An AI-driven autonomous penetration testing system that uses a multi-agent architecture and dual-graph tracking to automate vulnerability discovery and complex attack chains.

An open-source AI agent platform for Android that integrates LLMs with system automation, a Linux terminal, and web agents to enable complex task execution on mobile.

A local browser UI for the pi coding agent that allows users to manage conversations, configure models, and inspect project files via a web interface.

An open-source, AI-powered workspace and Notion alternative that prioritizes data privacy and native cross-platform performance.

An AI learning system built for the pi framework that uses specialized subagents and interactive extensions to provide a structured, visual, and verified learning experience.

A persistent memory layer for AI agents that stores explicit facts with sources and uses a knowledge graph to provide synthesized answers instead of simple search results.

A standardized, open format for packaging specialized knowledge and workflows into portable folders that AI agents can load on demand to gain domain expertise.

A Chinese-first editing skill that removes AI-style clichés and redundant wording from text while preserving the original meaning and author's voice.

A structured game development studio template for Claude Code, providing 49 specialized agents and 73 skills to bring professional studio organization to solo AI-assisted game dev.

A collection of 24 professional screenwriting and dramaturgy skills for AI agents, providing expert-level guidance on structure, dialogue, and series development based on extensive craft literature.

A cross-platform desktop client that provides a unified interface for multiple LLM providers, including cloud services, web AI, and local models.

A training-free self-orchestration framework that uses a shared filesystem to coordinate multiple model instances, enabling smaller open-weight models to match or exceed frontier coding performance.

An automated novel-writing framework for Claude Code that guides users through interactive planning and multi-agent drafting to produce complete, high-quality Chinese novels.

An all-in-one AI application that allows users to build a private ChatGPT-like interface to chat with documents and deploy AI agents with minimal setup.

A local-first, plain-text workspace that uses MCP integration to allow humans and AI assistants to collaborate directly on the same files.

A set of open-source SEO and GEO skills for Claude that leverage the Ryze MCP to analyze real Google Search Console, GA4, and Google Ads data for search optimization.

An automated hot-topic assistant that aggregates news from multiple platforms and uses AI to filter, analyze, and push personalized trend reports to various messaging apps.

An AI Agent system for long-form story creation and translation that manages world-building, character continuity, and narrative state to prevent plot holes and AI-style prose.

A lightweight, generalist framework for Named Entity Recognition (NER) that enables zero-shot extraction of any entity type without requiring task-specific training data.

A privacy-first AI meeting assistant that captures, transcribes, and summarizes meetings locally on your own infrastructure to ensure data sovereignty.

An AI-powered web scraping library that uses LLMs and graph logic to extract structured data from websites and local documents using natural language prompts.

An AI harness reference implementation for on-demand delivery operations that combines deterministic workflows, mock business tools, and human-review guardrails to analyze abnormal orders and suggest compensation.

A set of agent skills that enable AI agents to research top-grossing mobile apps and build high-fidelity, simulator-verified Expo and React Native screens.

A cross-platform team chat where AI agents are first-class participants, allowing them to collaborate with humans via shared DMs, Kanban boards, and calendars.

A marketplace of portable agentic building blocks that provides agents, skills, and commands compatible with multiple AI coding assistants like Claude Code and Cursor.

A self-hosted AI investment assistant that integrates a multi-agent framework to provide real-time stock monitoring, deep research analysis, and automated alerts for global markets.

A filesystem-first framework for building durable AI agents where prompts, tools, and schedules are managed as files in a project directory.

LobeHub is a comprehensive AI agent management platform that organizes agents into a cohesive team for 24/7 operation, featuring personalized memory and multi-agent collaboration.

A local-first knowledge system for Claude Code and Obsidian that turns source material into linked, source-cited notes while maintaining full user ownership of files.

A self-hosted AI workspace that integrates chat, agents, and deep research with productivity tools like email, calendar, and document editing.

A context-engineering and spec-driven development framework that prevents AI coding agents from degrading due to context bloat by using a disciplined phase loop and fresh-context subagents.

An IntelliJ IDEA plugin that provides a visual interface for AI coding CLIs like Claude Code and OpenAI Codex, streamlining AI-assisted programming.

A verifiable knowledge base and agent skill for analyzing the investment views and methodology of fund manager Zheng Xi, preventing AI hallucinations through strict source-tracing and real-time fund data integration.

An educational proof-of-concept for an AI-powered hedge fund that uses LLM-based investor agents to analyze financial data and make trading decisions.

A framework for distilling an author's writing style into a structured "Writing DNA" that AI agents can use to stably and accurately replicate that style.

An agent skill and design framework for AI coding agents to build premium, scroll-driven websites that avoid generic AI design tropes through strict craft standards and automated verification.

An opinionated, batteries-included agent harness built on LangGraph that provides out-of-the-box planning, context management, and tool integration for long-horizon tasks.

An open-source coding-agent CLI that provides a unified terminal workflow for cloud and local LLM providers, supporting tool-driven coding and codebase intelligence.

A scientific PDF translation tool that preserves the original layout, formulas, and charts while supporting multiple translation services and OCR.

An open-source hybrid scientific research agent that combines JSON orchestration with persistent Python and R kernels for complex scientific computation and analysis.

A series of compact, SOTA language models (1B-2B parameters) optimized for on-device deployment, featuring strong capabilities in coding, math, and agentic tasks.

A model-agnostic Python framework that uses object-oriented programming to unify agent state, prompts, and capabilities into a single Python class.

A local-first tool that distills a person's working habits, voice, and judgment into versioned Person Profiles that can be installed as skills for AI agents.

An autonomous LLM-based research system for public markets that uses specialized agents to find, debate, and audit trading opportunities using a strict evidence-first pipeline.

A CLI tool that uses AI agents to create and maintain a self-updating Markdown wiki for codebases or personal knowledge, featuring grounded claims to track facts back to source evidence.

A privacy-focused, self-hosted AI answering engine that combines private web search via SearxNG with local or cloud LLMs to provide cited answers.

A Claude-first framework for paid-media operations that automates audits, planning, and creative workflows across 12 advertising platforms with strict safety gates.

A TypeScript framework for building and scaling AI agents and applications, featuring model routing, graph-based workflows, and production-ready observability.