RAG / retrieval-augmented generation
RAGFlow is an open-source RAG engine that combines retrieval-augmented generation with agent capabilities to provide a self-hosted context layer for LLMs.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose it when you want a Tencent-backed full-stack RAG platform with autonomous agents and wiki in Go.
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Choose it when you need a REST-first agentic RAG backend with lightweight deployment instead of a full UI platform.
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose it when you need ready-to-run templates with live data connectors instead of a self-hosted platform.
Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.
Choose it when you want an API-only private RAG layer for local models rather than a full UI/agent platform.
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
Choose it when you want a lightweight embeddable RAG library for research or simple apps.
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
Choose it when you need graph-based global sense-making over large corpora instead of a full RAG engine.
A modular graph-based Retrieval-Augmented Generation (RAG) system
Choose it when you want vectorless, reasoning-based indexing to reduce storage and cost.
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Choose it when you need a modular all-in-one framework to assemble custom RAG pipelines.
"RAG-Anything: All-in-One RAG Framework"
Choose it when you need a broader semantic search/LLM orchestration framework that can include RAG.
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Choose it when you want on-device, storage-efficient private RAG with lower resource use.
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Choose it when you want to build custom RAG pipelines with explicit control over components in Python.
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
It is a local deep-research app for end users, not an embeddable RAG engine.
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
It is a deep-research application over private data, not a RAG library.
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
These projects were analysed and named ragflow among their alternatives. The relationship is not symmetric — how ragflow rates them is a separate judgement, made when ragflow is analysed in its own right.
calls ragflow “when you want a full RAG engine with UI and agent support”
Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.
calls ragflow “Choose for a leading open-source RAG engine with agent capabilities and a server-based deployment.”
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
calls ragflow “Choose if you need a robust, feature-rich RAG server with deep document understanding and a UI.”
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
calls ragflow “Choose it when you prefer a document-heavy RAG engine with a web UI over a connector-first search API.”
Open-source context retrieval layer for AI agents
calls ragflow “Choose when you want a full-featured RAG engine with an agent layer and web UI, deployable as a service.”
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
calls ragflow “Choose it when you want a self-hosted RAG engine with document management UI and APIs.”
A modular graph-based Retrieval-Augmented Generation (RAG) system
calls ragflow “Choose when you want a deployable RAG engine with a UI and agent capabilities; it runs as a service, not as a library you embed.”
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
calls ragflow “Full RAG engine with UI/API; choose when you want a deployed production RAG server instead of embedding a library.”
"RAG-Anything: All-in-One RAG Framework"
calls ragflow “Choose when you want a full-featured RAG engine with a web UI for document management and human-in-the-loop workflows.”
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
calls ragflow “Choose if you want a full RAG platform with UI/API, not an in-process library.”
Unified framework for building enterprise RAG pipelines with small, specialized models
calls ragflow “Choose when you want a ready-to-run RAG engine with GUI and document management.”
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
calls ragflow “Choose when you want a full-featured RAG engine with UI, deep document parsing, and agent capabilities rather than a library.”
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
calls ragflow “Choose for a self-hosted RAG engine with UI and agent features, not a framework to embed.”
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.