FinGPT is an open‑source suite of financial large language models fine‑tuned with LoRA/QLoRA for tasks like sentiment analysis, relation extraction, headline classification, NER, QA, and stock‑price forecasting. It offers multi‑task and single‑task checkpoints, public instruction‑tuning datasets, a benchmark suite, and demo interfaces, all under an Apache‑2.0 license.

Warp is an NVIDIA‑backed Python library that JIT‑compiles regular Python functions into fast CPU/GPU kernels for physics simulation, robotics, and differentiable computing. It works with PyTorch/JAX, provides a simple `@wp.kernel` decorator and `wp.launch` API, and ships as the `warp-lang` PyPI package.

A benchmark for evaluating how AI agents leverage and compose modular skills—instructions, scripts, and resources—to perform specialized workflows.

A multimodal MoE model that serves as an architectural preview for Qwen4, offering high efficiency in coding and office tasks with significantly reduced training and inference costs.

A multi-tier framework for evaluating AI agent skills, providing validation, deduplication, and live sandboxed evaluation to ensure agent extensions are safe and effective.

An enterprise-grade AI data analyst based on Spring AI Alibaba that converts natural language to SQL, performs deep Python analysis, and generates visual reports.

A Codex skill that transforms travel photos into collectible digital memory sticker cards.

The source release of NVIDIA's open GPU kernel modules for Linux, enabling the build and installation of kernel-level driver components for Turing and newer GPUs.

A one-stop repository for mathematical modeling competitions that integrates automated solving via Claude Code, LaTeX paper templates, and a library of common algorithms.

An agentic skills framework that gives AI coding agents domain-specific expertise and best practices for Godot 4.x game development in GDScript and C#.

A plugin marketplace and discovery platform for Claude Code that provides curated agents, commands, and hooks to extend AI development workflows.

An MCP server that connects AI assistants to Garmin Connect, allowing them to read health metrics, analyze activities, and create training workouts.

Atomic Agent is an open‑source, local‑first AI assistant that runs on your machine using quantised models via `llama.cpp`. It executes tool‑call JSON loops to browse, edit files, run shell commands, manage memory, and more, all while keeping state on disk and offering a TUI/CLI and HTTP side‑car for integration.

A DePIN blockchain that rewards the preservation of vintage hardware and provides hardware-attested, Sybil-resistant identities for AI agents using Proof of Antiquity.

An open-source singing voice synthesis editor for the UTAU community that provides a modern, cross-platform interface for creating vocal covers and songs.

A native local development environment for Windows, macOS, and Linux that manages runtimes, databases, and web servers in a single workspace.

An AI prompt management tool providing over 5,000 ready-to-use prompts to help users get expert-grade outputs from AI tools like ChatGPT and Cursor.

An all-in-one AI creation platform for novel writing and interactive role-playing games, featuring integrated AI agents, world-building databases, and version control.

An open-source AI Management System that lets companies manage agents, skills, and memory as a git repository and execute tasks in isolated cloud sandboxes.

A private, on-device voice-to-text and meeting transcription app for macOS that uses local AI models to ensure no data leaves the machine.

An open-source pipeline and retrieval system that converts public SKILL.md files into curated procedural knowledge for AI agents to improve task execution.

A semantic context layer for AWS that combines knowledge graphs and formal ontologies to provide AI agents with validated, business-aware context.

A multimodal data-processing framework that provides 200+ modular operators to clean, deduplicate, and curate large-scale datasets for foundation models.

An AI-native video production workspace for Claude Code that automates scriptwriting, asset generation, and rendering for low-cost, professional explainer videos.

A self-hosted all-in-one platform that replaces multiple SaaS tools by consolidating deployment, observability, and AI infrastructure into a single binary.

A collection of standardized task definitions and instructions that enable AI coding agents to perform complex AI/ML workflows on the Hugging Face Hub.

A web-based presentation application that replicates Microsoft PowerPoint features, providing a developer-focused foundation for building custom slide editors.

Aiden is an open‑source autonomous AI engine (Node/TypeScript) that turns a natural‑language goal into a verifiable, multi‑step workflow across files, terminal, browser, APIs, and Git. It records every action in SQLite, supports risk‑tiered approvals, multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama, etc.), and can run as a CLI, web workbench, or background daemon. Install via `npm i -g aiden-runtime` and start with `aiden`.

A pragmatic Vision-Language-Action (VLA) foundation model pre-trained on 20,000 hours of real-world robot data to enable high-performance robotic control across multiple platforms.

projectmem is a Python‑based, local‑first memory layer for AI coding assistants. It records structured events (issues, attempts, fixes, decisions) in a `.projectmem` folder, provides pre‑commit warnings to avoid repeating failures, and exposes the data via a native MCP server that Claude, Cursor, Codex and similar tools can query. With a single command (`pjm init`) it installs git hooks, starts a cross‑platform file watcher, and creates dashboards for visualizing the project’s debugging history and ROI. The tool aims to reduce token usage, prevent repeated bugs, and keep AI agents “experienced” across sessions.

A multi-agent harness that replaces AI narration with mechanical verification, ensuring agents actually complete work by checking artifacts and test results across multiple AI runtimes.

An AI-powered tool for scanning and diagnosing Kubernetes cluster issues, providing plain-English explanations and fix recommendations.

Type4Me is a macOS‑only voice input app that combines local and cloud speech‑recognition with LLM‑powered text processing. It offers eight built‑in modes (raw dictation, intelligent polishing, translation, AI Q&A, macOS control, prompt generation, task execution, etc.), customizable hotkeys, vocabulary management, history logging, and an URL‑scheme for automation.

A library of AI agent skills for App Store Optimization (ASO) and mobile app marketing that uses real-time App Store data to provide actionable growth recommendations.

A tool for extracting clean text from web pages, videos, and audio files to generate AI-powered summaries via a CLI, browser extension, or library.

SuperClaude Framework is an open‑source meta‑programming platform that extends Claude Code with 30 slash commands, 20 AI agents, 7 behavioral modes, and optional MCP servers for faster, token‑efficient execution. It automates the full software development lifecycle—from brainstorming and design to coding, testing, documentation, and project management—via simple commands like `/brainstorm`, `/implement`, and `/research`. Installable via pipx (or from source) and licensed under MIT.

A React component library built on shadcn/ui that provides pre-built, customizable UI elements for building AI-native applications faster.

HunyuanVideo is a large-scale open-source video foundation model with over 13 billion parameters that generates high-quality videos with superior motion and text alignment.

An infrastructure for agentic analog and mixed-signal design that allows LLM agents to drive Cadence Virtuoso for automated schematic, layout, and simulation flows.

Aurora is a Go‑based self‑hosted server that turns the private ChatGPT web backend into an OpenAI‑compatible REST API, supporting chat, tool‑calling, image, audio, file upload, and token‑pool management.

A modern cross-platform desktop toolset integrating image processing, audio/video editing, and local AI tools with GPU acceleration.

A high-performance Go-based application development platform that provides a unified framework for building AI applications with integrated LLM, RAG, and Agent capabilities.

Caura is an open-source governed memory layer for AI agent fleets that enables shared, self-improving knowledge storage and retrieval across multiple agents.

PM Skills is an open‑source library of 1 169 markdown “Agent Skills” that give Claude, ChatGPT, Gemini, etc. concrete, senior‑level procedures for professional and life‑admin tasks (e.g., lease decoding, PRD writing, salary‑negotiation simulation). Skills are plain markdown files containing framework, template, checks, and anti‑patterns. They can be installed with a one‑line `npx` command, used natively in Claude Code, or pasted into prompts for other agents. The repo also provides npm/PyPI packages, Docker image, and integrations (Telegram, Slack, Raycast, Obsidian, n8n). A web playground lets anyone run a skill in the browser without installing anything.

A creative workstation plugin for DeepSeek Harness that provides specialized AI-driven pipelines for writing novels, producing short dramas, creating interactive games, and generating video recaps.

A series of open-weight large language models (Qwen3.5, 3.6, and 3.8) that provide high-performance capabilities in coding, professional research, and autonomous agentic tasks.

A comprehensive offline AI suite for mobile and Mac that provides text, image, and vision AI, and voice transcription, all running natively on-device for total privacy.

A production-ready multi-agent orchestration framework that provides pre-built architectures for coordinating multiple AI agents to solve complex tasks.