An offline voice recognition input method for Android based on the Whisper engine, providing privacy-focused speech-to-text and translation.

A low-code AI development tool based on PaddlePaddle that provides pre-trained model pipelines for rapid training, inference, and deployment across diverse hardware.

An extension of the Hugging Face ecosystem that provides optimization tools to train and run AI models with maximum efficiency on targeted hardware accelerators.

MagenticLite is an agentic application from Microsoft AI Frontiers that automates browser and local file system tasks using efficient, small-scale AI models.

A lightweight, on-device voice dictation tool for macOS that uses Apple's native speech APIs to paste transcribed text into any active application privately.

LLaDA is a large-scale masked diffusion language model that challenges the dominance of autoregressive architectures, achieving performance comparable to LLaMA3 8B.

A high-accuracy Game Boy emulator written in C++ featuring an embedded MCP server for AI-assisted debugging and ROM hacking.

A portable AI workspace that bundles the OpenClaw framework onto a USB drive, allowing users to carry their AI configurations and memories across any computer.

Model Explorer is a Google‑AI‑Edge open‑source visualizer that renders TensorFlow, TFLite, TF‑JS, MLIR, and PyTorch ExportedProgram models as interactive hierarchical graphs. It offers GPU‑accelerated rendering, searchable nodes, I/O highlighting, metadata overlays, and an extensible adapter system for additional formats.

A Kubernetes alert enrichment engine that integrates with Prometheus to provide diagnostic data and automated remediation for alerts.

An open-source compiler that translates CUDA, HIP, and Triton kernels into binaries for AMD, NVIDIA, and Tenstorrent GPUs, as well as x86-64 CPUs.

A real-time spatial perception system that incrementally builds and optimizes 3D Scene Graphs for robotic environment understanding.

A privacy-first, cross-platform prompt management tool that allows users to organize, optimize, and use dynamic AI prompts with local storage.

A deployable research backend that provides cited answers and in-depth reports through orchestrated shallow and deep research agents.

A modular framework for building low-latency conversational AI avatars with integrated VAD, STT, LLM, and TTS pipelines across multiple channels.

The OpenAI CLI is an official command‑line client for the OpenAI REST API. Install via Homebrew or `go install`, set your API key, and run commands like `openai responses create` or admin queries. It supports custom headers, mutual‑TLS, flexible output formats, file uploads, and can be linked to any version of the OpenAI Go SDK. Licensed under Apache 2.0.

A local-first knowledge base that provides a shared memory and durable context for humans and multiple AI agents via MCP and Skills.

Taskhomie is a local AI agent that controls your computer via screenshots, mouse, and keyboard movements, or runs asynchronously in the background for web and terminal tasks.

Lance is a 3B parameter unified multimodal model that integrates image and video understanding, generation, and editing into a single framework.

A LiDAR Odometry pipeline that provides accurate and robust registration without requiring manual parameter tuning.

A Next.js‑based web app that logs in via GitHub OAuth, pulls a user’s public contribution data, and runs an AI model to produce a scored profile report (PDF export). Built with TypeScript, Bun, Neon PostgreSQL, Upstash Redis, and Tailwind CSS.

Sakura Desktop Pet is an open‑source AI‑driven desktop companion that watches the screen, remembers interactions, and can start conversations on its own. Users load a character pack (portrait, role‑card, optional voice) and configure LLM APIs; the agent then uses screenshots, tool calls (web search, reminders, notes) and a long‑term memory to act like a proactive virtual pet.

A local-first framework for architecture firms to build and govern AI-assisted workflows, providing persistent project memory and specialized AEC tools for Codex and Claude Code.

An open-source observability and self-improving layer for AI agents that detects production failures, root-causes them to source code, and opens verified fix PRs.

An MCP server that connects AI assistants to the Godot editor, providing 175 tools to automate scene management, scripting, and game testing.

An open source extension for JupyterLab that connects AI agents to computational notebooks, allowing them to read/write files and run terminal commands.

An MCP server that enables AI agents to read and manage projects, work items, and cycles within Plane project management software.

A highly extensible AI bot framework that enables LLMs to execute code in secure sandboxes and interact across multiple chat platforms via a unified adapter architecture.

A curated collection of pre-compiled Python wheels for AI/ML libraries that are difficult to install on Windows, eliminating the need to build from source.

An MCP server that enables AI assistants to search Airbnb listings with advanced filtering and retrieve detailed property information.

A collection of open-source, on-device text-to-speech models that enable natural-sounding speech and instant voice cloning locally on mobile and embedded devices.

GTCRN is an ultra-lightweight speech enhancement model designed for low-resource environments, providing high-quality noise reduction with minimal parameters and computational overhead.

An AI-powered toolkit for travel hacking that enables agents to search award flights, compare points vs cash, and manage loyalty balances across dozens of programs.

An agentic framework that generates high-quality educational videos by synthesizing executable Manim code rather than pixels, ensuring mathematical precision and coherence.

A framework for evaluating AI agent skills by running automated tasks in sandboxed environments and grading them with deterministic scripts or LLM rubrics.

A powerful search engine plugin for Obsidian that uses the BM25 algorithm to provide instant, relevance-ranked search across notes, PDFs, and images.

LLM Vision is a Home Assistant integration that uses multimodal large‑language models (OpenAI, Anthropic, Gemini, Ollama, etc.) to analyze images, video clips, live camera feeds and Frigate events. It returns natural‑language descriptions, remembers identified people/pets/objects, and stores each analysis in a timeline that can be shown on the dashboard or queried via Assist. Install via HACS, configure an LLM provider, and optionally add the supplied Blueprint for AI‑summarized camera notifications.

A framework that uses Claude Code to interview business owners and automatically build, test, and deploy AI-powered WhatsApp customer service agents.

An open-source OMR checking software that uses computer vision to accurately read and evaluate scanned OMR sheets or mobile photos, exporting results to CSV.

Shippie is an extendable code-review agent that analyzes diffs and explores codebases to identify bugs, secrets, and inefficiencies during the pull request process.

A set of AI skills and templates that guide AI agents to generate high-quality, professional personal homepages, portfolios, and HTML presentations instead of generic templates.

An efficient, prompt-free framework for few-shot fine-tuning of Sentence Transformers, enabling high-accuracy text classification with very little labeled data.

A native macOS app that provides an autonomous AI agent capable of controlling the desktop, managing codebases, and automating system tasks across 18 LLM providers.

An MCP server that enables AI models to interact with Slack workspaces, allowing them to read, search, and manage messages, users, and channels.

An MCP server that gives AI agents structured access to Azure DevOps for managing work items, repositories, and pipelines.

Harbor is a CLI‑driven Docker‑Compose orchestrator that lets you spin up a complete local LLM stack—including model back‑ends (Ollama, llama.cpp, vLLM, MLX, etc.), chat front‑ends (Open WebUI, LibreChat, AnythingLLM, …), web‑search, voice, image generation, and Boost‑based agentic workflows—with a single `harbor up` command.

A multi-agent orchestration engine that turns software goals into explicit graphs to separate code implementation from independent verification and delivery.

A local-first PDF parsing engine for AI agents that provides structured text, tables, and OCR with precise page-level citations to eliminate hallucinations.