KServe provides a Kubernetes Custom Resource Definition for serving predictive and generative machine learning (ML) models. It encapsulates the complexity of autoscaling, networking, health checking, and server configuration to bring cutting edge serving features like GPU Autoscaling, Scale to Zero, and Canary Rollouts to ML deployments. KServe enables a simple, pluggable, and complete story for Production ML Serving including prediction, pre-processing, post-processing, and explainability. It is a standard, cloud agnostic Model Inference Platform for serving predictive and generative AI models on Kubernetes, built for highly scalable use cases.

AIBrix is an open-source initiative providing essential building blocks for scalable GenAI inference infrastructure. It delivers a cloud-native solution optimized for deploying, managing, and scaling large language model (LLM) inference, tailored to enterprise needs. Key features include High-Density LoRA Management, LLM Gateway and Routing, LLM App-Tailored Autoscaler, Unified AI Runtime, Distributed Inference, Distributed KV Cache, Cost-efficient Heterogeneous Serving, and GPU Hardware Failure Detection.

TalkCody is a free, open-source AI coding agent designed for developers who value speed, cost, control, and privacy. It offers true freedom to use any AI model without vendor lock-in, maximum speed through unique four-level parallelism, and complete privacy as everything runs locally without leaving the user's machine. With professional-grade features like multimodal input support, MCP server compatibility, and a marketplace for agents and skills, TalkCody aims to enhance development productivity and flexibility.

ComfyUI-Copilot is an intelligent assistant built on the Comfy-UI framework that simplifies and enhances the AI algorithm debugging and deployment process through natural language interactions. It offers intuitive node recommendations, workflow building aids, and model querying services to streamline development processes. With features like interactive Q&A bot, natural language node suggestions, smart workflow assistance, and model querying, ComfyUI-Copilot aims to lower the barriers to entry for beginners, boost development efficiency with AI-driven suggestions, and provide real-time assistance for developers.

Heurist Agent Framework is a flexible multi-interface AI agent framework that allows processing text and voice messages, generating images and videos, interacting across multiple platforms, fetching and storing information in a knowledge base, accessing external APIs and tools, and composing complex workflows using Mesh Agents. It supports various platforms like Telegram, Discord, Twitter, Farcaster, REST API, and MCP. The framework is built on a modular architecture and provides core components, tools, workflows, and tool integration with MCP support.

veScale is a PyTorch Native LLM Training Framework. It provides a set of tools and components to facilitate the training of large language models (LLMs) using PyTorch. veScale includes features such as 4D parallelism, fast checkpointing, and a CUDA event monitor. It is designed to be scalable and efficient, and it can be used to train LLMs on a variety of hardware platforms.

Arcadia is an all-in-one enterprise-grade LLMOps platform that provides a unified interface for developers and operators to build, debug, deploy, and manage AI agents. It supports various LLMs, embedding models, reranking models, and more. Built on langchaingo (golang) for better performance and maintainability. The platform follows the operator pattern that extends Kubernetes APIs, ensuring secure and efficient operations.

Xagent is a dynamic task execution engine that allows users to describe outcomes instead of steps. It plans tasks dynamically, selects tools automatically, and executes them. Users can build various systems by clearly defining goals, such as content creation, research & analysis, enterprise automation, business intelligence, and knowledge work. Xagent features a dynamic planning engine, tool & model orchestration, instant execution mode, observability & control, and supports self-hosted deployment options. It separates core responsibilities into different layers for stability, scalability, and maintainability. Xagent is not a workflow builder but an autonomous planning system for building real AI agents.

AGiXT is a dynamic Artificial Intelligence Automation Platform engineered to orchestrate efficient AI instruction management and task execution across a multitude of providers. Our solution infuses adaptive memory handling with a broad spectrum of commands to enhance AI's understanding and responsiveness, leading to improved task completion. The platform's smart features, like Smart Instruct and Smart Chat, seamlessly integrate web search, planning strategies, and conversation continuity, transforming the interaction between users and AI. By leveraging a powerful plugin system that includes web browsing and command execution, AGiXT stands as a versatile bridge between AI models and users. With an expanding roster of AI providers, code evaluation capabilities, comprehensive chain management, and platform interoperability, AGiXT is consistently evolving to drive a multitude of applications, affirming its place at the forefront of AI technology.

Astron Agent is an enterprise-grade, commercial-friendly Agentic Workflow development platform that integrates AI workflow orchestration, model management, AI and MCP tool integration, RPA automation, and team collaboration features. It supports high-availability deployment, enabling organizations to rapidly build scalable, production-ready intelligent agent applications and establish their AI foundation for the future. The platform is stable, reliable, and business-friendly, with key features such as enterprise-grade high availability, intelligent RPA integration, ready-to-use tool ecosystem, and flexible large model support.

AgC is an open-core platform designed for deploying, running, and orchestrating AI agents at scale. It treats agents as first-class compute units, providing a modular, observable, cloud-neutral, and production-ready environment. Open Agentic Compute empowers developers and organizations to run agents like cloud-native workloads without lock-in.

Jetify's AI SDK for Go is a unified interface for interacting with multiple AI providers including OpenAI, Anthropic, and more. It addresses the challenges of fragmented ecosystems, vendor lock-in, poor Go developer experience, and complex multi-modal handling by providing a unified interface, Go-first design, production-ready features, multi-modal support, and extensible architecture. The SDK supports language models, embeddings, image generation, multi-provider support, multi-modal inputs, tool calling, and structured outputs.

AIGNE Hub is a unified AI gateway that manages connections to multiple LLM and AIGC providers, eliminating the complexity of handling API keys, usage tracking, and billing across different AI services. It provides self-hosting capabilities, multi-provider management, unified security, usage analytics, flexible billing, and seamless integration with the AIGNE framework. The tool supports various AI providers and deployment scenarios, catering to both enterprise self-hosting and service provider modes. Users can easily deploy and configure AI providers, enable billing, and utilize core capabilities such as chat completions, image generation, embeddings, and RESTful APIs. AIGNE Hub ensures secure access, encrypted API key management, user permissions, and audit logging. Built with modern technologies like AIGNE Framework, Node.js, TypeScript, React, SQLite, and Blocklet for cloud-native deployment.

MemU is an open-source memory framework designed for AI companions, offering high accuracy, fast retrieval, and cost-effectiveness. It serves as an intelligent 'memory folder' that adapts to various AI companion scenarios. With MemU, users can create AI companions that remember them, learn their preferences, and evolve through interactions. The framework provides advanced retrieval strategies, 24/7 support, and is specialized for AI companions. MemU offers cloud, enterprise, and self-hosting options, with features like memory organization, interconnected knowledge graph, continuous self-improvement, and adaptive forgetting mechanism. It boasts high memory accuracy, fast retrieval, and low cost, making it suitable for building intelligent agents with persistent memory capabilities.

An open-source AI assistant for taking meeting notes that captures live meeting audio, transcribes it in real-time, and generates summaries while ensuring user privacy. Perfect for teams to focus on discussions while automatically capturing and organizing meeting content without external servers or complex infrastructure. Features include modern UI, real-time audio capture, speaker diarization, local processing for privacy, and more. The tool also offers a Rust-based implementation for better performance and native integration, with features like live transcription, speaker diarization, and a rich text editor for notes. Future plans include database connection for saving meeting minutes, improving summarization quality, and adding download options for meeting transcriptions and summaries. The backend supports multiple LLM providers through a unified interface, with configurations for Anthropic, Groq, and Ollama models. System architecture includes core components like audio capture service, transcription engine, LLM orchestrator, data services, and API layer. Prerequisites for setup include Node.js, Python, FFmpeg, and Rust. Development guidelines emphasize project structure, testing, documentation, type hints, and ESLint configuration. Contributions are welcome under the MIT License.

Chipper provides a web interface, CLI, and architecture for pipelines, document chunking, web scraping, and query workflows. It is built with Haystack, Ollama, Hugging Face, Docker, Tailwind, and ElasticSearch, running locally or as a Dockerized service. Originally created to assist in creative writing, it now offers features like local Ollama and Hugging Face API, ElasticSearch embeddings, document splitting, web scraping, audio transcription, user-friendly CLI, and Docker deployment. The project aims to be educational, beginner-friendly, and a playground for AI exploration and innovation.

This repository contains assets related to AI/ML workloads on Google Kubernetes Engine (GKE). Run optimized AI/ML workloads with Google Kubernetes Engine (GKE) platform orchestration capabilities. A robust AI/ML platform considers the following layers: Infrastructure orchestration that support GPUs and TPUs for training and serving workloads at scale Flexible integration with distributed computing and data processing frameworks Support for multiple teams on the same infrastructure to maximize utilization of resources

Ray is a unified framework for scaling AI and Python applications. It consists of a core distributed runtime and a set of AI libraries for simplifying ML compute, including Data, Train, Tune, RLlib, and Serve. Ray runs on any machine, cluster, cloud provider, and Kubernetes, and features a growing ecosystem of community integrations. With Ray, you can seamlessly scale the same code from a laptop to a cluster, making it easy to meet the compute-intensive demands of modern ML workloads.

Labelbox is a data-centric AI platform for enterprises to develop, optimize, and use AI to solve problems and power new products and services. Enterprises use Labelbox to curate data, generate high-quality human feedback data for computer vision and LLMs, evaluate model performance, and automate tasks by combining AI and human-centric workflows. The academic & research community uses Labelbox for cutting-edge AI research.

Deep Java Library (DJL) is an open-source, high-level, engine-agnostic Java framework for deep learning. It is designed to be easy to get started with and simple to use for Java developers. DJL provides a native Java development experience and allows users to integrate machine learning and deep learning models with their Java applications. The framework is deep learning engine agnostic, enabling users to switch engines at any point for optimal performance. DJL's ergonomic API interface guides users with best practices to accomplish deep learning tasks, such as running inference and training neural networks.

MLflow is a platform to streamline machine learning development, including tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow offers a set of lightweight APIs that can be used with any existing machine learning application or library (TensorFlow, PyTorch, XGBoost, etc), wherever you currently run ML code (e.g. in notebooks, standalone applications or the cloud). MLflow's current components are: * `MLflow Tracking `_: An API to log parameters, code, and results in machine learning experiments and compare them using an interactive UI. * `MLflow Projects `_: A code packaging format for reproducible runs using Conda and Docker, so you can share your ML code with others. * `MLflow Models `_: A model packaging format and tools that let you easily deploy the same model (from any ML library) to batch and real-time scoring on platforms such as Docker, Apache Spark, Azure ML and AWS SageMaker. * `MLflow Model Registry `_: A centralized model store, set of APIs, and UI, to collaboratively manage the full lifecycle of MLflow Models.

TT-NN is a python & C++ Neural Network OP library. It provides a low-level programming model, TT-Metalium, enabling kernel development for Tenstorrent hardware.

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

This repository contains reference architectures and test cases for distributed model training with Amazon SageMaker Hyperpod, AWS ParallelCluster, AWS Batch, and Amazon EKS. The test cases cover different types and sizes of models as well as different frameworks and parallel optimizations (Pytorch DDP/FSDP, MegatronLM, NemoMegatron...).

Ludwig is a declarative deep learning framework designed for scale and efficiency. It is a low-code framework that allows users to build custom AI models like LLMs and other deep neural networks with ease. Ludwig offers features such as optimized scale and efficiency, expert level control, modularity, and extensibility. It is engineered for production with prebuilt Docker containers, support for running with Ray on Kubernetes, and the ability to export models to Torchscript and Triton. Ludwig is hosted by the Linux Foundation AI & Data.

Wenda is a platform for large-scale language model invocation designed to efficiently generate content for specific environments, considering the limitations of personal and small business computing resources, as well as knowledge security and privacy issues. The platform integrates capabilities such as knowledge base integration, multiple large language models for offline deployment, auto scripts for additional functionality, and other practical capabilities like conversation history management and multi-user simultaneous usage.

LLMonFHIR is an iOS application that utilizes large language models (LLMs) to interpret and provide context around patient data in the Fast Healthcare Interoperability Resources (FHIR) format. It connects to the OpenAI GPT API to analyze FHIR resources, supports multiple languages, and allows users to interact with their health data stored in the Apple Health app. The app aims to simplify complex health records, provide insights, and facilitate deeper understanding through a conversational interface. However, it is an experimental app for informational purposes only and should not be used as a substitute for professional medical advice. Users are advised to verify information provided by AI models and consult healthcare professionals for personalized advice.

Chinese-Mixtral-8x7B is an open-source project based on Mistral's Mixtral-8x7B model for incremental pre-training of Chinese vocabulary, aiming to advance research on MoE models in the Chinese natural language processing community. The expanded vocabulary significantly improves the model's encoding and decoding efficiency for Chinese, and the model is pre-trained incrementally on a large-scale open-source corpus, enabling it with powerful Chinese generation and comprehension capabilities. The project includes a large model with expanded Chinese vocabulary and incremental pre-training code.

AI-Horde-Worker is a repository containing the original reference implementation for a worker that turns your graphics card(s) into a worker for the AI Horde. It allows users to generate or alchemize images for others. The repository provides instructions for setting up the worker on Windows and Linux, updating the worker code, running with multiple GPUs, and stopping the worker. Users can configure the worker using a WebUI to connect to the horde with their username and API key. The repository also includes information on model usage and running the Docker container with specified environment variables.

OpenShield is a firewall designed for AI models to protect against various attacks such as prompt injection, insecure output handling, training data poisoning, model denial of service, supply chain vulnerabilities, sensitive information disclosure, insecure plugin design, excessive agency granting, overreliance, and model theft. It provides rate limiting, content filtering, and keyword filtering for AI models. The tool acts as a transparent proxy between AI models and clients, allowing users to set custom rate limits for OpenAI endpoints and perform tokenizer calculations for OpenAI models. OpenShield also supports Python and LLM based rules, with upcoming features including rate limiting per user and model, prompts manager, content filtering, keyword filtering based on LLM/Vector models, OpenMeter integration, and VectorDB integration. The tool requires an OpenAI API key, Postgres, and Redis for operation.

VoAPI is a new high-value/high-performance AI model interface management and distribution system. It is a closed-source tool for personal learning use only, not for commercial purposes. Users must comply with upstream AI model service providers and legal regulations. The system offers a visually appealing interface, independent development documentation page support, service monitoring page configuration support, and third-party login support. It also optimizes interface elements, user registration time support, data operation button positioning, and more.

VoAPI is a new high-value/high-performance AI model interface management and distribution system. It is a closed-source tool for personal learning use only, not for commercial purposes. Users must comply with upstream AI model service providers and legal regulations. The system offers a visually appealing interface with features such as independent development documentation page support, service monitoring page configuration support, and third-party login support. Users can manage user registration time, optimize interface elements, and support features like online recharge, model pricing display, and sensitive word filtering. VoAPI also provides support for various AI models and platforms, with the ability to configure homepage templates, model information, and manufacturer information.