Open-source alternatives to RWKV Runner

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a config-driven system for instantiating components, orchestrating distributed training, and managing parameter-efficient fine-tuning with quantization support, all through YAML-based configurations and command-line overrides. The library distinguishes itself through its comprehensive post-training workflow orchestration, combining supervised fine-tuning, preference optimization (DPO, PPO, GRPO), knowledge distillation, and quantization-aware training in a single configurable pip

CoAI is an enterprise-grade, self-hostable AI gateway platform that unifies access to over 200 AI models from more than 35 providers through a single OpenAI-compatible API endpoint. It functions as a multi-tenant gateway, routing requests across providers with load balancing, automatic failover, and priority-based routing, while exposing standard OpenAI API endpoints for chat, image generation, model listing, and billing to enable seamless integration with existing tools and clients. The platform distinguishes itself through a comprehensive set of operational capabilities built around the gat

This project is a containerized development stack and application framework for building retrieval-augmented generation systems. It provides a dockerized AI sandbox that integrates local model runtimes, knowledge graphs, and vector stores to enable the creation of contextual chatbots. The stack is distinguished by its graph-based vector store, which combines structured knowledge graphs with vector indices for both semantic and structural data retrieval. It allows for local model hosting with CPU or GPU acceleration, enabling generative tasks without reliance on external cloud APIs. The frame

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

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a configurable training pipeline orchestrated through YAML recipes, with CLI overrides and component swapping, distributed training via FSDP2, memory optimizations, and parameter-efficient fine-tuning methods like LoRA, DoRA, and QLoRA. The library distinguishes itself through its YAML-driven configuration system that defines all training parameters and instantiates components from config files, with full CLI override capability for any field or component at launch time. It suppo

ds4 is a local inference engine for DeepSeek models that includes a distributed runtime for splitting transformer layers across networked computers. It functions as a reasoning controller with a local weight streamer and an API server that streams chat completions via industry standard endpoints. The system employs a memory management model that loads model experts from disk on demand to execute models that exceed available system RAM. It provides controls for reasoning effort and model behavior steering, allowing the modification of response characteristics through activation directions. Th

AidLearning-Framework is an integrated development platform for building and deploying AI applications on ARM-based devices. It combines Android and Linux operating systems running simultaneously on a single device, providing a unified runtime environment for cross-system AI development. The platform includes hardware acceleration across CPU, GPU, and NPU, with a unified API that automatically selects the optimal compute backend for inference. The framework distinguishes itself by enabling Python-based AI projects to be packaged directly into Android APK files for installation on mobile devic

GPT4All is a cross-platform runtime environment designed to execute large language models directly on local consumer hardware. By leveraging an optimized C++ inference backend, it enables private, offline AI interactions without requiring an internet connection or external cloud services. The project provides a comprehensive ecosystem for managing the entire model lifecycle, including discovery, downloading, and configuration of local weights. What distinguishes the platform is its integrated retrieval-augmented generation engine, which allows users to index local documents into semantic vect

Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and multi-agent systems. It provides a comprehensive suite of primitives for creating resilient AI applications, including durable workflow orchestration, event-driven agent loops, and semantic memory management. By integrating these core components, the platform enables developers to build complex, multi-step processes that can reason about goals and execute tasks without manual intervention. The framework distinguishes itself through its focus on observability and secure, isolated execut

Kreuzberg is a document extraction engine that converts PDFs, Office files, images, and over 90 other formats into clean, structured text and metadata. It is built around a compiled Rust core that can be used as a native library, a command-line tool, a REST API server, or a WebAssembly module for browser-based processing. The system is designed to run entirely on self-hosted infrastructure, with no data leaving the user's environment. What distinguishes Kreuzberg is its breadth of integration surfaces and its pipeline architecture. It exposes extraction capabilities through native bindings fo

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

Muzic is a deep learning platform and framework for AI-driven music analysis, composition, and synthesis. It functions as a music generation framework and analysis tool, utilizing large language models and autonomous agents to orchestrate the creation and interpretation of symbolic and audio music. The project is distinguished by its cross-modal capabilities, mapping natural language and symbolic music into a shared joint embedding space for zero-shot classification and information retrieval. It employs a variety of specialized architectures, including diffusion frameworks for audio synthesis

Llama-GPT is a self-hosted generative AI model runner that provides a private web interface for interacting with large language models. By executing these models directly on local hardware, it ensures that all intelligent assistance remains offline and independent of external cloud service providers. The project functions as a private assistant that maintains complete data ownership by storing all application state and model interactions on local storage volumes. It is designed to operate within a broader self-hosted computing environment, allowing users to maintain control over their persona

Llamafile is a machine learning model runner and packager that enables local inference by bundling model weights and runtime environments into a single, self-contained executable. It functions as a cross-platform engine, allowing users to execute large language models and perform speech-to-text tasks directly on their own hardware without requiring external software dependencies or complex installations. The project distinguishes itself by utilizing a specialized binary format that allows the same executable to run natively across multiple operating systems and hardware architectures. It auto

The simplest way to run LLaMA on your local machine

ChatGPT-Next-Web is a web-based chat interface for interacting with large language models via API or self-hosted model runners. It functions as a prompt management tool and a cross-platform application available for web, mobile, and desktop environments. The project distinguishes itself through a plugin integration gateway that extends model capabilities with external tools like network search and calculators. It includes a self-hosted administrative dashboard for controlling model lists, member permissions, and access passwords on private infrastructure. The application covers prompt engine

Llama2.c is a minimal inference engine designed to execute transformer-based language models using only standard C code. By implementing neural network forward passes without external dependencies or complex runtime environments, it provides a lightweight execution environment for running pre-trained models. The project distinguishes itself through a focus on portability and resource efficiency. It utilizes static memory allocation to avoid dynamic heap management and maps model parameter files directly into the process address space to minimize memory overhead. The implementation relies on s

Langextract is a framework designed to transform unstructured text into structured, machine-readable data using language model orchestration. It provides a high-performance pipeline that processes large volumes of narrative text by utilizing parallel execution and sequential extraction passes. The library is built to handle complex data extraction tasks, including specialized support for clinical information and medical entity relationship recognition. The project distinguishes itself through a plugin-based architecture that supports both local hardware execution and cloud-hosted model endpoi

This repository serves as a comprehensive directory and resource hub for accessing, deploying, and optimizing artificial intelligence tools. It functions as a community-driven index that aggregates web portals, mirror sites, and alternative hosting platforms to provide users with free or alternative access to large language models and conversational assistants. The project distinguishes itself by offering a dual focus on both service discovery and self-hosting capabilities. It provides a curated collection of open-source templates and frameworks that enable users to deploy private, custom-tai

Open WebUI is a self-hosted, web-based platform designed for interacting with local and remote artificial intelligence models. It functions as a unified interface and orchestration suite, enabling users to build, deploy, and manage specialized AI agents equipped with custom instructions, external tool access, and private knowledge bases. The platform distinguishes itself through a modular architecture that supports complex AI workflows. It features a plugin-based framework for custom logic and pipeline-based request processing, allowing developers to filter or transform data streams before th

Danswer is an LLM application framework and RAG engine that provides a self-hosted interface for connecting large language models to private data. It serves as an enterprise AI chat interface and agent orchestrator, enabling the creation of specialized assistants with custom instructions and knowledge bases. The platform differentiates itself through an observability dashboard for tracking query history and token consumption, as well as a white-labeled interface for customized branding. It includes a multi-step research workflow for producing long-form reports and a sandboxed environment for

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

Jan is a local language model desktop application and AI assistant orchestrator. It provides a unified interface for interacting with both resident models and remote cloud AI providers. The project functions as a host for the Model Context Protocol, connecting AI models to external tools and data sources. It also operates as an OpenAI compatible API server, exposing local models through a standardized server endpoint for other applications to query. The system supports the creation of specialized AI personas with custom instructions and allows for the management of hybrid model environments,

The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.

KServe is a Kubernetes-native platform for deploying and serving machine learning models as scalable inference services. It supports both generative AI models, including large language models, and traditional predictive models from frameworks such as TensorFlow, PyTorch, Scikit-Learn, XGBoost, and ONNX. The platform manages the full lifecycle of model deployments, including revision tracking, canary rollouts, A/B testing, and automatic rollbacks, and provides serverless scale-to-zero capabilities for cost-efficient resource management. KServe distinguishes itself through a standardized infere

This project is a self-hosted AI frontend and web-based chat interface designed to interact with large language model APIs. It functions as an API-based chat client and dashboard that enables users to send prompts and receive responses from generative AI models. The application serves as a self-hosted AI gateway, providing API key proxying to connect official model keys to a web interface. It includes security and traffic controls, such as interface access restrictions via a shared secret key and request volume limiting to prevent service abuse. The system covers conversation data management