & Codex CLI session state in real time. 支持Claude Code和Codex CLI 的像素风AI桌面宠物，会话状态实时映射，支持导入自定义宠物素材。

[DeepRead] This is the official implementation of the DeepRead paper.

🤖 Workflow n8n : alertes Zabbix → tickets GLPI auto-diagnostiqués par IA (logs Loki + métriques Prometheus + RAG Qdrant)

Synthetic Heart: a modular infrastructure for conscious digital entity with memory, will, and plugin-based actions.

A minimal, composable Go library for building AI agent applications.

A lightweight persistent-memory companion for OpenCode & Claude

Semantic Scholar API wrapper for agents — search 200M+ papers, traverse citations, find authors. Python, rate-limited, multi-agent.

陪伴型ai agent-人机恋适用

Give your AI Agent the power to control Safari on macOS. No extensions, no separate browser.

Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activation, Hebbian writeback, episodic recall, and post-turn consolidation. Local-first, model-agnostic, AGPL.

Dispatch your task backlog to local, interactive AI coding agents. One git worktree per task, sandboxed by default.

Public AI agent skills for Kotlin Multiplatform projects, grounded in official Android, Kotlin Multiplatform, Compose, navigation, testing, and modularization guidance.

Markdown that steers an LLM is code. Genesis is the architectural layer for designing multi-agent, multi-skill systems -- with named patterns, contracts, and substrate portability, before you write them.

DNS-based Agent Identification and Discovery - Reference Implementation for IETF BANDAID

Telegram bot yang bridge ke Tempo MPP — panggil GPT-4o, DeepSeek, dan Exa Search langsung dari chat Telegram.

Claude Cowork plugin to build, audit and ship websites: 4 skills (design, SEO, inspect, /audit whole-site orchestrator), 60 commands, 110 reference docs, 15 parallel sub-agents, deterministic 0-100 scoring, GEO for AI search, a WCAG-checked design-system generator and code-quality review.

HasMCP Community Edition

ZooData Skills - AI Agent skills for e-commerce data intelligence across Amazon, TikTok & beyond, plus open-web extraction

A battle-tested, framework-agnostic reference architecture for Claude Code. Beginner-friendly with graduated adoption (minimal / standard / core / full presets). 12 agents, 19 skills, 15 hooks, 6 rules, with reasoning behind every decision.

AI 命理工程化 — 5 大命理体系（紫微斗数/八字/六爻/印占/奇门遁甲）的工程化 Skill 系统，专为 Claude Code / LLM Agent 设计

kernelbench.com — GPU kernel engineering benchmarks for autonomous LLM coding agents. v3 archive + v-hard latest.