Other

OpenClaw is an open-source (MIT) self-hosted AI assistant platform: a local Gateway runs on your own computer and reaches you through Discord, Slack, Telegram, WhatsApp and 20+ chat channels plus native apps, with models and tools as swappable plugins and all state, memory and credentials kept on your hardware

A feature-rich command-line audio/video downloader supporting thousands of sites, actively maintained as a fork of youtube-dl.

Running open models locally no longer needs the cloud — ollama compresses downloading, running, and serving into a few commands, offering a CLI, a REST API, and official Python / JS libraries across macOS, Windows, Linux, and Docker.

A Gradio-based web interface for Stable Diffusion, offering txt2img, img2img, and many advanced features.

LangChain is an open-source framework for building LLM applications and AI agents, offering unified interfaces for models, vector stores, and tools, integrating with LangGraph and LangSmith, available for Python and JS/TS.

Graphify is a local tool that turns any codebase — with its docs, SQL schemas, configs, and PDFs — into a queryable knowledge graph, integrating as a /graphify skill for Claude Code, Cursor, and other AI coding assistants with deterministic AST parsing instead of vector search.

A set of Windows system utilities from Microsoft, featuring over 30 tools to enhance productivity and customization.

A lightweight coding agent from OpenAI that runs in your terminal, with support for ChatGPT accounts or API keys.

A C/C++ implementation for LLM and VLM inference with minimal setup and state-of-the-art performance, supporting multiple model formats with CLI, server, and built-in Web UI.

An open-source remote desktop application designed for self-hosting, serving as an alternative to TeamViewer.

An AI orchestrator that runs multiple coding agents like Codex and ClaudeCode in parallel, available on desktop, mobile, and VPS.

An open-source framework for building cross-platform desktop applications using JavaScript, HTML, and CSS, built on Node.js and Chromium.

A cross-platform 2D and 3D game engine offering a unified development interface and one-click export to multiple platforms.

A design guidance tool for AI coding agents with 1 skill, 23 commands, 59 deterministic detector rules, and live browser iteration to improve AI-generated frontend design.

Microsoft's next-generation terminal application, incorporating both Windows Terminal and the classic console host (conhost.exe).

PyTorch is a Python deep learning framework providing GPU-accelerated tensor computation and tape-based autograd for training neural networks in research and production.

Stirling-PDF is the #1 PDF project on GitHub (96 K stars). A TypeScript + Java web toolkit, Docker one-command launch, 50+ PDF operations including merge/split/convert/OCR/encrypt.

vLLM is a high-throughput, memory-efficient LLM inference and serving engine (Python). Built on PagedAttention and continuous batching, it serves 200+ model architectures behind an OpenAI-compatible API across many hardware backends.

An Agent Skill for AI coding agents that turns a codebase or system description into a polished, interactive system map, supporting architecture, workflow, sequence, data-flow, and lifecycle diagrams.

A leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs.

A fancy, easy-to-use self-hosted monitoring tool supporting HTTP(s)/TCP/Ping/DNS and over 90 notification services.

An open-source software reverse engineering (SRE) framework developed by the National Security Agency (NSA), providing a full suite of analysis tools including disassembly, decompilation, graphing, and scripting.

An extremely fast Python package and project manager written in Rust, designed to replace pip, pip-tools, poetry, and more.

An open-source computer vision library providing extensive image and video processing algorithms, with multi-language and multi-platform support.