agent Tools

Cindy is an open-source AI agent that integrates multiple AI models and harnesses into a single, ready-to-use system. It solves the problem of fragmented AI tools by providing a unified agent that can switch between models and harnesses mid-task without losing context, enabling real work completion in projects and apps. It's designed for developers and teams who need a powerful, configurable, and continuous AI assistant that is both immediately usable and adaptable over time.

Headroom is a context optimization layer that compresses tool outputs, logs, files, and RAG chunks before they reach an LLM. It solves the problem of high token costs and slow response times caused by verbose agent outputs and retrieved data. It's for developers and teams building AI agents, coding assistants, and RAG applications who want to reduce costs and latency without changing model behavior.

Mobile MCP is a Model Context Protocol server that enables AI agents and developers to automate and interact with real iOS and Android devices, emulators, and simulators. It solves the problem of giving LLMs and automation tools direct, platform-agnostic access to mobile environments for development, testing, and scraping. It's for developers, QA engineers, and AI agents who need to build, test, and operate mobile apps without managing physical device labs.

PanWatch 是一个自托管的 AI 盯盘助手，集成了 TradingAgents 多智能体投资决策框架。它解决了投资者需要手动、持续监控多个市场（A股/港股/美股）的痛点，通过实时监控、持仓管理、智能分析和全渠道推送，自动化执行盯盘与决策任务。它适合希望将投资监控流程自动化、智能化，并注重数据隐私与自主控制的个人投资者及交易团队。

Cua provides the infrastructure to scale computer-use agent training, evaluation, and data generation. It solves the problem of running parallel GUI automation workloads across Linux, Windows, macOS, and Android by offering cross-OS fleets, background drivers, and batch throughput from warm pools. It's for AI researchers and engineers building agents that require scalable, reproducible interaction with real desktop and mobile environments.

Octop is a self-hosted AI assistant platform that enables teams to deploy and manage multiple AI agents securely on their own infrastructure. It solves the problem of data privacy and fragmented AI tools by providing a centralized, private hub for collaboration. It's ideal for developers, researchers, and organizations that need customizable, secure AI assistance without relying on external cloud services.

BrowserSkill is a CLI tool and browser extension that enables AI agents to automate tasks in your real, logged-in browser without interrupting your work. It solves the problem of AI agents being isolated from real user sessions and complex authentication states, requiring manual copying of cookies or complex setups. It's designed for developers and power users who work with shell-capable AI agents like Claude, Cursor, or Windsurf and need to automate web interactions seamlessly.

WeKnora is an open-source platform that turns your raw documents and data into a powerful, queryable knowledge base. It solves the problem of scattered, static information by creating a dynamic system that can answer questions via RAG, reason autonomously, and maintain itself like a wiki. It's built for developers, teams, and organizations who need to unlock the value trapped in their documents and build intelligent knowledge applications.

ASC is a high-performance front-end tool designed to decompile Android applications at exceptional speed. It addresses the need for rapid analysis and reverse engineering of APK files, which is crucial for security assessments and vulnerability research. This tool is specifically built for mobile security researchers, penetration testers, and agents who require fast, reliable decompilation to analyze app behavior and security posture efficiently.

Oh My Hermes is a comprehensive plugin suite that adds intelligent routing, long-term memory, and optimized workflows to the Hermes Agent coding assistant. It solves the problem of managing multiple AI models and executors by providing a unified, configurable layer that orchestrates tasks to the right tool based on your setup and preferences. It's for developers and teams who use Hermes Agent professionally and want to maximize its efficiency with model pooling, skill packages, and executor-neutral contracts.

Agent Skills is a secure, validated registry of specialized workflows and tool integrations for professional AI coding agents like Antigravity, Claude Code, and Cursor. It solves the problem of unreliable, unvetted, or insecure agent extensions by providing a curated collection of skills that developers can trust. This platform is for developers and engineering teams who use AI coding assistants and want to safely extend their capabilities with domain expertise, proven patterns, and secure integrations.

MathModelAgent是一款专为数学建模竞赛和课程训练设计的AI工具。它通过多智能体协作，自动完成从题目分析、模型建立、代码求解到论文撰写的完整工作流，生成可直接提交的完整论文。它面向参加数学建模竞赛的学生、进行课程训练的师生以及需要快速生成建模论文初稿的研究者，旨在将重复劳动自动化，让用户更专注于策略与创新。

Garden-Skills is an open-source repository that aggregates essential skills and tools for contemporary software development. It addresses the challenge of fragmented knowledge by providing a centralized, curated collection covering areas like web design, AI-powered code generation, and knowledge retrieval. This resource is designed for developers, engineers, and tech enthusiasts looking to efficiently learn and implement cutting-edge techniques in their projects.

AI-Infra-Guard is a comprehensive red teaming platform designed to secure modern AI ecosystems. It identifies vulnerabilities across AI agents, skills, MCP servers, underlying infrastructure, and LLM jailbreak risks. This platform is essential for security teams, AI developers, and enterprises deploying AI to ensure their systems are robust and resilient against emerging threats.

This is an open-source book titled 'Deep Understanding of AI Agent: Design Principles and Engineering Practice' by Li Bojie. It provides a systematic guide to the core concepts, design principles, and practical engineering techniques for creating effective AI agents. The repository contains the full book text, compiled PDFs, and chapter-by-chapter example code. It is designed for developers, engineers, and researchers who want to move beyond simple AI models and learn how to architect and implement sophisticated, autonomous agent systems.

holaOS is an open-source, all-in-one workspace for AI agents. It solves the problem of fragmented AI tools by letting you run any agent (like Claude Code or Codex) across your entire digital environment—100+ integrations, apps, browser, and files—with shared memory for seamless context. It's built for developers and teams who want to centralize their AI workflows, offering built-in models or the flexibility to bring your own keys.

Unsloth is an open-source desktop application that allows you to run and train large language models (LLMs) and diffusion models locally on your own hardware. It solves the problem of needing expensive cloud compute or specialized infrastructure to work with advanced AI models like Qwen3.8, Gemma 4, and FLUX. It's designed for developers, researchers, and AI enthusiasts who want full control, privacy, and cost-effectiveness in their AI projects.

Embabel is an Agentic AI framework designed for the JVM, enabling developers to move beyond AI experiments to build reliable, scalable, and production-ready AI agents. It solves the problem of Python's limitations in production environments by leveraging the type safety, performance, and mature ecosystem of Java and Kotlin. It's for JVM developers and teams who need to integrate robust, observable AI capabilities into their enterprise systems.

Macro is an open-source office suite that unifies email, chat, docs, tasks, CRM, and AI into a single workspace. It solves the problem of fragmented communication and data across dozens of apps by providing a shared, team-level memory built from all your work. It's built for modern teams who want to replace 7+ separate tools with one fast, secure, and intelligent system.

OpenMontage is the world's first open-source, agentic video production system. It solves the problem of complex, expensive video creation by automating the entire pipeline—from brief to final render—using AI agents. It's for developers, creators, and teams who want to produce professional videos programmatically, turning their coding environment into a full video production studio.

TradingAgents: Multi-Agents LLM Financial Trading Framework