A fast Rust library for PDF inspection, classification, and text extraction that distinguishes scanned from text-based documents for smart routing, with layout and table extraction plus multi-language bindings.
Official repository for Qiu Xipeng's Neural Networks and Deep Learning textbook, offering second-edition and general-audience e-books, chapter outlines, and guided learning paths for students.
Open-source general-purpose assistant that gives agents a complete Linux computer, controlling desktop browsers and documents while orchestrating sub-agents to complete diverse tasks.
Cocos2d-x is a suite of open-source, cross-platform, game-development tools utilized by millions of developers across the globe. Its core has evolved to serve as the foundation for Cocos Creator 1.x & 2.x.
High-performance browser-side LLM inference engine built on WebGPU and compatible with OpenAI APIs, distributed as npm packages for developers building web-based AI applications.
JavaScript library bringing machine learning to browsers and Node.js, enabling model training, deployment, and hardware acceleration including WebGL for interactive web developers.
Decentralized graph database and synchronization protocol enabling real-time P2P data sync with end-to-end encryption for developers building offline-first, privacy-preserving applications.
Reference checklist documenting native JavaScript replacements for Lodash and Underscore methods, plus an ESLint plugin to detect redundant imports and help developers reduce dependencies.
Life operating system running on agents like Claude Code, providing memory, skills, context, and intent-engineering enhanced shell for personal productivity management.
Efficient portrait animation application that drives static portraits into expressive videos for humans, cats, and dogs, providing a Gradio interface and one-click installation packages.
Companion teaching materials and code examples for a zero-to-mastery PyTorch deep learning course, covering fundamentals, classification, computer vision, and transfer learning topics.
Self-hosted online file converter supporting mutual conversion among thousands of image, audio, video, document, and ebook formats, deployable via Docker.
Open e-book for LLM training engineers systematically covering hardware selection, orchestration, debugging practices, scripts, and hands-on guidance for large-model training, fine-tuning, and inference.
Provides open Chinese LLaMA and Alpaca model weights alongside pretraining and instruction-tuning scripts plus local quantized deployment solutions supporting Chinese LLM research and experimentation.
🩵 A free, open-source app store for developers' releases on GitHub, Codeberg & Forgejo - browse, discover, and install apps with one click. Formerly GitHub Store.
Free open-source app store aggregating releases from GitHub, Codeberg, and Forgejo, letting developers browse, discover, install, and manage updates for developer-distributed applications in one place.
Open-source free stock market platform for tracking real-time prices, setting personalized alerts, and exploring detailed company insights, intended as an open alternative to paid market services.
Deep-learning file-type detection tool delivering millisecond identification of over 200 formats, providing CLI and multi-language APIs for security routing and content handling.
Open-source electronic signature platform enabling users to create PDF forms and collect online signatures, supporting multiple signers, email notifications, and API integration.
Meta's official Llama building guide offering example recipes and tutorials covering inference, fine-tuning, RAG, and end-to-end application scenarios for developers.
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
Lightweight web interface for the Hermes agent, offering three-column chat and workspace browsing that matches the command-line experience for remote users.
A locally deployable AI platform for quantitative research and trading, covering data ingestion, factor mining, backtesting, and live trading across stocks, funds, futures, and crypto assets.
Run Windows Subsystem For Android on your Windows 10 and Windows 11 PC using prebuilt binaries with Google Play Store (MindTheGapps) and/or Magisk or KernelSU (root solutions) built in.
Free open-source cross-platform streaming music player for discovering music, managing playlists and favorites, with plugin, theme, and MCP control support.
Lightweight RL training framework for AI agents using real execution environments, supporting Kubernetes scaling and optimization for coding and other tasks.
Open-source LLM evaluation framework similar to Pytest for unit-testing LLM applications, providing diverse metrics to assess models, prompts, and agent trajectory quality.
Lightweight, high-performance Micro-ORM for .NET that extends ADO.NET connections to execute SQL directly and map results to strongly typed objects for data access.
Desktop tool centrally managing accounts, quotas, multi-instance sessions, and wake-up automation across AI coding IDEs including Codex, Copilot, Cursor, and Gemini CLI.
Open-source framework for developers building enterprise customer-service conversational agents, using rule constraints and context engineering to deliver controllable, consistent, traceable LLM interactions.
An open-source, self-hostable AI platform for building assistants and agents, with document parsing, deep research, multi-model support, and enterprise search for private deployments.
Google's open-source international phone number library supporting multi-language parsing, formatting, validation, and carrier lookup, widely integrated into application development workflows.
End-to-end solution for creating personal digital avatars by fine-tuning large models on chat history, covering data export, training, and multi-platform chat deployment.
A JavaScript framework for building LLM applications, providing standardized interfaces for models, embeddings, and vector stores plus chaining and orchestration for complex workflows.
Rust-based open-source agent operating system shipped as a single binary with seven built-in scheduled autonomous agents for research, outreach, and sentiment tasks.
Desktop-resident open-source AI colleague that works across files to autonomously deliver code reviews, documentation drafts, and event analysis for developers and small teams.
A security scanner for AI agent skills that detects vulnerabilities, prompt injection, data exfiltration, and supply-chain risks, producing scored reports before installation for developers.
Cross-device orchestration platform for running and coordinating multiple coding agents in parallel on local machines, with mobile and desktop control plus voice-assisted collaboration.
Multi-agent workspace manager coordinating multiple coding agents through division of labor, using hooks and letter-based messaging for persistent task tracking.
A high-performance 2D UI layout library written in C, distributed as a single header with zero dependencies and offering a Flexbox-like model for developers embedding interface layout.
Google’s open-source C++ utility library collection supplementing the standard library with containers, strings, concurrency primitives, and other common components for developers.
Vulkan-based translation layer for Direct3D 8/9/10/11 enabling Windows 3D games and applications to run on Linux through Wine with improved performance and compatibility.
A free, open-source operating system compatible with Windows NT applications and drivers, currently in alpha quality and intended for testing inside virtual machines.
Zero-dependency front-end library providing beautiful, responsive, highly customizable, and accessible popup replacements for web pages with modern dialog components for developers.
Runtime harness connecting LLMs to real browsers, enabling external agents to operate the web autonomously while evolving and accumulating reusable assistants and behaviors.
AI-driven interactive wiki generator that analyzes code repositories from GitHub and similar sources, producing documentation and visualizations for easier codebase understanding.
Open-source developer platform converting multilingual scripts into webhooks, workflows, and internal UIs, supporting scheduled triggers and low-code application building for teams.
Introductory book on LLM fundamentals from Zhejiang University, systematically covering neural networks, Transformers, pretraining, prompting, and frontier topics through chapter PDFs.
Desktop AI teammate for knowledge workers that indexes email and meetings into a memory knowledge graph, working autonomously across mail, notes, browser, and code.
Production-ready multi-platform IM bot development platform allowing no-code bot construction via web panel, orchestrating models, knowledge bases, plugins, and multi-channel distribution.
The official PyTorch computer vision library, offering common datasets, image preprocessing transforms, and pretrained architectures for classification, detection, and related vision tasks.
A lightweight full-text search engine written in Go, compatible with Elasticsearch ingestion and query APIs, running as a single binary with low resource use, aggregation queries, and web UI.
Highly customizable desktop environment replacement for Windows 10/11, offering redesigned taskbar, window management, launcher, widgets, and theming engine for personal workflows.
A tutorial collection summarizing frequently tested machine learning, deep learning, and NLP concepts with code implementations, aimed at algorithm engineers preparing interviews and strengthening fundamentals.
A tiny JavaScript utility for conditionally joining CSS class names, widely used as a development dependency in React and other frontend projects handling dynamic styling logic.
A family of autoregressive unified multimodal models that decouple visual encoding to support both multimodal understanding and text-to-image generation within one architecture.
Early multi-agent development framework helping developers build agent applications through role-playing, multi-agent collaboration, and simulation capabilities for research and practical use cases.
Fast, low-cost, scalable time-series database and monitoring solution compatible with Prometheus, suitable for long-term storage and use as Grafana data source.
Official Google Cloud example repository for generative AI, providing notebooks, code samples, and demo apps that illustrate Gemini and Agent Platform usage for cloud developers.