Custom agents

[ICME 2026] Official implementation of Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations

实习.skill — 双非也能拿大厂 offer。帮你改简历、抠面经、准备面试，把真实背景翻译成面试官想要的样子。

Talk to any ArXiv paper using ChatGPT

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

A project implementing various agentic RL based on the Slime post-training framework

VICE is a security auditing CLI tool that finds vulnerabilities in your web applications.

Build digital human beings — autonomous, collaborative, and socially intelligent agents. FNzgGxU31RWiDgLr3GvxxSa42nRntvZNSG6aBMQ1pump

LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI for deep Android security research, built for researchers and hackers. Powered by Python orchestration and a Rust-accelerated core, enabling AI agent–driven hacking, credential recovery/cracking, APK analysis, intelligence gathering, runtime inspection.

Swift Concurrency agent skill for Claude Code, Codex, and other AI tools.

An SDK for working with LLMs and AI Agents from Apache Airflow, based on Pydantic AI

The open-source, self-hosted video conferencing software. Scalable, customizable, and with a powerful AI Meeting Agent.

EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysis, and multi-backend AI integration.

Access your terminal and your AI agent from any device — phone, tablet, desktop.

A fast, native RSS reader — plus an agent-facing CLI so your AI agent can read, search and triage your feeds from the shell.

Kolo is a text-based Python debugger for AI agents. Capture every executed function call, return value, local variable, HTTP request, and more in greppable trace files.

Use MCP and OpenAPI to safely control Proxmox VE VMs, LXCs, backups, and snapshots from LLMs and AI agents.

The Supabase of AI era. A modular, open-source backend for building AI-native software — designed for knowledge, not static data.

Hack Together: RAG Hack | Register, Learn, Hack

本项目为Generative Agents项目的重构+深度汉化版本，旨在为中文用户提供一个利于维护的基础版本，以便后续实验或功能拓展。

Hermes Agent skills and plugins: 350+ tools, memory providers, and guides for Nous Research's agent.

A dead-simple API to build LLM-powered apps

The LLM abstraction layer for modern AI agent applications.

An in-the-wild benchmark for AI agents in the production harness.

Keep your AI coding agents around. Launch Claude Code, Codex CLI, Gemini CLI, Pi Agent, and more from one place — side by side, connected, reachable, and ready to work across web, mobile, and messaging.

🔥 A Survey on AI Auto-Research

Agentic Development skills behind the JS Mastery workflow

Open-source, local-first 3D parametric CAD that runs in the browser for people and permissioned typed agents, powered by OpenCascade WASM.

The TypeScript framework for agents & workflows with react-like components. Lightning fast dev loop. Easy to learn. Easy to extend.

MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.

Stop hook for Claude Code that keeps the agent working until all plans and user requests are 100% complete

Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).

The design skill for Claude Code, Cursor and any coding agent. Stop shipping AI-slop UI: turn it into shippable, tasteful frontend. Install: npx skills add superdesigndev/superdesign-skill. Powered by superdesign.dev

🧠 Context Engineering Research - Not just another agent collection, but using research and context engineering to function as a collective. Hub-and-spoke coordination through Claude Code.

An intuitive LLM prompting framework for multifunctional agents, by explicitly constructing a complex "thought process" from simple natural language prompts.

AI 编程工具实战指南 — 66 个 Claude Code 技巧 + 9 款工具最佳实践 + 可复制配置模板 | AI Coding Tools Guide with 66 Claude Code tips

An experiment to give an autonomous GPT agent access to a browser and have it accomplish tasks

GMGN OpenAPI skills for AI Agent — query tokens, wallets, and market data, and execute on-chain trades across Solana, BSC, and Base.

YouTube Transcript API skills for AI agents. Get transcripts, search videos, browse channels. Works with OpenClaw, Hermes-Agent, Claude Code, Cursor, Windsurf.

200 production-grade DESIGN.md design systems for the world's best apps. Framework-neutral plus SwiftUI, Jetpack Compose, and Expo. Hand one to your AI agent, ship pixel-matched UI.

首个中医大语言模型——“仲景”。受古代中医学巨匠张仲景深邃智慧启迪，专为传统中医领域打造的预训练大语言模型。 The first-ever Traditional Chinese Medicine large language model - "CMLM-ZhongJing". Inspired by the profound wisdom of the ancient Chinese medical master Zhang Zhongjing, it is a pre-trained large language model designed specifically for the field of Traditional Chinese Medicine.

Mac compatible Ollama Voice

Survey on LLM Agents (Published on CoLing 2025)

Self-hosted Lovable/v0 alternative. Realtime database & storage included.

Comprehensive ML/AI interview codex with iterative system design, production-ready code, and 2026 standards. Includes LLM/GenAI, RAG systems, agentic AI, and algorithms from scratch.

🧃 Token weight loss. Lean output compaction for terminal-heavy agent workflows. Works as a native CLI tool or as an extension to popular coding and agent frameworks.

⚡ The Complete X/Twitter Automation Toolkit — Scrapers, MCP server for AI agents (Claude/GPT), CLI, browser scripts. No API fees. Open source. Unfollow people who don't follow back. Monitor real-time analytics. Auto follow, like, comment, scrape, without API. Follow Bot. Like bot. Grow your account automatically.

Production-ready MVP for securely chatting with your documents using pgvector

Data-Driven Evaluation for LLM-Powered Applications

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.

Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual intelligence (image/table captioning), agentic streaming chat, and inline citations. Powered by Gemini or local Ollama models.

ai-rules is a governance framework designed to solve "Architectural Decay" in AI-driven development. It forces AI Agents (Cursor, Windsurf, Copilot) to respect your project's boundaries, UI libraries, and design patterns.

A general framework for distilling human-created multimodal resources into reusable, executable skills that AI agents can browse, compose, and run, validated across diverse domains including web, PowerPoint, Excel, Blender, CAD, Unreal Engine 5, and REAPER-based music production.

💡 Awesome RAG: A resource of Retrieval-Augmented Generation (RAG) for LLMs, focusing on the development of technology.

A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.

CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.

Open-source Claude Code skills, agents, and slash commands for AI-powered penetration testing, bug bounty hunting, and security research

Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images

A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.

MCP server SDK/example implemented entirely in bash — build a Model Context Protocol server with no runtime dependency beyond a POSIX shell.

🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.

🕵️‍♂️ Library designed for developers eager to explore the potential of Large Language Models (LLMs) and other generative AI through a clean, effective, and Go-idiomatic approach.

Framework for building enterprise-level assistant agents.

Self-hosted platform for running coding agents (Claude Code, Codex, Hermes) in isolated sandboxes with vault proxy.

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents

The Agentic Startup - A collection of Claude Code commands, skills, and agents.

本书围绕 DeerFlow 2.0，从理论到源码，系统讲解如何进行二次开发。(精校)

Pocket-sized AI chatbot built using a RPI Zero 2w / 5

A multi-agent world model of US equity markets — simulating institutional players, information asymmetry, and emergent price dynamics

A MicroKernel Multi-Agents System Framework for Adaptive Social Simulation Powered by LLMs

Mega is an open-source implementation of Google Piper — a Git-compatible monorepo engine built for the AI Agent era.

Exact structure out of any language model completion.

An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style.

Bring Claude's Artifacts feature to ChatGPT

Official code for paper: Chain of Ideas: Revolutionizing Research via Novel Idea Development with LLM Agents

agent q - oss advanced reasoning and learning for autonomous ai agents

Python CLI toolkit for Amazon Bedrock AgentCore (legacy). For new projects, use the AgentCore CLI: https://github.com/aws/agentcore-cli

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

A highly efficient, secure, and stable application development platform with excellent performance, easy scalability, and deep integration of AI capabilities such as LLM, AI Chat, RAG, and Agents.高效、安全、稳定的服务研发平台，具备良好性能，同时易扩展，深度集成LLM、AIChat、RAG、Agent等AI能力

HackAgent is an open-source security toolkit to detect vulnerabilities of your AI Agents

🧠 AI-powered Personalized Exam System: Integrating OpenPangu LLM, Knowledge Graph RAG, and BKT algorithm for adaptive question generation and recommendation. 基于LLM与知识图谱的智能个性化出题系统。

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude Code, and Codex CLI.

A Gym for Agentic LLMs

Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

A framework where a deep Q-Learning Reinforcement Learning agent tries to choose the correct traffic light phase at an intersection to maximize traffic efficiency.

A command-line interface tool for serving LLM using vLLM.

II-Researcher: a new open-source framework designed to aid building search / research agents

SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until verified.

Hands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP servers. Includes code, slides, and video

Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.

Info about many of my Terraform, AWS, DevOps, and AI (tada!) projects.