ragbits and ragflow

RAGFlow is a comprehensive, production-ready RAG engine with integrated agentic capabilities, while ragbits is a lighter-weight modular framework for building RAG applications—they compete for the same use case but at different complexity/maturity tiers.

ragbits
85
Verified
ragflow
72
Verified
Maintenance 23/25
Adoption 18/25
Maturity 25/25
Community 19/25
Maintenance 25/25
Adoption 10/25
Maturity 16/25
Community 21/25
Stars: 1,627
Forks: 136
Downloads: 1,872
Commits (30d): 24
Language: Python
License: MIT
Stars: 74,911
Forks: 8,368
Downloads:
Commits (30d): 243
Language: Python
License: Apache-2.0
No risk flags
No Package No Dependents

About ragbits

deepsense-ai/ragbits

Building blocks for rapid development of GenAI applications

Provides modular Python packages for LLM integration (100+ models via LiteLLM), RAG pipelines with 20+ document formats, and multi-agent coordination using the A2A protocol and Model Context Protocol. Features type-safe prompt execution with Python generics, support for Qdrant/PgVector and other vector stores, Ray-based distributed document ingestion, and OpenTelemetry observability—installable as granular components (core, agents, document-search, evaluate, guardrails, chat, CLI) rather than monolithic framework.

About ragflow

infiniflow/ragflow

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

This tool helps create advanced AI assistants that can accurately answer questions using your specific business documents and data. You input various documents like PDFs, Word files, web pages, and even structured data, and it outputs a system that provides precise, traceable answers. It's designed for business leaders, knowledge managers, or AI product developers who need to build reliable question-answering systems for internal teams or customers.

knowledge-management enterprise-search customer-support-automation business-intelligence document-intelligence

Scores updated daily from GitHub, PyPI, and npm data. How scores work