CyberStrike is an open‑source AI agent that turns any LLM (Claude, GPT, Gemini, etc.) into an autonomous penetration‑testing platform. It adds a security‑focused “intelligence layer”, ships 13+ specialised agents and 7,600+ signed security‑skill files, supports 150+ AI providers (including offline models), and can orchestrate real tools locally or on remote Bolt servers. A TUI, optional web UI, and built‑in HackBrowser complete the workflow.

An open, event-based protocol that standardizes how AI agents connect to user-facing applications, enabling real-time interaction and generative UI.

A lightweight Rust/Tauri desktop client for Douyin that offers advanced content downloading, AI-powered interaction, and automation tools.

A project context and engineering control plane that provides AI coding agents with durable project knowledge, governance, and risk-driven quality gates.

An MCP bridge that connects AI assistants to the TradingView Desktop app via Chrome DevTools Protocol for AI-assisted chart analysis and Pine Script development.

An MCP server that allows AI assistants to automate PCB design in KiCAD using natural language commands.

AI‑YouTube‑Shorts‑Generator is an open‑source Python tool that turns long YouTube videos (or local files) into vertical short clips ready for TikTok/Reels/YouTube Shorts. It downloads the video, transcribes it with Whisper, uses an LLM (OpenAI, Gemini, or MuAPI’s model) to rank “viral‑worthy” moments, deduplicates overlapping candidates, and auto‑crops each highlight to 9:16 (or any aspect ratio). Two modes are offered: a zero‑setup API mode that delegates download, transcription, ranking and cropping to MuAPI, and a fully local mode that runs `yt‑dlp`, `faster‑whisper`, OpenCV/ffmpeg and calls an external LLM. The CLI returns MP4 files plus a score, hook sentence and reasoning for each clip, and can also output a detailed JSON file. MIT‑licensed, suitable for creators, agencies, or developers building their own clipping SaaS.

An open-source integration layer that centralizes tool configurations, authentication, and policies for AI agents via the Model Context Protocol (MCP).

An open-source static analysis CLI that detects dead code, security flaws, and AI-generated code hallucinations across multiple languages to ensure code quality before merge.

A skill management layer for AI agents that enables them to retrieve, evaluate, and evolve their capabilities based on real-world task outcomes.

A low-latency, modular voice-agent pipeline that coordinates VAD, STT, LLM, and TTS components to enable real-time voice conversations.

An AI-powered OSINT tool that uses LLMs to refine, filter, and summarize search results from dark web search engines via the Tor network.

A collection of AI skills for researchers to convert academic papers and static images into fully editable PowerPoint presentations and Office shapes using VBA.

A privacy-focused local AI desktop application that runs LLMs via Ollama, featuring a local knowledge graph and sandboxed agents for completely offline operation.

FaceFusion is a high-performance face manipulation platform for swapping and editing faces in images and videos.

An open-source AI orchestration app that lets developers run multiple agents from different providers in parallel with shared memory and unified context.

An open-source alternative to Zapier that enables AI-powered workflow automation through a no-code builder and a TypeScript-based integration framework.

An open-source desktop SQL workspace for multiple databases featuring SQL notebooks, a built-in MCP server for AI agents, and local AI text-to-SQL capabilities.

An open-source LLM evaluation framework that provides unit-testing capabilities for AI agents, RAG pipelines, and chatbots using LLM-as-a-judge metrics.

A tool for batch downloading WeChat Official Account articles, comments, and media into various formats like Markdown and PDF, featuring MCP support for AI integration.

A tool that clusters multiple local devices into a single AI cluster to run frontier models that exceed the memory capacity of a single machine.

AutoGen is a framework for creating multi-agent AI applications that can act autonomously or collaborate with humans using a layered, extensible architecture.

A curated library of procedural agent skills and prompt playbooks designed to help AI coding agents build high-quality UIs, games, and frontend systems consistently.

A system utility that tracks and displays AI plan usage and reset timers for multiple LLM providers across status bars, a TUI, and CLI.

A cross-platform desktop management tool for OpenAI Codex that provides a visual interface for managing prompts, API providers, sessions, and MCP/Skills extensions.

An open-source, enterprise-ready embedded BI platform that combines interactive dashboards, paginated reports, and AI-driven natural language analytics.

An open-source, event-driven orchestration platform for data, AI, and infrastructure workflows that unifies scheduled and real-time automation using a declarative YAML interface.

A comprehensive learning library for Embodied AI that provides a structured path from basic robotics simulation to the reproduction of state-of-the-art VLA and world models.

A third-party API integration library for XianYu that enables the creation of AI customer service agents by providing stable message communication capabilities.

A local model gateway and control plane that centralizes the management of multiple AI coding agents and LLM providers through a single endpoint.

A KV cache management layer for LLM inference that reduces TTFT and improves throughput by making KV caches persistent and reusable across requests and engines.

A framework and toolset for AI agents to eliminate "AI-style" Chinese writing by enforcing human-like rhythms, factual substance, and structural checks.

A desktop AIOps agent for Windows and macOS that automates IT operations tasks like alert analysis and system inspection through natural language and toolchain integration.

An open-source, agentic research workspace for brain science that coordinates specialist AI agents to automate literature review, experiment design, and data analysis.

A terminal-based AI coding assistant that integrates LLMs with local tools, LSPs, and MCP servers to provide an agentic coding experience in the CLI.

Browser Harness is a Python library that lets LLM agents control a real Chrome/Edge browser via a single CDP WebSocket. The agent can write helper functions during a session, making the system improve over time. It includes an optional MCP server for any MCP‑compatible client and can scale to multiple cloud browsers via Browser Use Cloud.

A privacy-first personal knowledge management system featuring block-level references, Markdown WYSIWYG editing, and AI-powered writing and chat.

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.

A plugin for DeepSeek Harness that connects AI bots to nine different instant messaging platforms, enabling unified management of models, workspaces, and sessions across multiple IM channels.

Honcho is a memory infrastructure for stateful AI agents that uses background reasoning to build evolving representations of people and projects over time.

A technical wiki and runbook collection for deploying and optimizing frontier LLMs on NVIDIA RTX PRO 6000 Blackwell PCIe systems, featuring reproducible Docker builds and hardware tuning.

An open-source deep research agent that automates web and local document analysis to produce detailed, factual research reports with citations.

A family of open-source text-to-speech models providing low-latency voice cloning and multilingual speech generation across various model sizes for GPU and CPU deployment.

A full application framework for the Model Context Protocol (MCP) that simplifies building servers, clients, and interactive apps to connect LLMs to tools and data.

An AI agent skill that converts natural language descriptions into professional, geometry-verified technical diagrams, SVG/PNG exports, and semantic animations.

Repomix converts a repository into a single formatted file (XML/Markdown/JSON) to feed codebases into LLMs, with token counting, compression, secret filtering, and git-aware filtering.

A fast automatic speech recognition system that enhances OpenAI's Whisper with batched inference, word-level timestamps, and speaker diarization.

A cloud-native observability platform for logs, metrics, and traces that uses Parquet columnar storage and S3 to reduce storage costs by up to 140x.