Projects sharing features with Serge

This project is an agentic retrieval-augmented generation platform and orchestration framework designed to connect large language models to private enterprise data. It serves as a self-hosted AI gateway that integrates vector databases and external tools to automate complex information retrieval and generation tasks. The system differentiates itself through an AI agent workflow builder that orchestrates multiple specialized agents with distinct roles to solve multi-step problems. It includes a dedicated vector database integration interface for indexing private documents and a secure sandbox

This is an educational training course that teaches Docker, Compose, Swarm, and Kubernetes for building and deploying containers from development to production. The course covers end-to-end Docker-based workflows for building, testing, and deploying containers using Compose, Swarm, and Kubernetes in cloud-native DevOps pipelines. The material covers architecture patterns for containerized applications, including declarative service orchestration, network bridging, image layering, health monitoring, and persistent storage across Docker and Kubernetes environments. It addresses multi-container

This project is an Ansible-based deployment tool that automates the setup of a fully configured Matrix homeserver using Docker containers. It orchestrates the entire Matrix server stack, including the homeserver itself, a PostgreSQL database, and reverse proxy integration with Traefik for automatic SSL certificate management, all from a single configuration file. The deployment supports connecting a Matrix installation to external messaging platforms like Discord, Slack, Telegram, and WhatsApp through dedicated bridges that run as isolated Docker containers. It also provides the ability to de

This project is a collection of curated deployment examples, manifests, and templates for running diverse applications and workloads on a Kubernetes cluster. It serves as a manifest library and a set of educational resources used to teach fundamental configuration patterns for container orchestration. The repository provides pre-configured templates for common architectural patterns, including the deployment of distributed databases, artificial intelligence models, and production-ready web servers. These resources include guided tutorials and verification commands to help users learn Kubernet

LazyLLM is a multi-agent framework and orchestration engine designed for building complex AI applications. It provides a system for chaining large language models into sequential or parallel pipelines, utilizing a tool registry to convert standard functions into discoverable tools that models can invoke via reasoning. The project features an application deployment kit that enables hosting model workflows as web services with integrated chat interfaces and API gateways. It includes an infrastructure abstraction layer that allows users to switch between bare-metal servers, clusters, and public

This is a distributed voting application designed to demonstrate a multi-service architecture. It uses stateless web frontends for submitting votes and viewing live results, with a Redis-backed queue to buffer incoming votes and a PostgreSQL database for persistent tallying. The application is built around asynchronous message queue processing, decoupling the vote submission from the tallying workflow. The project showcases how to deploy a multi-service application using container orchestration tools. It provides YAML-driven declarative deployment manifests for Docker Compose, Docker Swarm, a

Kimai is an open-source time tracking system that records employee working hours, manages absences, and generates professional invoices from recorded timesheets and expenses. It organizes all time records through a mandatory three-level hierarchy of customer, project, and activity, and supports project budget monitoring with configurable time and money limits. The application is extensible through a plugin system that allows adding custom features, invoice templates, reporting views, and dashboard widgets without modifying core files. It provides a RESTful JSON API for programmatic read and w

PiggyMetrics is a demonstration project that illustrates a complete microservice architecture built with Spring Boot, Spring Cloud, and Docker, centered around a personal finance tracking application. It records incomes, expenses, and savings for individual accounts while computing spending statistics and time-series data to track cash flow dynamics over time. The project showcases a full Spring Cloud service mesh, including an API gateway for request routing, service discovery for dynamic instance location, and a centralized configuration server that manages application settings from a singl

The simplest way to run LLaMA on your local machine

WasmEdge is an extensible WebAssembly runtime that executes WebAssembly bytecode in a secure sandbox for cloud, edge, and embedded applications. It functions as a multi-language compiler, compiling applications written in Rust, JavaScript, Go, and Python into WebAssembly bytecode for sandboxed execution, and as a server-side JavaScript runtime that runs JavaScript programs with ES6 modules, NPM packages, and Node.js-compatible APIs. The runtime also serves as an AI inference runtime, executing AI models from JavaScript using WASI-NN plug-ins for inference tasks on personal devices and edge har

eShopOnContainers is a .NET microservices reference application designed to demonstrate cloud-native architecture patterns. It serves as a sample distributed system that implements domain-driven design and utilizes containerized services. The project is developed as a cross-platform sample compatible with Windows, Linux, and macOS. It utilizes Docker for containerized application deployment and supports orchestration via Azure Kubernetes Service to manage the scaling and availability of its services. The system covers microservices architecture design, asynchronous service communication, and

Colanode is a local-first collaboration platform designed for shared documents, chat, and databases. It provides a self-hosted suite for team collaboration and knowledge management, allowing users to maintain full control over their data and privacy on their own infrastructure. The platform is distinguished by a synchronization engine that uses WebSockets for real-time data broadcasting and a local-first approach to ensure work continues offline. It incorporates AI-powered retrieval through vector-based semantic search, enabling users to find information based on meaning across documents and

Weblate is an open-source web-based translation management system that provides a collaborative platform for teams to review, suggest, and approve translations in real time. It functions as a continuous localization platform, automatically synchronizing translations with source code changes in version control repositories, and can be deployed either as a self-hosted server or through a managed cloud hosting service. The system integrates directly with Git hosting platforms like GitHub, GitLab, and Bitbucket, storing all translations in version control with individual translator attribution re

Multica is an autonomous coding agent manager and LLM agent orchestration platform. It coordinates teams of autonomous agents to execute coding tasks and manage their lifecycles through a centralized dashboard. The system provides multi-tenant agent workspaces that isolate agents, settings, and project issues into distinct organizational boundaries. The platform distinguishes itself through an agent skill library that captures successful task solutions as reusable, versioned skills. These skills are shared across the agent team and pinned using content hashes to ensure consistent behavior acr

Octelium is a zero-trust network access platform and identity-aware proxy designed to secure private HTTP, SSH, and SQL resources. It functions as a secure gateway that validates human and workload identities using OIDC, SAML, and FIDO2 passkeys before granting access to internal applications and SaaS APIs. The system is distinguished by its secretless access broker, which injects credentials—such as API keys, passwords, and AWS Sigv4 signatures—at the gateway level so users can access databases and cloud resources without managing secrets. It further specializes in AI gateway administration,

Ollama provides a framework for running and managing local machine learning models. It includes a command-line interface for model lifecycle management, such as creation, embedding generation, and configuration, alongside a stable API for programmatic interaction across multiple programming languages. The platform supports the import of models and adapters in various formats, including GGUF and Safetensors. Users can define custom model behaviors, prompt templates, and system messages through a configuration file format. It also offers tools for fine-tuning models with LoRA adapters and apply

OpenLLM is a framework for deploying, managing, and scaling open-source large language models

Guidance is a control framework and generation orchestrator for large language models. It provides a programming layer to steer model outputs through structured templates, schema enforcement, and logical flow management. The framework distinguishes itself by interleaving model generation with local code execution, enabling the use of loops and conditional branching within a single session. It employs grammar-based token constraints and regular expressions to force models to sample only from tokens that satisfy a specific structural format, ensuring strict adherence to predefined data models.

Promptfoo is an evaluation framework designed for testing, benchmarking, and red-teaming language models and agentic workflows. It provides a unified environment to run prompts against multiple providers, allowing developers to systematically validate model outputs against objective assertions, semantic similarity metrics, and custom grading rubrics. The platform distinguishes itself through a provider-agnostic execution layer and a stateful orchestrator capable of simulating multi-turn conversations and complex tool-use trajectories. It includes a dedicated adversarial mutation pipeline that

Evals is a framework designed for automating, managing, and executing repeatable benchmarking suites to analyze the quality and performance of language models. It provides a platform for running standardized tests to measure model accuracy and track behavioral changes over time. The system distinguishes itself through a modular architecture that uses a standardized adapter layer to normalize inputs and outputs, allowing different models to be swapped and tested interchangeably. It supports the creation of custom benchmarks using proprietary data, enabling quality assurance on sensitive tasks

PyTorch is a machine learning framework centered on a GPU-ready tensor library that supports multi-dimensional array operations across both CPU and accelerator hardware. It provides a foundational infrastructure for mathematical computation and dynamic neural network construction, utilizing a tape-based automatic differentiation system that allows for flexible, non-static graph execution. The framework is designed for deep integration with Python, enabling natural usage alongside standard scientific computing ecosystems. It distinguishes itself through a comprehensive distributed training sui

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

TensorFlow is a comprehensive machine learning framework designed for the construction, training, and deployment of complex mathematical models. It utilizes a graph-based execution model that represents operations as directed acyclic graphs, enabling automatic differentiation and efficient parallel processing. The system provides high-level interfaces for defining neural network architectures, alongside a robust engine for managing multidimensional array structures and tensor mathematics. The framework distinguishes itself through a scalable distributed runtime that orchestrates workloads acr

Dify is an open-source platform for building, orchestrating, and deploying generative AI applications and autonomous agents. It provides a visual development environment that allows users to design complex, multi-step logic chains and conversational flows, which can then be published as APIs, web interfaces, or embedded widgets. The platform acts as a centralized infrastructure layer, managing model connections, prompt templates, and knowledge retrieval to support scalable AI-powered services. What distinguishes the platform is its focus on stateful application design and workflow orchestrati

ColossalAI is a distributed deep learning framework designed for training and deploying massive artificial intelligence models across clusters of hardware accelerators. It functions as a parallel computing engine that partitions model workloads and data across multiple processors to maximize memory efficiency and throughput. The platform distinguishes itself through a comprehensive suite of parallelization strategies, including multi-dimensional tensor parallelism and pipeline-based model parallelism, which segment neural network layers and stages across devices. To support large-scale genera

This repository serves as an educational framework for building large language models from the ground up. It provides a structured curriculum that guides learners through the end-to-end lifecycle of model development, including data processing, architecture design, and optimization. By focusing on low-level implementation, the project enables users to master the fundamental mechanics of artificial intelligence without relying on high-level abstraction frameworks. The project distinguishes itself by constructing neural network components and gradient-based optimization logic from first princip

Chinese-Vicuna is a Chinese large language model and instruction-following AI based on the LLaMA architecture. It is specifically designed for natural language understanding and generation in the Chinese language, utilizing an instruction-tuned model to follow complex user prompts across conversations. The project provides a LoRA fine-tuning framework and quantization systems to enable model adaptation and inference on consumer hardware. It implements quantized inference to reduce memory usage on both CPUs and GPUs, supported by a low-level C++ implementation to minimize system resource requi