Custom agents

Agentic Engineering for Reinforcement Learning

Multi-agent system for research, powered by ag2

AI-powered authorized security testing workspace. Maintained on the release branch (NestJS + Ink TUI + Web/Desktop).

Enables developers to build, deploy, and manage multiple specialized agents that work together to tackle complex workflows. Each agent focuses on a specific task, breaks down processes into manageable steps, assigns tasks to the appropriate agents, and ensures accurate, and reliable outcomes.

openJiuwen agent-studio provides zero-code and low-code visual development, workflow orchestration, and unified management for models, knowledge bases, plugins, and other resources.

If you can read ~200 lines of Python, you understand MCP.

Give your AI agent access to all crypto data — prices, wallets, social, on-chain, prediction markets. One skill, 83+ endpoints.

Self-hosted alert platform for ops teams. Telegram Bot API compatible. ACK, push, team chat.

The official implementation of "ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering"

A working POC of a GPT-5 jailbreak via PROMISQROUTE (Prompt-based Router Open-Mode Manipulation) with a barebones C2 server & agent generation demo.

A Benchmark for Evaluating Multi-Hop, Multi-Source Tool-Calling in AI Agents

A skill for coding agents that build, review, and refactor Web UI that should be easier for humans, screen readers, browser automation, Playwright tests, and AI agents to understand and operate.

Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

27 AI-ready skills for generating production-grade .NET code — Clean Architecture, CQRS, DDD. Works with Claude Code, GitHub Copilot, and Cursor.

ShaprAI — Agent Sharpener by Elyan Labs. Sharpen raw models into principled, self-governing Elyan-class agents. Requires beacon-skill, grazer-skill, atlas, RustChain.

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

Automate end-to-end AI governance with Microsoft Purview DSPM for AI and Defender for AI. Configure DLP, sensitivity labels, audit logging, and threat detection across M365 Copilot, Microsoft Foundry, Microsoft Fabric, and custom agentic solutions.

[NIPS2025] A decentralized, RAG-enhanced multi-agent framework for LLMs with dynamic task routing and agent evolution.

Skills and tools for scientific research with LLM agents. 给 Agent（如 Claude Code、Openclaw）提供的科研 skills

Skills for AI coding agents working with Capacitor (formerly capacitor-skills)

将任意线上网站的设计风格提取为一份结构化 `DESIGN.md`。本 skill 是 design-extractor Chrome 扩展的命令行 / AI Agent 移植版。

外贸B端全链路AI自动化获客转化Agent系统

MCP server for agentic AI-assisted development in SAP BW/4HANA

Elaina Ai : Your Magical AI Companion, Blending Intelligence 🧠 with Enchantment 🪄 By Murali

Curated index of 200+ AI tools, one writeup per tool with hands-on takes. Covers coding, design, research, video, voice, agents, music, local LLMs. Compare alternatives, see real pricing, find the right tool for the job.

MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland — 29 tools for virtual and live sessions

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.

Missing Xcode Tools Documentation

Search the web and primary sources, read full pages, and check every citation. MCP server for Claude, Cursor, Codex and more. Runs on your machine.

One dashboard for all your AI agents — manage teams across Claude Code, Codex, Gemini, Aider, and more. No database required.

Knowledge-enhanced multimodal Fire Safety Agent with two-hop reasoning, evidence-tree RAG, open-set guardrails, and four-layer memory.

Skills for agentic coding CLIs: output you can ship with minimal review, on work you can tell was worth doing.

Self-improving AI agent companies — Paperclip V2 fork with persistent memory, MCPs, skills management, and KPI tracking. Built by HarborSEO (harborseo.ai)

三合一排盤引擎：西洋星盤 + 人類圖 + 紫微斗數，原生天文/曆法計算，離線 deterministic，CLI + JSON（供 AI agent）。MIT。

开源研究管道 —— 文献综述、新颖性生成、引用验证与对抗性审查 | Open-source research pipeline — literature review, novelty generation, citation verification, and adversarial review.

Feature-rich all-in-one self-hosted server & server fleet management (Web UI): patching, monitoring (agent + agentless/SNMP), CVE scanning, CMDB, RMM, alerts & webhooks, Proxmox/VMware, Ansible, compliance & more — the Swiss-army knife to keep your servers healthy.

Native macOS app for managing and monitoring Docker — local and over SSH. Agent-ready: built-in MCP server and App Intents. Free and open source.

Schema-as-code memory for AI agents in Obsidian: typed cards, entity dedup, link repair, update-in-place, and Ebbinghaus decay. Plain Markdown you own — a Claude Code skill.

One-shot LLM eval cases by NAGI STUDIO - same prompt, different agents (model + harness), runnable artifacts side by side.

Open-source 100-day Python curriculum for AI, data, quant, LLM and agent projects

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

探索任务之间如何直接通信、交接并长期协作，同时提供一个真正可用的终端 AI 编程工具。 CodePlus 并不是为了直接复刻 Codex。我希望通过这个项目持续探索新的 Agent 协作方式，同时吸收现有工具中已经得到验证的优秀实践，并逐步把自己的理解变成可以公开、可以使用的技术实现。

ViForge is a local-first AI collaboration workbench for creative and knowledge work. It helps people turn ideas, judgment, and personal methodology into reusable agents, skills, knowledge bases, and evaluable workflows.

Local-only web GUI for inspecting agent skills (SKILL.md) across user, project, plugin, cache, and marketplace sources

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown library (loop-graph), not a framework.

A Network Arena for Benchmarking AI Agents on Network Troubleshooting

A WebView2 UI framework for foobar2000 - build the entire player in web tech (Vue/React) with native Windows 11 Mica/Acrylic effects. Ships a TypeScript SDK and an MCP server for AI agents.

A lightweight macOS menu bar companion that reads copied conversation text and AI responses from Codex, Kimi Work, Deepseek, QianWen, and other apps aloud via Doubao TTS. BYOK.

Sandbox for running AI coding agents autonomously: isolated, network-restricted, host-safe

Self-hosted memory server for AI agents. Your brain is a git repo, served over MCP and REST.

MCP server that turns any video — YouTube, Instagram, TikTok, Loom, X, Vimeo, direct URLs, local files — into transcripts, key frames, OCR text, and metadata for AI agents.

Source-grounded MCP memory runtime and Obsidian-compatible vault template for LLM agents.

EvoX Genesis is an autonomous system for long-horizon software evolution that recursively builds, continues, and transforms complex software from high-level objectives.

ActonOS is a single-purpose appliance operating system engineered as a customizable, self-governing AI agent kernel running 24/7.

REVLab - Windows PE reverse engineering workflow platform (static analysis, unpacking, disassembly, decompile, dynamic sandbox, network capture, custom pipelines, MCP + AI agent integration). For lab/legal compliance testing only.

AuditMind 是一个面向法规合规与审计场景的 AI Agent 系统，支持法规知识管理、可追溯规则抽取、文档合规审计、审计任务管理和基于原文证据的智能问答

Go SDK for standardizing local agent execution across `codex`, `claude`, `cursor` and `codebuddy`.

⚡ Modular prompt-engineering framework for AI Agents (Cursor, Claude Code, Copilot). Forces structured SDLC, linear execution, context isolation, and systematic debugging via a standalone Windows launcher. Stop vibe coding, start agentic discipline! 🚀

Agent skill and field guide: the security pitfalls that block Omarchy plugins on the marketplace, from 5,000+ maintainer reviews

Step-by-step handbook for building autonomous security agents with clear limits, runnable lessons, diagrams, and honest evidence.

Free, open source, realtime task manager. Issues, boards, sprints, projects and docs that sync instantly. Keyboard-first, self-hostable, with an MCP server for AI agents. No pricing, ever.

AI-agent skill for reproducible, validated GIS analysis — from authoritative data discovery to interactive maps, on an open-first geospatial stack (OSM, Overture, STAC, DuckDB, PostGIS, QGIS, MapLibre).

The attention layer for coding agents.

[ACL 2026] MegaRAG: Multimodal Graph-based RAG

Free ADB GUI and Android Emulator control panel for macOS. One click for dark mode, font scale, RTL and pseudo-locales, TalkBack, layout bounds, network speed and GPS: no adb commands. Layout Inspector in dp for any app (Compose and Views) with Figma overlay and TalkBack-order audit. Plus an MCP ser

Free HTTP/SOCKS proxies with every check on the record: passed, failed or couldn't run, and when. Hourly list, --pick --verify, --diagnose, rotating proxy, Python API, MCP server.

Your AI agent builds exactly what you asked for, and proves it. A Claude Code plugin: brief → quoted requirements → spec → tickets → blind acceptance check, with a live capybara pane and a model per stage.

Free Gemini Spark skills library with reusable Google Workspace AI agent workflows for Gmail, Calendar, Drive, Docs, Sheets, Slides, YouTube, Maps and business automation.

CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters

Open-source product marketing skills for Claude Code and Codex: research, positioning, messaging, GTM, launches, and competitive intelligence.

Eremos is a lightweight framework for deploying autonomous swarm agents that detect early on-chain activity across Solana.

Implement korean restaurant reservation dialogue system based on hybrid code network.

A Multipurpose GPT Chatbot with AI Image Generator, Counting , Logging, Leveling, Reaction Roles, Boost Tracker, Welcomer, Ticket.

Multi-agent PPO with noise (97% win rates on Hard scenarios of SMAC)

Sirji is a framework to build & run custom AI agents for your everyday dev tasks.

:bomb: Bot para o Telegram do grupo do Be MEAN

This is a PowerShell script that automates the process of setting up and running VICUNA on a CPU (without a graphics card) using the llama.cpp library and a pre-trained ggml-vicuna-13b-4bit.bin model. The script downloads and extracts the required files, creates a batch file to run VICUNA, and creates a desktop shortcut to launch the batch file.

Go (GoLang) package for Facebook Messenger API and Chat bot

A framework for orchestrating AI agents using a mermaid graph

Falco-powered policy and visibility layer for AI coding agents

A comprehensive Model Context Protocol (MCP) server that enables AI agents to create fully mixed and mastered tracks in REAPER with both MIDI and audio capabilities.

multi-agent data collection and distributed learning in CARLA simulation

Pytorch Implementation for KDD22 paper "Multi-Agent Graph Convolutional Reinforcement Learning for Dynamic Electric Vehicle Charging Pricing"

Langchain tools to search/extract/transcribe text transcripts of Youtube videos. Some of this has been integrated into LangChain main branch

Generate Python Package with Simple Prompts

Build a dialog dataset from online books in many languages

`fdgt` is a mock API for the Twitch. Via `fdgt`, you can simulate events without having to spend a penny!

Welcome to the Cybertron AI Agent project, an open-source initiative leveraging the Trend Micro Cybertron AI model in the NIM catalog.

An agentic tool to configure Dockerfiles for any repo

LLMs write a lot of code, but humans still need to understand it...for now. Code Diver provides 2 things a skill that teaches your agent how to build a connected graph of higher level semantically related code as it works and then ingests, builds and visualizes this graph in realtime so you can review massive changes more easily.

This is another way to bypass the restriction of calling dl functions for system lib.

Official Code for "Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction (ECCV 2022)"

Extract data from websites in LLM ready JSON or CSV format. Crawl or Scrape entire website with Website Crawler

让 AI Agent 像人一样没事找事 —— 内生思考系统 🦞

Generate-on-Graph: Treat LLM as both Agent and KG for Incomplete Knowledge Graph Question Answering. EMNLP 2024 Main

Online deadlock-free multi-agent trajectory planner using linear safe corridor (LSC)

Give your AI assistant memory, skills, and autonomy. Persistent memory, integration skills, and autonomous workflows

A sophisticated RAG intelligence engine for Singaporean laws, policies, and history. Comes with a triple-AI failover backend (Gemini/Llama/Groq), semantic embeddings using FAISS, and an Apple-inspired interactive UI. Designed with precision and high availability in mind.

Token-efficient navigation substrate for AI coding agents. Index code once and retrieve only the symbols you need.