30 open-source projects similar to nsarrazin/serge, ranked by shared indexed features. Tags may describe platforms or build tools rather than the same primary purpose. Check each project’s use case, license, and deployment requirements before treating it as a replacement.
Serge is a self-hosted web chat interface for running large language models locally using the llama.cpp inference engine. It loads GGUF-format model files directly on your own machine, removing the need for internet connectivity or external API keys, and streams responses to the browser in real time via WebSocket connections. The project is packaged for containerized deployment using Docker and Docker Compose, with a Traefik reverse proxy that handles HTTP and WebSocket routing along with automatic TLS certificate management. Ready-made Kubernetes manifests are also provided, enabling deploym
Shimmy is a local large language model inference engine and server that loads and serves GGUF formatted weights. It is distributed as a single binary runtime written in Rust, providing a standalone environment for running models without external runtime dependencies. The project utilizes WebGPU for hardware acceleration, allowing model compute kernels to execute across diverse graphics hardware through a standardized interface. It features a local server that implements an OpenAI-compatible API layer, enabling applications to interface with local models via standardized REST endpoints. Memor
SQL Chat is a Docker-deployed chat interface that translates natural language questions into SQL queries and executes them against connected databases. It uses a large language model to generate SQL from plain English instructions, supporting both querying and record modification through INSERT, UPDATE, and DELETE statements within the chat conversation flow. The application connects to MySQL, PostgreSQL, MSSQL, TiDB Cloud, and OceanBase databases through a unified driver abstraction layer, allowing users to interact with multiple database types from a single chat interface. Users provide the
Actual Budget is an open-source personal finance application that stores all financial data locally on the user's device using a SQLite database, enabling offline access and complete data ownership without cloud dependency. It packages the entire application stack into Docker containers for one-click deployment on any hosting platform with container support, and connects to over 10,000 financial institutions through the Plaid API to automatically sync account balances, transactions, and investment data. The application implements a monthly budget model that tracks spending against category li
This project is a starter template for building secure web services and REST application backends using Node.js, Express, MongoDB, and JSON Web Tokens. It provides a foundation for server-side development, incorporating document mapping for database integration, cryptographic token authentication, and role-based access control. The system features user account administration, automated database seeding and cleanup scripts, dynamic file-based routing, and environment-based configuration management. Security features include brute-force protection through failed login tracking and request activ
Open-event is an open-source event management platform designed to organize conferences and gatherings through centralized backend services, a management REST API, and a responsive web application. The platform provides event lifecycle management tools for organizers to create events, configure tracks, build schedules, manage speakers, coordinate venues, and handle ticket sales. The system includes automated compilation tools that generate custom Android and iOS applications from structured event data packages, delivering offline-capable browsing for attendees. Additionally, it supports stat
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
Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.
Enchanted is a privacy-focused, cross-platform chat frontend for interacting with self-hosted large language models on iOS and macOS. It serves as a native client for communicating with private model servers, specifically providing integration for the Ollama API. The application supports multimodal interactions, allowing users to combine text, image attachments, and voice prompts. It provides tools for local AI model management, including the ability to define persistent system prompts and switch between different models for specific tasks. The interface includes capabilities for rendering m
Isso is a self-hosted commenting system that provides a server and client-side script for adding interactive discussion threads to websites. It functions as an independent platform for managing site-wide comment sections and user profiles on private infrastructure, utilizing a JSON API and a Markdown rendering engine to handle user-generated content. The system is designed to support multi-site comment management, allowing a single server installation to serve independent threads for multiple different domains. It includes a dedicated moderation tool featuring signed URLs and an administrativ
Express es6 rest api is a starter template for building RESTful backend applications using modern JavaScript syntax and standard server routes. It provides a foundational code structure for setting up HTTP routing, middleware parsing, and database models in backend services. The project organizes application routes into modular components and handles incoming HTTP requests cleanly. It includes configuration for cross-origin resource sharing to manage security headers and access controls, enabling web applications on different domains to safely reach backend endpoints.
This is a streamlined Ruby on Rails framework designed for building lightweight backend services and JSON endpoints. It utilizes a model-view-controller architecture to separate data models and business logic from API responses, specifically omitting browser-centric views to reduce system overhead. The framework provides a system for rapidly generating models, controllers, and routes through JSON API scaffolding. It maps HTTP verbs to controllers to ensure consistent resource routing and data modeling for RESTful API backends. The project includes capabilities for HTTP request management, su
This project is a Spring Boot API starter kit and RESTful project skeleton designed for building backend services. It provides a foundational codebase that implements a layered service architecture and standardized directory structures to organize controllers, services, and data mappers. The project features a MyBatis CRUD boilerplate generator that automates the creation of models and controllers from database tables using customizable templates. It includes a security framework for protecting endpoints via interface signature authentication to verify user identity and request authorization.
This backend starter template provides a modular structure for building REST APIs using Node.js, Express, and MongoDB. It includes predefined database models, schema-driven validation, and structured routing to facilitate the development of server-side applications. The application incorporates authentication and security features centered on user registration, login flows, and credential verification. Passwords are protected using cryptographic hashing, and access to protected endpoints is managed through signed token issuance and middleware-based route protection. Additional identity manage
This project is a reference implementation and boilerplate for building RESTful services using the Gin web framework in Go. It provides a structured backend architecture featuring modular routing and middleware to serve as a template for Go web applications. The project distinguishes itself through a comprehensive set of integrated systems, including a security layer for user authentication and private endpoint protection using JSON Web Tokens. It also implements a high-speed memory storage layer via Redis to cache frequent database queries and a containerized runtime environment for consiste
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
Baserow is a no-code relational database and application builder that allows users to create structured data tables and business tools through a visual interface. It functions as a headless REST API data backend and a self-hosted data workspace, providing a platform for managing collaborative databases while maintaining full control over data residency. The platform integrates large language models to serve as an LLM-powered data platform, capable of generating database structures, record content, and technical workflows from natural language. It also acts as a Model Context Protocol server,
This project is a production-ready template for building RESTful APIs using Node.js and the Express web framework. It provides a pre-configured structure for backend services, integrating a MongoDB Mongoose ODM framework for data modeling and a token-based security system for managing user identity. The boilerplate distinguishes itself through automated API documentation generated via Swagger by parsing code comments. It implements a layered controller architecture and a middleware-based request pipeline to separate routing logic from business logic and security processing. The system covers
Rest is a Node.js backend boilerplate and API generator that scaffolds resource-based server applications utilizing Express and Mongoose database models. It provides command-line automation tools to generate complete project directory structures, automated endpoints, and database schemas from the command line. The system incorporates user identity management for account registration, password recovery, and third-party social provider logins alongside query parameter validation against defined rules. It includes collection filtering, sorting, and pagination controls for query endpoints, as wel
This project is a foundational server template built with NestJS designed for creating REST APIs and enterprise backend environments. It provides a pre-configured structure that integrates database connectivity, authentication, and common API services. The boilerplate includes a security system utilizing JSON Web Tokens and role-based access control to manage user sessions and restrict resource access. It supports internationalization for serving content in multiple languages and provides a containerized environment using Docker for consistent deployment. The framework covers a broad range o
novel 是一套基于时下最新 Java 技术栈 Spring Boot 3 Vue 3 开发的前后端分离学习型小说项目,配备保姆级教程手把手教你从零开始开发上线一套生产级别的 Java 系统,由小说门户系统、作家后台管理系统、平台后台管理系统等多个子系统构成。包括小说推荐、作品检索、小说排行榜、小说阅读、小说评论、会员中心、作家专区、充值订阅、新闻发布等功能。
TodoApp is a task management web application designed for organizing and tracking pending items. It consists of a web-based interface and a REST API backend that handles business logic and data requests. The system includes an OAuth 2.0 identity provider for user authentication via passwords and external social providers, as well as an API gateway proxy that routes traffic from the frontend to the backend to prevent cross-origin resource sharing issues. Operational capabilities cover system observability through OpenTelemetry for collecting logs and metrics, request rate limiting to maintain
This project is a headless commerce API and a REST-based gateway that exposes e-commerce business logic and product data to decoupled frontend applications. It provides a centralized system for handling online store operations through a set of commerce interfaces. The platform is designed for large-scale marketplace management, featuring a multi-tenant architecture that isolates data for multiple independent vendors, channels, and warehouses within a single installation. It distinguishes itself with an automated subscription billing system for recurring payment cycles and a tiered pricing eng
CRMEB is a comprehensive e-commerce platform built on ThinkPHP 6, designed as a headless system that delivers standardized APIs to various frontend clients. It provides a unified backend to synchronize product catalogs, orders, and customer data across web browsers, mobile applications, and mini-programs. The platform supports diverse commerce models, including multi-vendor marketplaces where independent merchants manage their own stores, centralized chain store networks, and social commerce frameworks featuring affiliate distribution and community group buying. It also integrates specialized
Dev-Cpp is a comprehensive development suite that serves as a C++ integrated development environment, a cross-platform application builder, and a visual UI designer. It provides a toolchain for writing, compiling, and debugging native C++ applications on Windows, while offering a framework to create native binaries for desktop, mobile, and IoT devices from a single codebase. The project distinguishes itself by integrating an embedded SQL database engine and a REST API development platform directly into the workflow. It includes an AI-assisted coding tool that leverages large language models t
bknd is a self-hosted backend-as-a-service platform and serverless backend framework that provides an integrated environment for managing databases, authentication, and file storage. It functions as a headless CMS and a portable API engine designed to run across various JavaScript runtimes, including Node.js, Bun, Cloudflare Workers, and AWS Lambda. The project distinguishes itself through a combination of schema-driven API generation and a built-in database management UI. It enables the definition of data structures either programmatically via a type-safe API or visually through an administr
PocketPal AI is an on-device LLM chat application for Android that runs small language models locally, enabling private AI conversations without requiring an internet connection. It functions as an offline inference engine that downloads and executes quantized language models directly on the device, with adjustable parameters like temperature and chat templates to control how the AI behaves. The application lets users create custom AI personalities by configuring unique system prompts and contextual settings for different conversational roles. It integrates with the Hugging Face Hub to downlo
deployd is a realtime API framework and MongoDB backend as a service that allows for the creation of networked interfaces synchronizing data and events between clients and servers. It functions as a JavaScript API middleware that can be integrated with HTTP servers to provide authentication, request interceptors, and realtime capabilities. The project features a self-hosted API management dashboard for configuring resource settings, managing data collections, and monitoring server status through a web-based interface. It includes a realtime data synchronization engine that pushes live databas
This project is a self-hosted community engine and forum software designed for hosting threaded discussions. It functions as a JSON API community platform, exposing all data and functionality through a standardized interface to support a single-page application architecture. The system is built to be a multi-language discussion board with integrated localization and language pack support. The platform is defined by a modular architecture that allows for extensive customization through an extension-based plugin system. This extensibility enables the modification of core behavior, the addition