Open Source RAG Projects
Discover 59 open source RAG repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. RAG projects here are most often combined with Python, AI Agents and LLM. Last updated October 4, 2026.
59 repositories · updated October 4, 2026
kotaemon: Chat with Documents Using RAG
kotaemon is a customizable web interface and toolkit for asking questions about documents with retrieval-augmented generation. It suits teams that want a self-hosted document QA app or developers building and adapting RAG pipelines.
data-prep-kit: Prepare Data for LLM Applications
Data-Prep-Kit is a toolkit for cleaning, transforming, and enriching unstructured data used in LLM training and RAG pipelines. It offers reusable transforms that run with Python or Ray, from local experiments to larger-scale processing.
rag-web-ui: Build Knowledge-Base Q&A with RAG
RAG Web UI is a self-hostable web application for creating question-answering systems over your own documents. It combines document ingestion, vector search, and configurable cloud or local language models, with a web interface and OpenAPI access.
marmot: Replicate SQLite Across Distributed Nodes
Marmot is a Go database server that replicates SQLite across nodes and accepts connections through the MySQL protocol. It suits read-heavy, multi-region and edge deployments that can tolerate eventual consistency.
openapi-servers: Expose Tools to AI Agents Through OpenAPI
openapi-servers provides FastAPI reference servers for connecting AI agents and workflows to external tools and data through standard REST APIs. Use its examples to build or host services such as filesystem, Git, weather, SQL, and RAG tools.
ComfyUI-Copilot: Add AI Assistance to ComfyUI Workflows
ComfyUI-Copilot is a custom node that helps ComfyUI users create, debug, and revise image-generation workflows with AI assistance. It is useful for creators and developers who want workflow support and parameter tuning inside ComfyUI.
53AIHub: Manage AI Agents, Knowledge, Prompts, and Tools
53AIHub is an AI portal for organizations that want to publish and operate agents, prompts, tools, and knowledge bases in one place. It connects to platforms such as Coze, Dify, FastGPT, and RAGFlow, with options for cloud or self-hosted deployment.
MaxKB: Build and Run Enterprise AI Agents
MaxKB is a self-hostable platform for building AI agents that use company knowledge, workflows, and external tools. It suits teams that want to add model-backed question answering to internal or customer-facing systems.
AnyCrawl: Crawl Websites and Extract LLM-Ready Data
AnyCrawl is a TypeScript toolkit for scraping individual pages, crawling sites, processing batches of URLs, and extracting structured data with LLMs. It suits developers building data pipelines for AI applications who need browser rendering or parallel processing.
memvid: Store Persistent AI Memory in a Single File
Memvid is a Rust-based memory layer that stores content, search indexes, and metadata in a portable .mv2 file. It suits developers building agents that need local, persistent retrieval without operating a separate database service.
SurfSense: Create Source-Grounded Briefings from Local Documents
SurfSense is a desktop research assistant that indexes documents on your machine, answers questions with citations, and generates study and work materials. It suits users who need document analysis without uploading their files to a hosted service.