8 रिपॉजिटरी
Configurations for deploying API services on private, user-owned infrastructure.
Distinguishing note: Candidates are too narrow (finance, auth, document processing); requires a general API self-hosting tag.
Explore 8 awesome GitHub repositories matching devops & infrastructure · Self-Hosted API Deployments. Refine with filters or upvote what's useful.
gpt-oss is an open-weight large language model and reasoning engine designed for complex reasoning and agentic workflows. It functions as an AI agent framework and model serving API, allowing for local deployment and the hosting of standardized interfaces to expose model completions and internal reasoning processes. The project distinguishes itself as a quantized inference engine, utilizing tensor parallelism and weight quantization to run high-parameter models on limited hardware. It features a reasoning model that employs chain-of-thought processing to solve multi-step logical tasks. The s
Exposes model completions and internal reasoning traces via a standardized REST API for self-hosting.
pywebview is a cross-platform desktop GUI framework for Python that renders HTML, CSS, and JavaScript content using the operating system's native web rendering engine. It enables developers to build desktop applications that run on Windows, macOS, and Linux from a single Python codebase, with the web frontend displayed in a lightweight, native window. The framework provides a bidirectional JavaScript-Python bridge for real-time data exchange between frontend and backend, along with the ability to manipulate the Document Object Model directly from Python without writing JavaScript. It includes
Integrates with PyInstaller, Nuitka, and py2app to bundle the application into a distributable executable.
A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.
Exposes a local LLM through a REST API for integration with other applications or workflows.
DeepReasoning is a self-hosted AI gateway and chat interface that provides an LLM inference API. It functions as a bridge that merges reasoning traces from DeepSeek R1 with the generative capabilities of Claude models to facilitate complex problem solving. The system is delivered as a dockerized application, allowing for deployment on private infrastructure. This architecture enables private LLM inference and secure local management of API keys and authentication tokens on user-controlled hardware. The project covers multi-model orchestration by combining chain-of-thought reasoning and gener
Provides a configuration for deploying the API service on private, user-owned infrastructure.
This project is a multi-purpose REST API utility collection and developer suite. It serves as a centralized service for real-time information aggregation, data transformation, and a wide array of programmatic tools. The service distinguishes itself by providing a broad range of specialized content delivery endpoints, from curated daily summaries and global trending rankings to randomized entertainment content like jokes and quotes. It also functions as a real-time aggregator for environmental and network data, including weather forecasts, currency exchange rates, and public IP lookups. The c
Enables the deployment of a personal instance of the service for reliable connectivity.
Lilishop is a multi-vendor B2B2C e-commerce platform designed as a marketplace where third-party merchants can manage independent storefronts within a unified ecosystem. It is built on a Spring Cloud microservices architecture and a Spring Boot backend, utilizing Vue and Uniapp to deliver responsive user interfaces across web, mobile, and mini-program platforms. The platform differentiates itself through integrated marketing automation tools, including group buying, bargain campaigns, and a commission-based affiliate distribution network. It also features a comprehensive financial settlement
Bootstraps API services using environment-specific startup parameters across different deployment stages.
Presenton is an AI-powered presentation engine and API designed to transform natural language prompts, uploaded documents, and structured data into professional slide decks. It functions as a generation service that leverages large language models to automate the creation of outlines, slide content, and visual assets. The system is distinguished by its support for both cloud-based and self-hosted infrastructure, allowing for the integration of local language models and image generators to ensure data privacy. It implements a Model Context Protocol server, enabling external AI agents to trigge
Hosts the presentation generation engine as a standalone containerized service.
Ever Gauzy is an integrated business management suite providing an ERP and CRM framework for professional services automation. It functions as a multi-tenant SaaS platform that combines time tracking, billing, and human resource management into a unified system. The project is distinguished by its headless architecture, utilizing a REST and GraphQL API gateway to expose business operations. It features a Model Context Protocol server that allows AI assistants to interact with system data and execute functional tools for automated business workflows. The platform covers a broad operational su
Enables running a self-hosted API server on private infrastructure for independent data management.