Custom agents

个人微信号自动回复、陪聊、查天气、查垃圾分类。新增查看今日新闻和知乎热榜功能。

协程、高性能、灵活的聊天机器人 & Web 开发框架（炸毛框架）

A comprehensive, production-ready framework for building intelligent AI agents with advanced capabilities including tool calling, persistent memory, intelligent concurrency, and event-driven observability

An NVIDIA AI Workbench example project for an Agentic Retrieval Augmented Generation (RAG)

Attention-based Deep Reinforcement Learning framework for portfolio allocation on S&P 500 equities. Includes custom environment, policy architecture with cross-sectional attention, PPO/A2C/REINFORCE agents, training/evaluation pipeline, and fine-tuning grid search.

Welcome to **LiveRecall**, the open-source alternative to Microsoft's Recall. LiveRecall captures snapshots of your screen and allows you to recall them using natural language queries, leveraging semantic search technology. For added security, all images are encrypted.

Structure-aware Multi-Index RAG System

一个用于 B站直播间的机器人与积分系统。 支持监听指定直播间的弹幕、礼物、进入、关注、分享等事件，并提供积分商城、签到系统、PK 播报、礼物答谢、关键词自动回复、定时广告、自动禁言等完整的互动功能。 内置数据分析，可生成观众消费统计、盲盒盈亏、弹幕词云等报告，帮助主播提升直播间的互动性与运营效率。

Remote MCP Server that securely connects Enterprise context with your LLM, IDE, or agent platform of choice.

Run Surfer-H agents powered by Holo1 using the Surfer-H-CLI. Includes example tasks, scripts, and configurations.

CivAgent is an LLM-based Human-like Agent acting as a Digital Player within the Strategy Game Unciv.

LLM-KG4QA: Large Language Models and Knowledge Graphs for Question Answering

Code for our paper: Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

Deploy a fleet of AI agents (OpenClaw, Hermes) on your machine in 10 minutes — use your ChatGPT subscription, no cloud bills. Open-source fleet manager with browser dashboard.

An AI companion that lives on your desktop - OpenGuider watches your screen, listens to your voice, and guides every step with clear actions.

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

A lightweight secure Self-evolution engine built in Rust, featuring a built-in native system-level sandbox, zero dependencies, and fully local execution.

Local knowledge graph for AI agents. Hybrid search + MCP server for Obsidian vaults.

Bootstrap AI agent companies from modular templates.

A list of AI memory projects（ AI长期记忆的开源和商业项目列表）

AI-powered Pokemon gameplay agent with headless emulation, REST API, and live dashboard. Works with any LLM.

全栈式自动数学建模竞赛 Claude Code Skill — AI 担任 Autopilot，人类担任 Copilot。支持国赛/美赛，AP/Manual 双模式，GitOps 流水线，强制代码自证。

Native Safari browser automation for AI agents. 80 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chrome DevTools MCP with 40-60% less CPU/heat on Apple Silicon.

一个基于 LaTeX 的中文简历模板，配合 Claude Code 的 /Auto-CV Agent Skill，支持导入简历，自动提取内容并转换和交互式自然语言描述制作简历两个功能

A React component library for rendering AI-generated markdown — LLM streaming, LaTeX math, Mermaid diagrams, GFM, syntax highlighting, CJK-friendly typography, and cross-chunk reference coordination.

[KDD 2026] MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation

Open-source agent skills for AI for Science: topic exploration, literature survey, experiments, paper writing, and integrity audit — driven by any coding agent.

An Enterprise-Grade Full-Stack RBAC Permission Management System Built with Go + React

The Deterministic Contract Layer for AI. Defines strict tool-calling protocols, the Token Box Model for context allocation, and type-safe execution. Treats AI behavior as compiled software, not probabilistic improvisation. Eliminating runtime failures since 2025.

This repo is a live list of papers on game playing and large multimodality model - "A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges".

Lazy, AI chatbot service.

An AIO Discord bot for sneaker groups

Multi-turn dialogue baselines written in PyTorch

A very simple implementation of a service for a mattermost bot that uses ChatGPT in the backend.

Integrate user-agent detection in an idiomatic React way

Minimal typescript agent framework that keeps it simple and gives you control - no BS

AI-driven web automation agent that uses Playwright for browser interactions and LLM integration for intelligent decision-making. It's designed for reliable, adaptable web automation with robust element detection and contextual understanding. It's single agent by design, and it is built with getting solid benefit out of smaller models in mind.

Like ChatGPT's voice conversations with an AI, but entirely offline/private/trade-secret-friendly, using local AI models such as LLama 2 and Whisper

AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query file structure, dependency graphs, and change impact. Built for Copilot, Cursor, and any tool-calling LLM. 面向 AI 编程助手的代码库感知技能——生成持久化知识图谱，精准查询文件结构、依赖关系与改动影响半径。

An Multi-Modal LLM Powered Agent to automatically solve Captchas

[MTI-LLM@NeurIPS 2025] Official implementation of "PyVision: Agentic Vision with Dynamic Tooling."

Infra-agnostic hosting framework for browser agents.

Independent research on Claude Code internals, Claude Agent SDK, and related tooling.

DarkGPT Chat Explorer is an interactive web application that allows users to engage in conversations with various GPT (Generative Pre-trained Transformer) models in real-time. This repository contains the source code for the application.

🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and connect to Claude, Cursor, and more.

Open source AI agent for e-commerce

Spring Boot skills for AI coding agents

Bridge Claude Code CLI with Feishu/Lark via WebSocket. 飞书 × Claude Code 实时对话。

[ICLR 2026] VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

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.

Vibe Coding on one side, looking stylish on the other.

Distribb CLI, Claude, Codex, Hermes, OpenClaw skill for AI-powered SEO. Write content with your own AI, publish through Distribb's backlink network.

Two AI VTubers co-hosting one live show — the realtime engine & orchestration. Open-core, battle-tested by a daily stream.

One install. Shared memory, smart routing, disciplined workflow, multi-AI audits -- across every AI coding agent. No BS.

Framework for learning dialogue agents in a two-player game setting.

A multi agent path planning solution under a warehouse scenario using Q learning and transfer learning.🤖️

Blink is a self-hosted platform for building and running custom, in-house AI agents.

🤖 Visual AI agent workflow automation platform with local LLM integration - build intelligent workflows using drag-and-drop interface, no cloud dependencies required.

The agent OS that evolves itself.

Mermaid diagrams (.mmd) from natural language with validation loop. 11+ types, multi-backend (mmdc / Kroki), PNG/SVG/PDF, multi-agent.

💻 Desktop AI assistant built for real productivity. Voice, automation, memory, vision, web search, and workflow tools in one experience.

AI-native, open-source Frame.io alternative for creative collaboration.

Tensorflow chatbot which is capable of interacting with user through Rest Api, Web interface, GUI and CLI.

Build Secure and Compliant AI agents and MCP Servers. YC W23

🤖 Easily create chat bots for Twitch.tv

Open-source VS Code AI agent that combines the best of Roo Code, Cline and kilo code, with advanced AI capabilities, multi-model support, and seamless development workflow integration.

Claude-style sub-agents (reviewer, debugger, security) for Codex CLI via a tiny MCP server. Each call spins up a clean context in a temp workdir, injects a persona via AGENTS.md, and runs codex exec --profile <agent> to preserve isolated state.

An open-source Python SDK and CLI Starter Toolkit for deploying AI agents to Volcengine AgentKit Runtime.

7 production n8n workflows from Jacobo, a multi-agent AI system (WhatsApp + Voice). Open source by default.

Zero-knowledge credentials infrastructure built for AI agents to operate, not just consume.

A sandbox for prototyping and demonstrating Agent Skills for MATLAB and Simulink work.

📝 Glyph is a private desktop workspace for notes, documents, and ideas, with Markdown editing and built-in AI tools.

Agentic Coding with Claude Code, published by Packt

Voice notes for iPhone and macOS - 100% Rust, Dioxus, local-first (SQLite + LanceDB + RIG)

The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.

Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints autonomously

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

Frakio Work - 终极缝合 AI 工作台，致力于在一个对话中丝滑调用多 Agent 协作。Hermes 和 Pi 双重内核，Hermes管生活长期记忆进化，Pi 管编码等复杂任务

本项目是《AI Agents in Action》第二版的中文译本，是一本智能体系统构建与应用的实战指南——目标不止于打造自主实体，更在于开发能够切实应对并解决现实问题的智能体。 全书从大语言模型（LLM）的基础应用出发，逐步深入到智能助手、多智能体系统与自主智能体的构建，系统讲解智能体系统的关键组成部分：角色、工具与行动、知识与记忆、检索与增强、推理与规划、评估与反馈。第二版将五个功能层作为组织原则，并新增 MCP 协议、测试驱动的智能体开发（TDAD）、智能体循环、认知与元认知等前沿主题，帮助开发者构建生产级智能体系统。

Reusable Agent Skills, plus integrations (statusline, provider usage, vision) that install into Codex, Claude Code, and opencode.

AI Engineering Runtime for Professional Developers — terminal coding agent with IOSM methodology, MCP, checkpoints, orchestration, and extensions

Web scan foundation framework

Opperator is a framework for building and running general AI agents locally from your terminal

🔥 Your private task assistant with GPT 🔥 - Ask questions about your documents.

This RAG (Retrieval-Augmented Generation) project is implemented using pure Java. This approach makes it easier to adapt to enterprise-level environments and is more conducive to secondary development.

PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.

A general AI agent framework that can be adapted to various tasks and environments.

A framework for building LLM based agents and integrating them into larger applications.

This is the documentation for Roo Code, an AI-powered autonomous coding agent that lives in your editor.

Toolkit for Coding Agents to work reliably with repo of any size.

Talk with multiple ChatGPT agents

Pragmatic AI Labs MCP Agent Toolkit - An MCP Server designed to make code with agents more deterministic

Multi-agent investment team powered by Agno and Gemini — 7 AI analysts collaborate across 5 architectures to deploy a $10M equity portfolio

Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University

A generative Minecraft structure tool for the Cynia Agents framework.

Official Repository for TimeSeriesScientist

Automated system for LLM evaluation via agents. Doc as below:

M-Courtyard: Local AI Model Fine-tuning Assistant for Apple Silicon. Zero-code, zero-cloud, privacy-first desktop app powered by Tauri + React + mlx-lm.

🐾 Authority, not credentials, for AI agents: policy-approved actions, delegation that can only narrow, instant revocation, tamper-evident audit.