A local-first AI workbench for WeChat data that enables natural language search, group chat summarization, and automation of chat history analysis.

A team-architecture factory for Claude Code that automatically generates specialized agent teams and skills based on a domain description.

A local-first personal AI assistant and readable blueprint for agentic systems, featuring a transparent loop, multi-tiered memory, and built-in LLM-Ops.

Ouroboros is a self-evolving AI agent with durable memory and a continuous identity that can rewrite its own code and coordinate specialist agent swarms.

An autonomous AI company framework that orchestrates 14 expert AI agents to ideate, build, and market products 24/7 via a continuous agentic loop.

An AI-native workflow automation platform for building, visualizing, and running multi-agent orchestrations and RAG pipelines via a no-code visual canvas.

MaiBot (MaiSaka) is a Python 3.12+ chatbot built on large‑language‑model technology. It focuses on natural, personality‑driven conversation rather than pure task efficiency, learns user preferences, mimics group chat styles, and offers a plugin/event system for extensibility. The project provides a web UI, a one‑click Windows/macOS launcher, and detailed docs for deployment and plugin development. Licensed under GPL‑3.0.

HanaAgent is a user-friendly AI assistant with memory and personality that can operate your computer, browse the web, and collaborate across multiple agents via a graphical interface.

A browser bridge and extension that connects DeepSeek Harness to Chrome or Firefox, allowing an AI agent to operate the user's active browser tabs while preserving login sessions.

A collection of Agent Skills for solving CTF challenges, providing AI agents with the technical knowledge and tooling required for cybersecurity competitions.

A management system for Xianyu that automates customer replies using AI and keywords, manages multiple accounts, and handles automatic delivery of goods.

A browser extension that adds folder organization, prompt management, and timeline navigation to Gemini, Claude, and ChatGPT.

An all-in-one workspace that unifies email, chat, tasks, docs, and CRM into a single system with shared team-level memory for AI agents.

A code-first Python framework for building, evaluating, and deploying sophisticated AI agents using graph-based workflows and multi-agent orchestration.

A 100% private, offline AI voice assistant that provides conversational awareness and unlimited local memory, integrating with thousands of tools via MCP.

A workspace to build, deploy, and manage AI agents and workflows, featuring a visual builder, 1,000+ integrations, and integrated data management.

An open-source framework for building general AI agents capable of browser automation and data analysis.

A browser automation framework for AI agents that bypasses anti-bot protections and provides token-efficient web interaction via indexed text formats.

A real-time shared workspace that connects multiple AI agents and apps, eliminating the need to manually copy-paste context between different AI tools.

A reverse proxy that converts the National Anti-Fraud AI assistant into a standard OpenAI-compatible API for use in third-party AI clients.

A comprehensive web-access skill for AI agents that provides browser automation via CDP Proxy, allowing agents to to use existing login sessions and interact with dynamic websites.

A Python library that uses LLMs to extract structured, grounded information from unstructured text, featuring optimized processing for long documents and interactive visualization.

ColorTxt (彩读) is a cross‑platform desktop novel reader built with Electron, Vue and Monaco. It reads plain‑text and simple e‑books, adds automatic chapter detection, custom colour‑highlighting, notes, dictionary, translation, multi‑voice TTS, and an AI Reading Assistant. The assistant uses local embedding models (BGE Small ZH, multilingual‑E5 Small) for RAG search and any OpenAI‑compatible chat model for plot analysis, mind‑map/word‑cloud generation, and smart formatting. It can also generate character cards and AI‑drawn portraits via text‑to‑image services. Features include book‑pack export (`.ctz/.ctzx`), WebDAV sync, Pomodoro timer, reading‑ruler, and “fish‑hiding” shortcuts. All AI/ML components can run locally, keeping costs low and preserving privacy.

An AI-powered video note-taking tool that converts videos from Bilibili, YouTube, and other platforms into structured Markdown notes with automatic summaries and screenshots.

An intelligent data questioning system based on LLMs and RAG that enables conversational data analysis (ChatBI) by converting natural language to SQL.

An AI-powered interview platform that provides resume analysis, RAG-based knowledge base management, and real-time voice/text mock interviews with automated evaluation.

A stateful agent harness that enables AI agents to maintain long-term memory, identity, and evolve through self-rewriting context and skills.

An AI-powered research and writing tool that generates publication-ready scientific papers, grant proposals, and reports backed by real-time literature search and verified citations.

A self-hosted, cross-device platform for managing AI agents that allows users to run agents on their own devices and track tasks via a centralized board.

An autonomous AI agent that enables LLMs to fix GitHub issues, find security vulnerabilities, and perform custom coding tasks.

A human-led AI agent team framework that integrates with GitHub Copilot to provide persistent, specialized AI developers that live in your repository.

A local-first desktop workspace for coding agents that integrates multiple AI runtimes, execution tools, and review surfaces into a single project-aware environment.

A collection of high-quality SKILL.md files for AI agents (Cursor, Claude Code, etc.) that enable automatic task triggering for academic writing, diagramming, and development workflows.

A local financial research workstation that uses AI agents to perform structured, evidence-based analysis of A-shares and global markets with full traceability of data and calculations.

A Claude Code skill that automates website optimization for traditional search engines and AI answer engines (AEO, GEO, LLMO) to increase citations and visibility.

A personal memory infrastructure that allows different AI agents to share a structured memory of user preferences and project history, ensuring task continuity across tools.

A local-first Markdown editor with a built-in MCP server and agent panel, allowing AI agents to safely read and write to your personal knowledge base.

An immersive AI companionship assistant that combines LLMs with emotion recognition, desktop vision, and Galgame-style visuals to create a reactive digital character.

A collection of agent skills and plugins for Google Stitch that enables AI coding agents to automate design generation, design system management, and conversion of designs to frontend code.

A framework designed to bypass GPT-5.6 safety filters for security research, combining context reconstruction, a real-time response tampering proxy, and integration with 78 security tools via Kali Linux.

A production-ready Java framework for building agentic, workflow-based, and multi-agent applications with built-in support for state management and context engineering.

An asynchronous inbox for long-running AI agent tasks that allows users to start work, disconnect, and manage completed results and approval requests via a queue system.

A collection of reusable agent skills, plugins, and agent definitions for security operations and offensive security tradecraft, compatible with Codex and Claude Code.

A self-hosted enterprise knowledge management layer and MCP server that compiles organizational documents into a structured wiki for secure, permission-scoped AI access.

A privacy-focused desktop AI companion that can operate your computer, manage files, and use MCP tools, featuring a hormone-based emotion system and a Live2D avatar.

An engineering-driven writing environment for long-form fiction that uses a world-state engine and plot tracking to prevent AI hallucinations and narrative inconsistency.

A ready-to-go translation and OCR tool developed with WPF for easy text translation and image text recognition.

An open-source computer use agent framework that operates real GUIs via mouse and keyboard, achieving human-level performance on the OSWorld benchmark.