Open-source alternatives to RAGatouille

This project is an educational resource and engineering guide for building, deploying, and optimizing large language model applications and production pipelines. It serves as a blueprint for cloud AI infrastructure, providing a framework for orchestrating inference endpoints, data warehouses, and scalable production environments. The repository provides specific implementation patterns for retrieval augmented generation to ground model responses in external data. It includes a training workflow for crawling, structuring, and processing datasets to facilitate model fine-tuning, alongside an ev

Cube Studio is a cloud-native MLOps platform and Kubernetes-based AI orchestrator designed for the entire machine learning lifecycle. It provides a distributed training framework for large-scale model fine-tuning, a GPU resource manager for hardware virtualization, and an ML pipeline orchestrator that uses visual directed acyclic graphs to manage end-to-end workflows. The platform distinguishes itself through its specialized LLM inference server, which supports retrieval-augmented generation and the construction of private knowledge bases. It features a dedicated system for supervised fine-tu

OpenAgent is an autonomous AI agent framework designed to orchestrate language models and retrieved context to execute complex user goals. It functions as a platform for building autonomous agents that utilize iterative loops to select tools and process information. The project features a multi-model gateway that abstracts various large language model providers, allowing users to switch between models on a per-conversation basis without modifying code. It also includes a RAG knowledge base system that ingests documents and generates embeddings to provide semantic context during inference. Th

This project is an AI-driven phone agent platform and telephony gateway designed to automate inbound and outbound voice interactions. It functions as a conversational voicebot system that utilizes large language models to conduct natural language phone conversations for customer support and data collection. The platform distinguishes itself through the integration of retrieval-augmented generation, allowing voice agents to search internal knowledge bases for domain-specific answers during live calls. It features automated language detection to support multilingual conversations and a system f

Wenda is a self-hosted infrastructure and gateway platform for deploying language models within internal networks to ensure data privacy and security. It functions as a centralized hub and API gateway that unifies communication between various offline model runners and online service providers through a single interface. The platform includes a workflow orchestrator that uses custom scripts and API calls to automate complex conversation flows and model settings. It also incorporates a retrieval system that augments model responses with external knowledge retrieved from vector databases and se

QAnything is a retrieval-augmented generation application framework and self-hosted AI interface. It functions as a system that combines a vector database knowledge base, a document parsing service, and a hybrid search engine to generate answers based on private user data. The project features a modular pipeline architecture that allows users to independently replace components such as parsers, embedding models, and reranking engines. It supports local-first model deployment and offline operation to ensure data privacy, and includes a two-stage retrieval pipeline that merges dense vector embe

This project is a Llama Stack agentic framework and orchestrator used to build autonomous AI applications. It coordinates model inference and tool execution to decompose complex goals into multi-step reasoning chains and continuous inference loops. The framework incorporates a dedicated safety guardrail system that filters model inputs and outputs through safety models to enforce system-level content restrictions. It also includes a tool integration layer that maps model-generated function requests to external runtime definitions to execute actions beyond text generation. The system provides

Streamer-Sales is a digital avatar video generator and large language model sales agent framework. It functions as a multimodal AI pipeline that synthesizes talking-head videos using text-to-speech and face animation to create virtual spokespeople. The system differentiates itself by combining retrieval-augmented generation with agentic web searching to ground product descriptions and sales scripts in factual data and real-time information. It further integrates a multimodal interaction workflow that coordinates automatic speech recognition and text-to-speech for real-time voice conversations

iflow-cli is a command-line interface and suite of AI tools designed for software engineering, workflow orchestration, and multimodal data analysis. It functions as an LLM command line interface that enables users to execute AI workflows, analyze codebase structures, and interact with large language models directly from the terminal. The project features a plugin-based agent architecture that allows for the integration of specialized domain experts and custom instruction sets from an external marketplace. It distinguishes itself through a multimodal AI terminal capable of processing visual da

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

This project is a knowledge base plugin and RAG context manager that uses a local vector database interface to enable semantic search and relationship mapping. It transforms text into numerical vectors to find semantically related notes and excerpts based on conceptual meaning rather than keyword matches. The system differentiates itself through a semantic graph visualizer that maps notes into clusters to reveal conceptual connections. It also features a context manager capable of bundling local notes and excerpts into reusable packs to provide grounded factual bases for large language model

This project is a legal AI system that provides a language model assistant grounded in a retrieval-augmented generation knowledge base. It enables users to perform vector-based legal searches and receive grounded answers to legal questions. The system specifically supports Chinese legal knowledge retrieval by converting markdown documents into vector embeddings for semantic search. It utilizes a streaming web interface that delivers incremental AI responses via server-sent events. The broader capability surface includes chunk-based document processing, vector-based knowledge indexing, and si

LMOps is a research-driven operations framework for optimizing the deployment, fine-tuning, and performance of large language models. It provides a specialized toolkit for foundation model adaptation, inference acceleration, prompt optimization, and context orchestration. The framework distinguishes itself through an inference accelerator that reduces token generation latency by verifying and copying overlapping text spans from reference documents. It also features a prompt engineering optimizer that employs reinforcement learning, beam search, and non-natural language markers to automaticall

CatBoost is a gradient boosting machine learning library used to train decision tree ensembles for regression, classification, and ranking tasks. It functions as a high-performance framework that provides a categorical data processor for transforming non-numeric features, a distributed trainer for large-scale datasets, and GPU acceleration to speed up model construction. The library distinguishes itself through native handling of categorical data and text features, removing the need for manual encoding. It includes a specialized model interpretability tool that leverages SHAP values and featu

OpenGpt is an agent orchestration platform and multimodal interface designed for building and deploying specialized AI personas. It allows users to create task-oriented agents with custom system prompts and behavioral constraints to automate professional, creative, and technical workflows. The project features a prompt engineering workflow that transforms simple user inputs into structured instructions to improve model accuracy. It integrates retrieval-augmented generation by connecting vector databases to the chat interface, enabling context-aware responses from private datasets. The platfo

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

Giskard is an AI quality assurance suite and evaluation framework designed to measure the performance, bias, and security risks of large language models and AI agents. It functions as a vulnerability scanner to detect security flaws and performance regressions. The project provides automated red-teaming and adversarial testing workflows. These tools generate prompt-injection probes and adversarial attacks based on system descriptions to identify security gaps and vulnerabilities. The platform covers AI agent auditing and RAG quality validation, using knowledge-base grounding and synthetic da

ruby_llm is an LLM integration framework and AI agent orchestrator designed to connect applications to multiple large language model providers through a unified interface. It serves as a toolkit for building autonomous assistants with custom personas, managing structured output via JSON schemas, and implementing vector embedding engines for semantic search. The project distinguishes itself as an observability suite and multimodal toolkit. It provides specialized capabilities for tracking token usage, calculating model costs, and tracing workflows via OpenTelemetry, while supporting the proces

OpenGPTs is a platform for building, deploying, and managing customizable AI assistants. It serves as an orchestrator that allows for the configuration of large language models with specific personas, cognitive architectures, and tool integrations. The system provides a complete lifecycle manager for AI agents, enabling the drafting of configurations, testing within sandboxes, and publishing assistants for public or internal distribution. It integrates a knowledge base interface using retrieval-augmented generation to attach documents to bots for context-aware responses. The platform covers

This repository is a collection of guides, notebooks, and recipes for implementing advanced prompting techniques and workflow patterns with large language models. It serves as a prompt engineering guide, an evaluation suite for scoring prompt quality, and a framework for orchestrating agents and integrating external tools. The project provides implementation patterns for building applications with Claude, specifically focusing on coordinating multiple models to split complex tasks between high-reasoning and high-efficiency agents. It includes technical demonstrations for multimodal data proce

mi-gpt is a voice assistant bridge and agent orchestrator that connects smart speakers to large language models. It functions as an integration layer that routes audio requests from hardware speakers to AI providers and converts generated text back into speech via a customizable synthesis system. The project features a retrieval-augmented generation knowledge base that uses embeddings and external documents to provide context-aware responses. It includes a persona definition system for configuring behavioral rules, system prompts, and roleplay characteristics, alongside a plugin architecture

Jeesite is a full-stack low-code development framework designed for building enterprise administrative portals using Spring Boot, MyBatis, and Vue. It functions as a comprehensive platform for creating administrative dashboards with integrated role-based access control and organizational data permission systems. The framework distinguishes itself through a combination of automated CRUD code generation and an integrated RAG platform that connects large language models to enterprise data via vector stores. It further incorporates a BPMN-based workflow engine to automate complex business process

ChatGPT-On-CS is an intelligent customer service automation platform that utilizes large language models to automate interactions across social media and e-commerce platforms. It functions as a bridge connecting these models to external services, providing a unified interface for managing chats from multiple networks and online stores. The platform features a custom knowledge base engine that allows for the creation of private domain AI agents trained on uploaded company documents. It also includes a plugin framework that enables AI agents to access real-time internet data and local operating

Koog is an LLM agent framework used to build autonomous entities that execute tool-based workflows. It utilizes a graph-based workflow engine to define agent behaviors and decision paths as a directed graph of nodes and edges. The framework distinguishes itself through a model provider orchestrator that enables dynamic switching, load balancing, and automatic fallbacks between different AI backends. It implements the Model Context Protocol to connect agents to remote tool servers and features a RAG memory system using vector embeddings to maintain long-term conversation context. The project

PyTorch Metric Learning is an open-source library for training neural networks to produce similarity-preserving embedding spaces. It provides a modular framework where interchangeable loss functions, mining strategies, and evaluation tools can be composed to learn representations that map similar items to nearby points and dissimilar items to distant points in the embedding space. The library distinguishes itself through a highly configurable architecture that separates concerns across several interchangeable components. Users can assemble custom loss functions from pluggable distance metrics

llm-zoomcamp is a comprehensive educational program and course for building real-life AI systems using large language models. It serves as a structured curriculum and implementation guide for developing AI applications and retrieval techniques. The project provides instructional material on building retrieval augmented generation pipelines to ground model responses in custom knowledge bases. It includes training on vector database implementation, semantic search, and the use of function calling to create autonomous agentic workflows. The curriculum covers a broad range of system development

Virgilio is an AI educational roadmap generator and learning path orchestrator designed to structure personalized study trajectories for data science and machine learning. It functions as an AI-driven mentor that organizes educational content into hierarchical levels of abstraction, ranging from high-level introductions to technical tutorials. The system automates curriculum design by mapping technical knowledge into organized levels to ensure a logical progression of study. It manages e-learning journeys by breaking down broad domains into smaller sub-modules, guiding users through necessary