Projects sharing features with Nexa Sdk

Intel XPU LLM Acceleration Library is a toolkit designed to accelerate large language model inference and finetuning on Intel CPUs, GPUs, and NPUs. It provides a distributed inference engine for scaling models across multiple accelerators, a multimodal model runtime for vision and speech tasks, and a low-bit model quantization tool for converting weights into INT4, FP8, and GGUF formats. The project features a parameter-efficient finetuning framework that enables model adaptation using QLoRA and DPO on Intel hardware. It distinguishes itself by providing specialized optimizations for Intel XP

llmware is a Python framework for AI agent orchestration and model management, designed to coordinate multi-model workflows and autonomous agents. It provides a unified model catalog and standardized interface to execute specialized language models for complex research, analysis, and structured data generation. The project distinguishes itself through its heavy emphasis on local execution and quantized inference, allowing models to run on private infrastructure using CPU, GPU, and NPU acceleration via runtimes like ONNX and OpenVino. It features a specialized ability to translate natural lang

GLM-4 is a large language model and fine-tuning framework designed for human-like text production, complex reasoning, and multilingual conversation. It functions as a multimodal system capable of processing high-resolution visual content and as a long-context model designed to analyze documents with a context window of up to one million tokens. The project differentiates itself through a function calling interface that enables AI agent development by connecting the model to external APIs and real-time web browsing. It includes specialized capabilities for generating functional programming cod

llama.cpp is a high-performance C++ inference engine and runtime for executing large language models locally across various hardware architectures. It provides the core components for local model execution, including a dedicated model quantizer for compressing weights into the GGUF format and a system for generating text embeddings for semantic search. The project distinguishes itself through specialized memory and execution optimizations, such as block-wise weight quantization to reduce memory footprints and memory-mapped model loading. It supports structured text generation by using formal

This project is an on-device AI SDK providing a framework for running large language models, vision models, and speech models locally. It serves as an orchestration layer for local LLM execution, ensuring data privacy and offline availability by utilizing hardware acceleration on the device. The SDK is distinguished by its comprehensive voice and multimodal capabilities, including a coordinated voice pipeline for activity detection, speech-to-text, and text-to-speech synthesis. It also provides a dedicated implementation kit for local retrieval-augmented generation and tools for processing co

LLamaSharp is a .NET LLM inference library and local runtime that enables the execution of large language models on CPU and GPU hardware. It serves as a multimodal AI library capable of processing both text and image inputs to generate analytical textual responses without relying on external APIs. The project distinguishes itself as a grammar-based text generator that enforces specific output formats, such as JSON, through constrained sampling pipelines. It also functions as a retrieval augmented generation framework integration, allowing the combination of local inference with external data

MNN is a high-performance inference engine and framework designed for on-device machine learning. It provides a comprehensive environment for executing, optimizing, and deploying neural network models directly on mobile and resource-constrained edge devices. The framework distinguishes itself through a robust model optimization toolkit that supports quantization, compression, and structural graph manipulation to minimize memory footprint and maximize execution speed. It features a modular architecture that abstracts hardware-specific backends, allowing models to run efficiently across diverse

all-in-one is a containerized deployment system designed to install and manage a complete suite of productivity and collaboration services. It functions as a cloud suite deployer that orchestrates the installation of a self-hosted content platform, incorporating necessary dependencies via Docker or Kubernetes. The project distinguishes itself by providing a web-based dashboard for orchestrating, updating, and monitoring the lifecycle of service containers. It also serves as a local AI inference server, enabling the execution of generative text models, image diffusion, and speech processing on

Sherpa-ONNX is an ONNX-based speech processing toolkit that provides a local speech recognition engine, an on-device voice synthesis tool, and a speaker identification framework. It is designed as a cross-platform speech API that enables speech-to-text, text-to-speech, and speaker verification tasks to be executed locally on a device without requiring network access. The project is distinguished by its ability to perform zero-shot voice cloning and speaker diarization on-device. It supports a wide range of hardware accelerations, including GPU and various NPU architectures, and provides a Web

MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained environments. The project focuses on running dense Transformer models on consumer hardware, including GPUs, CPUs, and Apple Silicon, without requiring custom code forks. The project distinguishes itself through heavy optimization for edge hardware, utilizing quantized weight compression in GGUF and MLX formats to reduce memory overhead. It implements advanced inference techniques such as speculative sampling and radix-tree prefix caching to accelerate generation speed and throughp

Moshi is a real-time voice foundation model and speech-to-speech framework designed for bidirectional, low-latency conversations. It functions as a full-duplex voice interface that processes audio and text concurrently in a single stream, enabling natural human-machine dialogue without sequential processing delays. The system utilizes a neural audio codec to compress high-fidelity audio into low-bitrate tokens for efficient transmission. To manage complex responses and reasoning, it employs internal monologue modeling, which generates a hidden stream of thought tokens alongside audible speech

mistral.rs is an inference engine for large language models that runs locally and exposes models behind OpenAI and Anthropic-compatible APIs. It serves as a multi-model serving platform, capable of loading several models in a single server process with per-request routing and on-demand loading and unloading. The engine supports multimodal inference, processing text alongside images, video, audio, and speech inputs, and includes a quantized model deployment runtime that reduces memory use and speeds up inference on consumer hardware. The project distinguishes itself through an agentic tool exe

PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

MiniCPM-V is a multimodal large language model and vision-language system designed for complex visual and linguistic understanding. It functions as an on-device AI model, providing the capacity to process text, images, and video as a compact neural network. The project is specifically developed as an edge AI framework, utilizing quantization and weight sharding to run on memory-constrained mobile chipsets. This allows for the deployment of multimodal intelligence directly on mobile operating systems for local inference. Its capabilities cover multimodal content analysis of high-resolution im

omlx is a local inference server designed to run large language models, vision models, and embedding models on Apple Silicon. It provides a private alternative to industry-standard AI endpoints by hosting a local API gateway that mirrors OpenAI and Anthropic specifications. The system distinguishes itself through specialized hardware optimizations, including continuous batching for high throughput and a tiered caching system that offloads memory blocks to SSD. It also functions as a Model Context Protocol host, enabling the integration of local models with external tools, agents, and structur

LiteRT-LM is a high-performance inference framework designed to execute large language models locally on mobile, desktop, and IoT hardware. It serves as an on-device model runtime that utilizes CPU, GPU, and NPU acceleration to provide low-latency processing. The framework is distinguished by its ability to process text, vision, and audio inputs through a single multi-modal inference engine. It features a local HTTP server that emulates OpenAI-compatible API endpoints and a WebGPU-based runtime for executing models directly within a web browser. To ensure output reliability, it includes a con

Fauxpilot is a self-hosted AI coding assistant and local inference server. It functions as a proxy and API gateway that redirects traffic from IDE plugins to a local large language model, allowing for AI-assisted programming without external cloud dependencies. The project provides a specialized API emulation layer that mimics coding assistant protocols and a standardized OpenAI-compatible interface. This enables supported code editors to use local models for completions and suggestions by overriding default proxy URLs. The system includes capabilities for downloading and deploying local mod

MLC LLM is a machine learning compiler and inference engine designed to execute large language models locally across diverse hardware platforms, including desktop, mobile, and web environments. By utilizing machine learning compilation, the project transforms high-level model definitions into specialized, hardware-specific binary libraries. This process optimizes model weights and generates compute kernels tailored to the unique memory and processing characteristics of target graphics and mobile hardware. The engine distinguishes itself by providing a unified runtime abstraction that enables

gemma.cpp is a C++ inference engine for Gemma, PaliGemma, and Griffin language models, designed to run directly on-device without Python dependencies. It provides a self-contained runtime that loads quantized model weights and performs text generation on CPU or GPU, along with a model checkpoint converter that transforms PyTorch or Keras checkpoints into a compact binary format for fast loading. The engine supports multiple model architectures, including the Griffin recurrent architecture with gated linear recurrent layers and sliding-window attention for efficient long-sequence handling, as

Leela Chess Zero is a deep learning game AI and neural network chess engine that uses search algorithms to determine optimal moves and evaluate game states. It functions as a UCI chess engine, implementing the Universal Chess Interface standard for compatibility with various graphical user interfaces. The system acts as a hardware-accelerated move calculator, leveraging GPU and CPU backends to accelerate neural network inference. It supports the generation and submission of self-play games to training clients to improve the strength of its neural network models. The engine provides capabilit

LocalAI is a local generative AI platform and inference engine designed to host large language, vision, and audio models on private hardware. It functions as an API compatible gateway that mimics proprietary service endpoints, allowing existing third-party software to integrate with a self-hosted backend. The platform distinguishes itself as a distributed AI model orchestrator, capable of scaling inference across machine clusters using VRAM-aware routing and hardware coordination. It provides a unified interface for diverse open-source backends and supports self-hosted RAG infrastructure thro

Duix-Mobile is a software development kit for deploying real-time conversational AI characters on mobile devices. It enables the creation of interactive digital humans capable of fluid voice-to-voice interactions, featuring low-latency speech recognition and synchronized lip movements. The project distinguishes itself through the ability to integrate custom external language models and speech providers to define an avatar's intelligence and voice. It supports the generation of real-time multilingual subtitles and provides mechanisms to track the training status of newly created digital charac

LiteRT is a runtime and API for executing machine learning and generative AI models on mobile, desktop, and IoT hardware. It consists of an inference engine and a specialized environment for running quantized large language and diffusion models locally on edge hardware. The system includes an ahead-of-time model compiler that translates models into hardware-specific bytecode to reduce startup latency and memory overhead. It provides a unified interface for Neural Processing Units with automatic fallback routing to CPUs or GPUs when specific subgraph support is unavailable. An edge model conve

ruby_llm is an LLM integration framework and AI agent orchestrator designed to connect applications to multiple large language model providers through a unified interface. It serves as a toolkit for building autonomous assistants with custom personas, managing structured output via JSON schemas, and implementing vector embedding engines for semantic search. The project distinguishes itself as an observability suite and multimodal toolkit. It provides specialized capabilities for tracking token usage, calculating model costs, and tracing workflows via OpenTelemetry, while supporting the proces

Oatpp is a high-performance C++ web framework and API development kit used for building REST APIs and web services. It functions as an asynchronous HTTP server that utilizes coroutines to handle thousands of simultaneous connections without blocking threads. The toolkit includes a native C++ object-relational mapping layer for executing SQL queries and transforming database results into data objects. It also provides a WebSocket communication library for establishing full-duplex channels to support real-time data streaming and live media. The framework covers a broad range of capabilities, i

ollama-js is a JavaScript client library and API wrapper that provides a programmatic interface for interacting with and managing large language models. It enables the execution of models in both local and cloud-based environments, facilitating the generation of conversational text and the management of model lifecycles. The project distinguishes itself by offering specialized tools for model administration, including the ability to download, create, and remove models, as well as the capacity to define custom model blueprints and prompt templates. It also provides a vector embedding client fo