Retrieval Augmented Generation: open-source projects on GitHub
85 repositories on Retrieval Augmented Generation, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
RAGFlow — RAG Engine with Agents
Open system for building intelligent RAG pipelines with agent capabilities — builds high-quality context for LLM.
★ 80,605 · PythonReady LLM templates
Ready cloud templates for RAG, AI‑pipeline, and search with live data, Docker‑compatible and synchronized with SharePoint, S3, Kafka, and PostgreSQL.
★ 59,750 · Jupyter NotebookREADY DOCKER TEMPLATES RAG
Ready-to-run cloud templates for RAG, AI‑pipeline and enterprise search with live data. Docker support, sync with SharePoint, Google Drive, S3, Kafka, PostgreSQL and APIs
★ 58,707 · PythonChatBot on LangChain
A local RAG application on LangChain for working with LLMs (ChatGLM, Qwen, Llama) with agent support and loading of custom knowledge.
★ 38,014 · PythonLightRAG: Fast RAG
A simple and fast framework for Retrieval-Augmented Generation, optimized for high performance and ease of use.
★ 35,143 · PythonVectorless RAG Index
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
★ 32,176 · PythonAdvanced RAG Techniques
The repository demonstrates various advanced methods for Retrieval-Augmented Generation (RAG) systems with detailed tutorials in Jupyter Notebook format.
★ 27,523 · Jupyter NotebookHaystack: AI Framework for LLM
An open framework for building production-ready LLM applications with modular control over search, routing, memory, and generation.
★ 25,289 · MDXAI Agent Memory File
Replaces complex RAG pipelines with a serverless memory layer for AI agents, enabling instant search.
★ 15,579 · RustLLMware: RAG framework
Unified framework for building corporate RAG pipelines using compact specialized models.
★ 14,860 · PythonTXTAI — AI All-in-One
An algorithmic framework for semantic search, LLM orchestration, and language-model workflows. All in one!
★ 12,620 · PythonFLAGEMBEDDING: SMART SEARCH
Project for efficient retrieval and retrieval-augmented generation on Python. Supports fast search and integration with LLM.
★ 12,323 · PythonLEANN - FAST RAG ON PHONE
LEANN lets you run private RAG on your personal device, saving up to 97% of space while delivering high accuracy.
★ 11,845 · PythonLEANN: RAG for everything
LEANN — fast and accurate RAG application with 97% storage savings, running fully on your device with complete privacy.
★ 11,392 · PythonPocketFlow - 100 Lines of Agents
A minimalist 100-line framework for building LLM agents that create other agents.
★ 11,322 · PythonLocal Deep Search
Achieves ~95% accuracy on SimpleQA, works with any local and cloud LLMs and more than 10 search engines, all encrypted and local.
★ 7,516 · PythonAIRWEAVE: AI AGENTS GITHUB CONTEXT
Open context extraction layer for AI agents. Python tool with 6K+ stars!
★ 6,379 · PythonRAG FOR MONOREPOS
AI tool for understanding and editing multilingual codebases through knowledge graphs. 2274 ⭐
★ 5,354 · PythonAutoRAG: RAG System Automation
An open-source framework for automatic evaluation and optimization of RAG pipelines in an AutoML style.
★ 4,804 · PythonBRAG-LANGCHAIN: YOUR RAG
A complete set of tools and examples for building RAG applications in Jupyter Notebook. A quick start and deep understanding.
★ 4,202 · Jupyter NotebookGENERATIVE AI MICROSERVICE WORKFLOW
A collection of generative AI examples optimized for accelerated infrastructure and microservices architecture. Ready-to-use Jupyter notebooks for a quick start.
★ 4,037 · Jupyter NotebookLANGRID - Multi-agent AI for Code
A simple framework for building LLM-based agents with memory and tool support.
★ 4,029 · PythonFASTEMBED: FAST EMBEDDINGS IN PYTHON
The fastembed library provides ultra-fast and accurate embeddings for text and images, ideal for RAG and LLM applications.
★ 3,294 · PythonSWIRL-SEARCH - FAST AI SEARCH
Get instant answers from corporate data in 100+ apps without moving the information.
★ 3,050 · PythonGenerative AI Roadmap Projects
A collection of generative AI resources: roadmap, projects, interview and coding preparation.
★ 2,670 · Jupyter NotebookAwesome-GraphRAG: Best RAG Resources
A collection of materials on graph RAG: articles, surveys, benchmarks, and open-source projects.
★ 2,424VEARCH: Vector Search for AI
Vearch is a distributed vector search system built on Go, optimized for AI applications and scalable in the cloud.
★ 2,334 · GoNESTIA - AI ASSISTANT FOR NESTJS
Nestia simplifies NestJS application development by providing ready‑to‑use utilities and integrating an AI chatbot for rapid prototyping.
★ 2,182 · TypeScriptSUPERLINKED INFERENCE ENGINE
Open-source server for embedding inference, reranking, and data extraction. 2000+ stars on GitHub.
★ 2,029 · PythonRAGHUB: Resources and RAG Frameworks
The community gathers the best RAG frameworks, projects, and materials for AI developers. Contribute and discover new solutions.
★ 2,019WFGY 5.0 POLARIS PROTOCOL
WFGY 5.0 — major open-source release for AI reasoning, RAG, agents and real-world workflows. 1752 ⭐
★ 1,752 · Jupyter NotebookMEMORYOS — MEMORY FOR AI AGENTS
MemoryOS provides a memory operating system for personalized AI agents, learning from their interactions.
★ 1,622 · PythonAwesome AI Web Search
A collection of the best web tools where AI helps search the web faster and more accurately.
★ 1,519 · HTMLAWESOME-RAG: BEST RAG APPLICATIONS
Curated list of the best Retrieval-Augmented Generation projects in Generative AI. 1284 stars ⭐
★ 1,429AWESOME-LLM-RAG: BEST RAG SOLUTIONS
A collection of the best resources and libraries for building Retrieval Augmented Generation in large language models.
★ 1,374RAGLITE - FAST RAG ON DUCKDB
Simple tool for building RAG pipelines with DuckDB or PostgreSQL in Python.
★ 1,212 · PythonRAG-RETRIEVAL UNIFY SEARCH
The project unifies efficient fine-tuning of RAG search methods: embeddings, ColBERT, and reranker.
★ 1,138 · PythonJAMAIBASE AI TABLE FOR TEAM
A table where cells are combined into AI pipelines, allowing experimentation with prompts and models in real time.
★ 1,103 · PythonCHROMEM-GO: VECTOR DB WITH ZERO DEPENDENCIES
Embeddable vector DB in pure Go. Chroma-like API, zero external deps, runs in-memory with optional persistence.
★ 1,078 · GoFASTEMBED-RS: FAST EMBEDDINGS IN RUST
Rust library for local embedding creation and reranking. Fast inference with support for popular models.
★ 1,053 · RustFLASHRANK: SUPER-FAST RE-RANKING
Lightning-fast re‑ranking for search and retrieval pipelines based on LLMs and cross‑encoders. Supports SOTA listwise and pairwise ranking.
★ 1,015 · PythonVISRAG: RAG WITHOUT PARSING
VisRAG provides RAG without text parsing, using VLMs to directly extract knowledge from images and documents.
★ 991 · PythonLOCAL_PDF_CHAT_RAG - PDF CHAT RAG
A simple Python RAG with hybrid FAISS+BM25 search, reranking, and a Gradio + FastAPI UI.
★ 961 · PythonRAG-FUSION: IMPROVEMENT OF RETRIEVAL
RAG-Fusion generates multiple queries and combines their results via Reciprocal Rank Fusion, improving search quality for RAG systems. The package includes evaluation on
★ 961 · PythonSERVERLESS AI CHAT ON AZURE
Template to deploy serverless RAG chatbot on Azure Functions. Uses LangChain.js and TypeScript. Production-ready in minutes.
★ 870 · TypeScriptNVIDIA'S RAG PIPELINE
NVIDIA's reference implementation of Retrieval Augmented Generation — a full RAG pipeline for accurate AI answers from your data.
★ 823 · PythonRust + LLM: Indexing Speed
Swiftide — fast streaming indexing and queries for AI agents on Rust. 710⭐ and growing.
★ 806 · RustOntology‑Driven AI Generation
Adds external ontologies to LLM prompts, enabling AI agents to generate fact‑grounded, domain‑specific outputs.
★ 804 · PythonLOCAL-RAG: RAG WITHOUT DATA LEAK
Ingest files for RAG with an open-source LLM — everything runs locally, with no third‑party services and no data leaving your network.
★ 768 · PythonRAGLight modular RAG framework
A flexible framework for Retrieval-Augmented Generation in Python. Support for various LLMs, embeddings, vector stores, and seamless integration with MCP.
★ 674 · PythonAI PARTNER WITH TERMINAL FORWARD CODING
agentty — a static binary AI pair‑programming assistant for the terminal. It starts in sub‑millisecond and works with any LLM, including Claude via API.
★ 623 · C++VOICE RAG WITH AZURE OPENAI
VoiceRAG implementation example for interactive voice AI. Uses Azure AI Search and gpt-4o-realtime-preview for real-time search and generation. Ready-to-deploy template v
★ 567 · PythonASKIMO: AI CHAT CLIENT
askimo is a universal AI client in Kotlin with support for chat, RAG, plans, and agents through multiple model providers.
★ 549 · KotlinMULTIMODAL RAG SURVEY
Comprehensive survey of multimodal RAG methods: from retriever architectures to generation strategies. 545 stars on GitHub. Perfect for topic entry.
★ 545AWS CDK FOR GENERATIVE AI
AWS CDK construct library for building generative AI solutions. Ready-made patterns for quick start.
★ 544 · TypeScriptAWESOME-RAG: RESOURCE LIBRARY
A curated collection of resources on Retrieval-Augmented Generation for LLMs. Perfect for developers working with RAG technologies.
★ 521CONTINUOUS-EVAL - LLM EVALUATION ON DATA
Platform for automatic evaluation of LLM applications based on real data. Enables measuring quality and improving models without manual effort.
★ 519 · PythonMANIFOLD: AGENTS FOR AUTOMATION
Manifold is an experimental platform where teams of AI assistants automate complex multi-task processes. Written in Go and has already gained 498 stars.
★ 503 · GoREDIS-VL-PYTHON - VECTOR LIBRARY FOR AI
RedisVL is a Python client for working with vector data in Redis, simplifying the creation of AI applications and similarity search.
★ 437 · PythonRAG System for GitHub Issues
RAG over GitHub issues with hand-reviewed eval set and judge audit. Reports confidence intervals, not just point metrics.
★ 419 · PythonNew projects on this topic in Telegram
Telegram →