A desktop application that provides a visual interface to manage MCP servers, commands, and agents across multiple AI coding assistants like Claude Code and Cursor.

A library for measuring and optimizing the energy consumption of deep learning workloads across various hardware platforms including NVIDIA, AMD, and Apple Silicon.

A local-first issue tracker CLI that provides a persistent memory layer and behavioral guardrails for AI-assisted development to prevent context loss across sessions.

A PyTorch emulation library for MX-compatible formats and bfloat quantization, enabling data scientists to explore the impact of low-precision numerical formats on DNNs.

An open-source full-stack API for quantum simulation and quantum hardware control, providing a device-agnostic way to execute quantum circuits.

A Dart MCP server and Flutter package that allows AI agents to inspect, drive, and interact with running Flutter apps in debug mode.

SpatialBot is a Vision-Language-Action model that enhances spatial understanding and depth perception in VLMs, enabling precise spatial reasoning and robot manipulation.

An API that integrates ComfyUI nodes into Nuke, allowing VFX artists to use generative AI workflows directly within their professional compositing software.

A Windows desktop assistant that uses vision models to analyze screen content in real-time and generate scrolling AI comments (danmu) with optional voice synthesis.

pytorch‑ood is a genuine Python library for out‑of‑distribution detection built on PyTorch. It bundles >30 detectors, loss functions, pretrained models, datasets and utilities, integrates with pytorch‑lightning, and offers a simple API plus benchmark helpers. Install via `pip install pytorch-ood` and start using detectors like `EnergyBased` with just a few lines of code.

A secure local AI chat application that supports the Model Context Protocol (MCP) for easy integration of AI tools and services while keeping data stored locally.

An MCP server that connects AI assistants to SEC EDGAR filings, providing precise access to company financial statements and insider trading data.

A high-performance library for training large language models that uses 3D parallelism and optimized kernels to reduce training time and cost.

The official Claude SDK for C#, allowing .NET developers to integrate Anthropic's Claude API into their applications.

A source-available Agent Runtime platform for building, orchestrating, and operating AI agents and executable workflows with built-in governance and sandboxed execution.

AgentKit is an open‑source SDK that provides a catalog of 70 ready‑made “kits” (full apps, pipelines, or templates) for building, testing and deploying AI agents. Kits are defined by a simple config file, can be edited in a visual flow studio, and are shipped as Next.js apps that run server‑less. The collection covers support triage, code review, RAG chat, hiring assistants, legal/medical bots, and many other business‑focused agents, making it a turnkey platform for creating reliable, enterprise‑grade AI agents.

ZUNA1.1 is an open foundation model for EEG that denoises, reconstructs missing channels, and upsamples sparse electrode layouts using 3D scalp coordinates.

A local-first AI filmmaking workspace that integrates coding agents with a visual canvas and a unified API for generating images, video, and voice.

PEAR is a real-time framework for expressive 3D human mesh recovery that can predict human mesh parameters at 100 FPS from images or video.

ERA is an AI system that helps scientists write expert-level empirical software by combining LLMs with a tree-search algorithm to iteratively generate and score candidate programs.

A comprehensive benchmark and modular codebase for image manipulation detection and localization, providing standardized components and SOTA model implementations.

CT-1 is a Vision-Language-Camera model that estimates precise camera trajectories from images and text prompts to enable spatially aware, controllable video generation.

A prompt compilation kit for Claude Code that transforms vague image requests into professional, validated prompts for gpt-image-2.

An AI-powered video enhancement toolkit specialized for anime that provides upscaling, motion interpolation, and restoration in a single processing pass.

A set of Quarkus extensions that integrate the LangChain4j library, allowing Java developers to easily incorporate LLMs, embeddings, and document stores into their applications.

A library that extends the safetensors format to provide a unified storage and management system for various LLM compression and quantization schemes.

A Python library for modeling and solving automated planning problems in a planner-independent way, supporting various solvers and PDDL formats.

LLM‑TPU is an open‑source SOPHGO project that compiles HuggingFace LLM and vision‑language models into SOPHGO TPU‑compatible bmodels. It supports one‑click compilation, a large catalog of quantised models, dynamic/KV‑cache inference, multi‑chip scaling, and provides ready Python/C++ demos for BM1684X, BM1688 and CV186X chips.

An infinite canvas for learning that allows users to branch into new documents by asking questions at any point in existing content.

An AI-native platform for building and orchestrating security agents to automate complex tasks like vulnerability analysis and penetration testing.

A spatiotemporal image and video engine that generates AI visuals of any location on Earth at any point in time from 252 million years ago to 3050 AD.

Tutel is Microsoft’s open‑source, high‑performance MoE library for large language models. It provides dynamic parallelism, low‑precision inference (NVFP4, MXFP4, FP8, BF16), support for up to 1 M‑token contexts, vision extensions, and Docker images that serve models like DeepSeek‑V3.2, Kimi‑K3, GLM‑5.x, Qwen‑3, and GPT‑OSS on both NVIDIA and AMD GPUs. Install via pip from the Git repo or build from source, then run the supplied Docker containers or use the Python API for custom MoE routing.

An open-source ecosystem of Chinese pre-trained foundation models and a supporting framework for natural language understanding, generation, and multimodal tasks.

A mobile GUI agent framework for Android that enables AI agents to perceive and operate app interfaces on real devices for automated, long-running workflows.

A lightweight Python package for Automatic Speech Recognition using ONNX models, eliminating the need for PyTorch or Transformers for fast deployment on edge and server hardware.

A self-hosted AI tool for real-time transcription and translation of live streams, microphone audio, and video files into English and other languages.

A family of Arabic-first generative speech recognition models that provide state-of-the-art transcription for dialectal Arabic and code-switched speech.

A Russian-language voice assistant that works offline by default and supports extensible plugins and LLM-powered natural language command processing.

PocketSphinx is an open‑source, offline speech‑to‑text engine (C library with Python bindings) that runs efficiently on low‑resource devices. It provides a command‑line tool and APIs for recognizing or aligning audio, outputting results as JSON.

A Manim plugin that integrates AI voiceovers and recording tools directly into Python, enabling per-word animation synchronization using OpenAI Whisper.

A simple Azure Speech Service module that uses the Microsoft Edge Read Aloud API to provide text-to-speech synthesis for server-side runtimes.

A local-first voice studio for macOS and iOS that uses MLX and Swift to generate high-quality speech, featuring voice cloning and custom voice design without cloud dependency.

An augmentative and alternative communication (AAC) web app that enables people with speech impairments to communicate via symbols and text-to-speech.

A Python library for offline text-to-speech conversion that utilizes native system engines to generate voice output without an internet connection.

A Python/C library and toolset for forced alignment, automatically synchronizing audio narrations with their corresponding text fragments.

Kiwi‑Edit is an open‑source video‑editing system that takes natural‑language instructions (and optional reference images) to modify whole videos. It fuses a multi‑modal LLM encoder with a video Diffusion Transformer, offering style transfer, object add/replace/remove, and background changes. The repo provides full training scripts (three‑stage curriculum with Qwen2.5‑VL‑3B + Wan2.2‑TI2V‑5B), pretrained Diffusers checkpoints, and evaluation pipelines on OpenVE‑Bench and RefVIE‑Bench.

A Payload CMS plugin that adds AI‑powered text, image, and voice generation to content fields, supports multiple model providers, and offers fine‑grained configuration and access control.

A Python frontend and library for ComfyUI that allows users to define and run image generation workflows as Python scripts instead of visual node graphs.