genai-processors: a modular framework for building asynchronous and composable multimodal AI pipelines
A lightweight Python library for building modular, asynchronous, and composable AI pipelines that unify multimodal content processing and streaming.
instill-core: an end-to-end AI infrastructure platform for data processing, pipeline orchestration, and model hosting
An end-to-end AI platform that simplifies the orchestration of unstructured data, AI pipelines, and model deployment to build RAG and AI-first applications.
YTPro: a modified YouTube client with AI-powered video summarization and advanced playback controls
A modified YouTube client that integrates Google Gemini for AI video summarization alongside ad-blocking and content downloading tools.
alan-sdk-web: an intelligent app platform SDK that enables real-time generation of business logic and UI
An SDK for embedding an intelligent layer into web applications that enables the real-time generation of business logic and UI components.
presentation-ai: an open-source AI presentation generator with support for local LLMs and custom themes
An open-source, AI-powered presentation generator that creates customizable slides from a topic via an outline-first workflow.
TTS-WebUI: a unified web interface for running and managing dozens of open-source text-to-speech and audio generation models
A unified web interface for managing and running a wide range of open-source text-to-speech, audio generation, and audio conversion AI models.
Gemini-API: a reverse-engineered asynchronous Python wrapper for the Google Gemini web app
A reverse-engineered asynchronous Python wrapper for the Google Gemini web app that enables programmatic access to features like image generation, deep research, and custom Gems.
hallucination-leaderboard: a public leaderboard tracking LLM hallucination rates in summarization tasks
A public leaderboard that uses Vectara's Hallucination Evaluation Model (HHEM) to measure and compare how often different LLMs hallucinate when summarizing documents.
semantic-router: a superfast decision-making layer for LLMs and agents using semantic vector space for routing
A high-speed decision-making layer for LLMs and agents that uses semantic vector space to route requests based on meaning rather than slow LLM generation.
Decepticon: an autonomous red team agent that executes professional attack chains and kill chains within a hardened sandbox
An autonomous red team agent that executes realistic, professional attack chains and kill chains within a hardened sandbox to automate security testing and defense verification.
transformer-explainer: an interactive browser-based visualization for learning the internal operations of GPT-2
An interactive visualization tool that runs a live GPT-2 model in the browser to help users learn how Transformer-based models predict text.
ChatGPT-Shortcut: a curated prompt library and management tool for improving AI outputs across multiple platforms
An AI prompt management tool providing a curated library of 5,000+ prompts and tools to organize, create, and share custom prompts across various AI platforms.
morphic: an AI search engine with a generative UI that renders rich inline components from streamed JSON
An AI-powered search engine that uses a generative UI to render rich, cited answers with interactive components instead of plain text.
krita-ai-diffusion: a generative AI plugin for Krita that integrates diffusion models for precise image editing and painting
A Krita plugin that integrates generative AI diffusion models into the painting workflow, offering tools for inpainting, live painting, and precise structural control.
outlines: a library for guaranteeing structured LLM outputs via type-constrained generation
A library for guaranteeing structured outputs from LLMs by constraining generation to match specific Python types or Pydantic models.
Open-Generative-AI: an unrestricted open-source alternative to AI video platforms with local inference and multi-model support
An open-source, unrestricted AI studio for generating images and videos using 200+ models, featuring local inference options and a visual workflow builder.
openui: an open-source AI-powered UI generator that renders live descriptions into framework-ready code
An open-source tool that lets you describe UI components in plain language and see them rendered live, with the ability to convert them to React, Svelte, or Web Components.
TurboDiffusion: a video generation acceleration framework that reduces diffusion latency by 100-200x
TurboDiffusion is a video generation acceleration framework that speeds up diffusion generation by 100-200x on a single GPU using attention optimization and timestep distillation.
MAGI-1: an autoregressive world model for scalable high-fidelity video generation with strong physical accuracy
MAGI-1 is an autoregressive video generation model that produces high-fidelity videos chunk-by-chunk to ensure temporal consistency and physical accuracy.
ComfyUI-LTXVideo: custom ComfyUI nodes for advanced LTX-2 video generation and audio synthesis
A collection of custom ComfyUI nodes and workflows that extend the LTX-2 video generation model with features like HDR output, lip-syncing, and generative upscaling.
transformerlab-app: an open-source machine learning platform that unifies AI research tooling and cluster orchestration
An open-source machine learning platform that unifies training, fine-tuning, inference, and evaluation into a single interface for individuals and research labs.
maestro: a streamlined tool to accelerate the fine-tuning of multimodal vision-language models
A streamlined tool for accelerating the fine-tuning of multimodal vision-language models like Florence-2, PaliGemma 2, and Qwen2.5-VL.
SimpleTuner: a unified training framework for fine-tuning multi-modal generative models with enterprise-grade orchestration
A comprehensive training framework for fine-tuning image, video, and audio generative models, supporting a wide range of architectures with a focus on simplicity and memory efficiency.
OneTrainer: a one-stop solution for training and fine-tuning a wide variety of diffusion models
A comprehensive training suite for diffusion models that provides tools for dataset preparation, fine-tuning, and model conversion through a GUI or CLI.
OpenDeepWiki: an AI-driven repository knowledge base that generates structured docs, chat interfaces, and MCP endpoints from codebases
An AI-driven knowledge base generator that turns Git repositories and local directories into structured documentation, searchable chat interfaces, and MCP endpoints.
MetaClaw: an agent proxy that enables AI assistants to meta-learn and evolve through real-world conversations
An agent proxy that enables AI assistants to meta-learn and evolve through real-world conversations using skill injection and asynchronous RL fine-tuning.
Kiln: a local-first AI development workbench for prompt optimization, evaluations, and agent orchestration
A local-first AI development workbench that integrates prompt optimization, evaluations, RAG, and fine-tuning into a single workflow for teams.
h2o-llmstudio: a no-code GUI and framework for fine-tuning large language models with support for memory-efficient training
A no-code GUI and framework for fine-tuning large language models, supporting memory-efficient techniques like LoRA and advanced optimization methods like DPO.
CosyVoice: a scalable multilingual zero-shot text-to-speech synthesizer based on large language models
An LLM-based text-to-speech system for zero-shot multilingual speech synthesis with high speaker similarity and low-latency streaming.
any-llm: a unified API to access any LLM provider using official SDKs without a proxy
A unified Python SDK that provides a single interface to access multiple LLM providers like OpenAI, Anthropic, and Mistral without changing code.
dstack: a unified control plane for GPU provisioning and orchestration across multiple clouds and on-prem clusters
A unified control plane for GPU provisioning and orchestration that streamlines development, training, and inference across any GPU cloud, Kubernetes, or on-prem clusters.
XNNPACK: a low-level acceleration library providing optimized neural network primitives for cross-platform inference
XNNPACK is a highly optimized library of low-level performance primitives used to accelerate neural network inference across ARM, x86, WebAssembly, and RISC-V platforms.
optimum: a hardware-optimization toolkit for maximizing the efficiency of training and inference across diverse AI accelerators
An extension of the Hugging Face ecosystem that provides optimization tools to train and run AI models with maximum efficiency on targeted hardware accelerators.
zml: a production inference stack that decouples AI workloads from proprietary hardware
A production inference stack that decouples AI workloads from proprietary hardware, allowing a single codebase to run models on NVIDIA, AMD, Intel, and TPU/Trainium accelerators.
FastDeploy: a production-ready LLM and VLM deployment toolkit with PD separation and broad hardware acceleration
A production-grade deployment toolkit for LLMs and VLMs based on PaddlePaddle, offering high-performance inference and broad hardware compatibility.
csghub: a private on-premise LLM asset management platform similar to Hugging Face
An open-source, on-premise alternative to Hugging Face for managing, storing, and distributing LLM assets, datasets, and code.
typedb: a strongly-typed database unifying relational, document, and graph models with a declarative query language
TypeDB is a next-generation database that unifies relational, document, and graph models into a single strongly-typed system to simplify the management of complex, interconnected data.
open_model_zoo: a collection of optimized pre-trained deep learning models and tools for high-performance inference
A collection of optimized pre-trained deep learning models and tools for accelerating the development and deployment of high-performance inference applications.
CTranslate2: a high-performance inference engine for Transformer models with advanced quantization and hardware optimization
A C++ and Python library for efficient Transformer model inference, using quantization and custom runtimes to accelerate execution and reduce memory usage on CPU and GPU.
whichllm: a hardware-aware recommendation engine that ranks the best local LLMs based on system specs and real-world benchmarks
A hardware-aware LLM recommendation tool that ranks the best HuggingFace models based on your specific GPU/CPU/RAM and real-world benchmark performance.
argmax-oss-swift: on-device audio inference frameworks for Apple platforms providing speech-to-text, text-to-speech, and speaker diarization
A collection of on-device inference frameworks for Apple platforms providing speech-to-text, text-to-speech, and speaker diarization using Core ML.
TensorRT: a high-performance inference optimizer and runtime for accelerating AI models on NVIDIA GPUs
An AI inference optimizer and runtime that accelerates deep learning model execution on NVIDIA GPUs across various modalities.
ncnn: a high-performance neural network inference framework optimized for mobile, embedded, and desktop deployment
A high-performance neural network inference framework optimized for mobile, embedded, and desktop deployment with no third-party runtime dependencies.
ColossalAI: a distributed deep learning framework for efficient large-scale model training and inference
A distributed deep learning framework that makes training and inference for large AI models faster and cheaper through advanced parallelism and memory management.
keras-tcn: a Temporal Convolutional Network layer for Keras to replace LSTMs and GRUs in sequence modeling
A Keras implementation of Temporal Convolutional Networks (TCN) that provides a more stable and parallelizable alternative to LSTMs and GRUs for long sequence modeling.
pykeen: a Python framework for training and evaluating knowledge graph embedding models
A Python package for training and evaluating knowledge graph embedding models, featuring a wide array of built-in datasets and models.
PyPOTS: a machine learning toolbox for analyzing multivariate time series with missing values
A Python toolbox for machine learning on partially-observed time series, providing unified APIs for imputation, forecasting, and anomaly detection on data with missing values.
diffrax: a JAX-based library for autodifferentiable and GPU-capable numerical differential equation solvers
A JAX-based library for numerical differential equation solvers that is autodifferentiable and GPU-capable, supporting ODEs, SDEs, and CDEs.
SimpleHTR: a handwritten text recognition system that converts images of words and text lines into digital text
A TensorFlow-based handwritten text recognition system that converts images of single words or text lines into digital text using CNN and LSTM layers.
xlstm: a recurrent neural network architecture that extends LSTM to compete with Transformers in language modeling
A new Recurrent Neural Network architecture that extends LSTM to compete with Transformers and State Space Models, featuring a 7B parameter language model for efficient inference.