ragbits and Awesome-RAG-Reasoning
A practical framework for building RAG applications complements a curated collection of reasoning techniques and research resources that inform architectural decisions within those applications.
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 Awesome-RAG-Reasoning
DavidZWZ/Awesome-RAG-Reasoning
[EMNLP 2025] Awesome RAG Reasoning Resources
Curates papers, benchmarks, and implementations across three integration patterns: reasoning-enhanced RAG (optimizing retrieval and generation), RAG-enhanced reasoning (grounding with external knowledge), and synergized systems using iterative retrieval-reasoning loops. Organizes taxonomy covering chain/tree/graph-based workflows, single/multi-agent orchestration, and tool-using approaches within agentic AI frameworks. Provides evaluation resources spanning single/multi-hop QA, fact-checking, summarization, and domain-specific tasks alongside code implementations.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work