Open-source alternatives to Exo

LiteLLM is a unified gateway and proxy server designed to centralize access to over one hundred language model providers. It provides a standardized API interface that abstracts vendor-specific schemas, allowing developers to interact with diverse models through a single, consistent format. By acting as a central traffic management layer, it enables organizations to route, secure, and govern model interactions across multiple deployments. The platform distinguishes itself through its policy-driven architecture, which uses configuration-based routing to manage traffic distribution, load balanc

OpenVINO is an AI inference engine and model serving platform designed to execute optimized deep learning models across CPUs, GPUs, and NPUs through a unified API. It includes a model optimization toolkit for converting, quantizing, and compressing models from various frameworks, alongside a specialized generative AI runtime for large language models. The project distinguishes itself through a plugin-based hardware acceleration layer that maps neural network operations to vendor-specific drivers. It features advanced execution mechanisms such as continuous batching, speculative decoding, and

This project is an AI model API gateway and proxy server designed to provide a unified interface for interacting with diverse artificial intelligence service providers. It functions as a centralized middleware platform that routes, load balances, and translates API requests across multiple models, enabling developers to access text, image, audio, and video generation capabilities through a single, standardized integration. The gateway distinguishes itself through comprehensive administrative and financial controls, including event-driven usage accounting, real-time token consumption tracking,

Langroid is a multi-agent orchestration framework and tool integration suite designed for building complex AI applications. It serves as a multi-modal integration layer that connects diverse local and remote language models with an agentic retrieval-augmented generation system. The project distinguishes itself through a collaborative message-exchange paradigm, allowing specialized agents to delegate tasks hierarchically and coordinate via structured communication. It features an advanced state management system for conversational AI, including the ability to rewind and prune conversation hist

TensorFlowOnSpark is a distributed framework for running TensorFlow machine learning workloads and model training across Apache Spark clusters. It functions as a cluster computing orchestrator that manages worker processes and resource allocation to scale deep learning tasks across multiple computing nodes. The platform enables distributed deep learning training and large-scale model inference, allowing users to execute tasks across a cluster of servers to handle datasets that exceed the memory of a single machine. It integrates deep learning workloads with Spark data processing to create end

Qwen3 is a transformer-based large language model designed as a generative AI foundation for understanding, reasoning, and generating human language. It functions as a comprehensive ecosystem for model training, fine-tuning, and production-ready inference, providing the underlying architecture and weights necessary to build diverse artificial intelligence applications. The project distinguishes itself through extensive support for model quantization and distributed inference, enabling efficient execution across a wide range of hardware from consumer-grade devices to scalable cloud infrastruct

Llama-swap is a local inference orchestrator and API gateway for large language models. It functions as an OpenAI API proxy that manages the lifecycle of multiple local model servers, automatically starting and stopping them to swap models based on incoming request identifiers. The project distinguishes itself through dynamic model swapping and hardware optimization. It utilizes a specialized matrix-based concurrency control to define which models can run simultaneously and employs cost-based eviction to remove inactive servers from memory based on relative resource costs. The system provide

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

This project is a comprehensive framework for the entire lifecycle of transformer-based language models, supporting everything from foundational pretraining to specialized deployment. It provides a modular toolkit for defining neural network architectures, managing data preparation pipelines, and executing training routines across various scales. The framework is designed to handle the full model development process, including supervised fine-tuning, behavioral alignment, and the integration of agentic capabilities. What distinguishes this framework is its focus on efficient training and adva

Whisper.cpp is a high-performance, local-first speech recognition engine designed to run large-scale machine learning models on consumer hardware. It functions as a portable library that converts audio into text, supporting both static file transcription and real-time stream processing. By utilizing a lightweight inference engine and weight quantization, the project minimizes memory and compute overhead, allowing for efficient execution without reliance on external cloud APIs or internet connectivity. The project distinguishes itself through a hardware-agnostic compute abstraction that offloa

Distributed-llama is a distributed inference engine and command line tool for running large language models across multiple networked machines. It functions as a compute cluster manager that coordinates worker nodes to share the computational load of a single model. The system utilizes tensor parallelism to shard model weights across different hosts, allowing the execution of models that exceed the memory capacity of a single piece of hardware. It includes a dedicated format converter to transform standard model files into a compatible binary layout optimized for distributed loading. The eng

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

BitNet is a quantized inference engine designed to execute highly compressed language models by performing arithmetic on low-precision, bit-level weight data. It functions as a model optimization toolkit and a high-performance kernel library, enabling the execution of large language models on consumer hardware by reducing memory footprints and increasing processing speeds. The project distinguishes itself through hardware-specific kernel optimizations that leverage native processor instructions to accelerate matrix multiplication. By utilizing packed integer arithmetic and memory-aligned weig

Modular is a unified machine learning development platform designed for building, compiling, and deploying high-performance neural network models. It provides a comprehensive execution engine that supports both local and production-grade inference, enabling developers to manage the entire model lifecycle from initial architecture definition to scalable, containerized service deployment. The platform distinguishes itself through a hardware-agnostic runtime that abstracts diverse silicon architectures, allowing models to execute efficiently across varied compute environments. It includes a spec

BentoML is a machine learning model serving framework and GPU-accelerated inference server designed to package, deploy, and scale AI models as production-ready REST APIs. It functions as an AI model lifecycle manager and an inference graph orchestrator, enabling the chaining of multiple models and custom logic into complex pipelines for advanced task sequences. The framework distinguishes itself through a dynamic batching engine that optimizes GPU throughput and an artifact-based packaging system that bundles model weights and dependencies into immutable archives for consistent deployment. It

llama-cpp-python provides a Python interface for the llama.cpp library, enabling the execution of large language models with hardware acceleration. It functions as a GGUF model loader and a structured text generator capable of running inference servers and multimodal runtimes for processing both text and image inputs. The project distinguishes itself through a local inference server that exposes model capabilities via an OpenAI-compatible web API. It supports advanced execution techniques including speculative decoding, weight quantization, and layer-based GPU offloading to manage memory acro

Dask is a parallel computing framework and distributed task scheduler designed to scale Python data science workflows from single machines to large clusters. It functions as a cluster resource manager that orchestrates computational logic by representing tasks and their dependencies as directed acyclic graphs. This architecture allows the system to automate the distribution of workloads across available hardware while managing complex execution requirements. The project distinguishes itself through a lazy evaluation engine that defers data operations until they are explicitly requested, enabl

KoboldCPP is a local large language model inference engine and GGUF model runner designed to execute quantized models on personal hardware. It functions as a multimodal AI server and API gateway, providing OpenAI-compatible endpoints that allow third-party clients to interact with locally hosted models. The project distinguishes itself as an AI storytelling backend, featuring dedicated tools for long-form narrative management through persistent memory, world lore tracking, and character state management. It further extends its capabilities as a multimodal server capable of processing text, im

This project is a headless large language model inference engine and server manager designed for local deployments. It provides a developer toolkit and API gateway that allows for the management of model lifecycles and inference tasks without a graphical user interface. The system enables the deployment of model engines across different operating systems, cloud environments, or CI pipelines. It includes a command-line interface for bootstrapping development projects and automating the orchestration of loading and unloading model binaries based on specific workflow needs. The toolset covers i

Triton Inference Server is a high-performance server designed to deploy machine learning models from multiple frameworks across GPUs and CPUs. It functions as a hardware-accelerated inference engine and a gRPC inference gateway, providing a standardized communication layer for transmitting binary tensor data with low latency. The system acts as a multi-framework model orchestrator, allowing users to link multiple AI models into ensembles and scripts to create complex inference pipelines. It also serves as a model lifecycle manager, providing controls to load, unload, and monitor the performan

Ollama is a cross-platform runtime for managing, serving, and executing large language models on local hardware. It functions as a model manager and orchestrator that allows for the downloading, updating, and organization of model weights and configurations to ensure private and offline inference. The system provides a local inference API and a RESTful interface for programmatic model lifecycle management and text generation. It utilizes a compiled C++ backend to handle tensor operations and memory management. To support various hardware configurations, the runtime employs dynamic GPU offloa

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

Airllm is a framework designed to execute and fine-tune large language models on consumer-grade hardware. By employing layer-wise model decomposition and memory-efficient loading techniques, the engine enables the operation of massive models that would otherwise exceed available system or video memory. The project distinguishes itself through a suite of optimization strategies that balance memory footprint with performance. It utilizes block-wise weight quantization and asynchronous layer prefetching to reduce resource consumption and hide data transfer latency. Additionally, the framework su

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

Dynamo is a distributed inference orchestration platform designed for large language models. It functions as a system to coordinate prefill and decode phases across GPU nodes, utilizing a multi-backend runtime adapter to connect engines like vLLM and TensorRT-LLM through a unified block-oriented memory interface. An OpenAI-compatible API server provides the frontend for integration with existing tools and clients. The project is distinguished by its disaggregated serving architecture, which separates prompt processing and token generation onto independent GPU pools to optimize throughput and

Nano-vllm is a high-performance inference engine designed for executing large language models locally. It functions as a specialized runtime that prioritizes accelerated token generation and efficient hardware utilization for text generation tasks. The project distinguishes itself through a comprehensive suite of optimization techniques, including a graph compilation engine that transforms neural network operations into pre-compiled execution plans. It also incorporates a tensor parallelism framework to distribute model weights across multiple hardware accelerators, effectively reducing memor

Llama.cpp is an inference engine designed for the local execution of text-based and multimodal language models on consumer hardware. It provides a core environment for running models that process both text and image inputs, utilizing hardware-accelerated backends to optimize performance across diverse CPU and GPU architectures. The project distinguishes itself by offering a lightweight HTTP server that adheres to standard API specifications, enabling chat completion, embeddings, and reranking services. It includes a suite of tools for model quantization and conversion, which reduces memory us