The most-starred RAG repositories on GitHub
RAG (Retrieval-Augmented Generation) is a method where the system first retrieves relevant passages from your documents, and only then does the model answer based on what was retrieved. The answer rests on your organisation's data, not only on what the model remembers. This list covers RAG frameworks, vector databases and document-processing tools. It ranks repositories tagged rag on GitHub.
Refreshed every day. Ranked by GitHub stars on the day of the update.
- Updated
- Source
- GitHub search API
- Repositories ranked
- 15
The 15 most-starred repositories
- Rank 1
open-webui/open-webui
158,341 starsUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
- Language:
- Svelte
- Opened:
- Last update:
- ai
- llm
- llm-ui
- llm-webui
- llms
- mcp
- Rank 2
langchain-ai/langchain
149,338 starsThe agent engineering platform.
- Language:
- Python
- Opened:
- Last update:
- agents
- ai
- ai-agents
- anthropic
- chatgpt
- deepagents
- Rank 3
Graphify-Labs/graphify
145,743 starsTurn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
- Language:
- Python
- Opened:
- Last update:
- ai-agents
- antigravity
- ast
- claude-code
- code-analysis
- code-search
- Rank 4
Shubhamsaboo/awesome-llm-apps
144,387 stars100+ AI Agents, Agent Skills and RAG Apps, Free and Open Source.
- Language:
- Python
- Opened:
- Last update:
- agents
- llms
- python
- rag
- Rank 5
thedotmack/claude-mem
115,910 starsPersistent Context Across Sessions for Every Agent, Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
- Language:
- TypeScript
- Opened:
- Last update:
- ai
- ai-agents
- ai-memory
- anthropic
- artificial-intelligence
- chromadb
- Rank 6
infiniflow/ragflow
93,990 starsRAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
- Language:
- Go
- Opened:
- Last update:
- agent-harness
- agent-native-database
- agentic-ai
- agentic-retrieval
- agentic-search
- ai
- Rank 7
PaddlePaddle/PaddleOCR
92,550 starsTurn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- Language:
- Python
- Opened:
- Last update:
- ai4science
- chineseocr
- document-parsing
- document-translation
- kie
- ocr
- Rank 8
unclecode/crawl4ai
87,197 starsOfficial Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.
- Language:
- Python
- Opened:
- Last update:
- ai
- ai-agents
- crawl4ai-cloud
- crawler
- data-extraction
- llm
- Rank 9
datawhalechina/hello-agents
86,647 starsBuilding Agents from Scratch, A tutorial on agent principles and practice from scratch
- Language:
- Python
- Opened:
- Last update:
- agent
- llm
- rag
- tutorial
- Rank 10
dair-ai/Prompt-Engineering-Guide
79,977 starsGuides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
- Language:
- MDX
- Opened:
- Last update:
- agent
- agents
- ai-agents
- chatgpt
- deep-learning
- generative-ai
- Rank 11
headroomlabs-ai/headroom
79,324 starsCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
- Language:
- Python
- Opened:
- Last update:
- agent
- ai
- anthropic
- claude-code
- compression
- context-engineering
- Rank 12
mem0ai/mem0
68,777 starsThe Memory Layer for AI Agents, Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
- Language:
- Python
- Opened:
- Last update:
- agentic-memory
- agentic-memory-system
- agents
- ai
- ai-agents
- chatgpt
- Rank 13
Mintplex-Labs/anything-llm
68,163 starsStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
- Language:
- JavaScript
- Opened:
- Last update:
- agent-computer
- agent-harness
- agent-orchestration
- agentic-ai
- agentic-workflow
- ai-agents
- Rank 14
pathwaycom/serviette
58,713 starsA no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.
- Language:
- Python
- Opened:
- Last update:
- chromadb
- document-qa
- document-search
- duckdb
- live-data
- llm
- Rank 15
HKUDS/DeepTutor
58,056 starsDeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
- Language:
- Python
- Opened:
- Last update:
- ai-agents
- ai-tutor
- clawbot
- cli-tool
- deepresearch
- interactive-learning