The best R2R alternatives

haystack

deepset-ai/haystack

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

Choose haystack if…

• Apache License 2.0 suits your use better than MIT License
• you want the more widely starred option (26.9k)
• you want the more recently updated codebase
• you specifically need agent-framework or agentic-ai

Shares large-language-models, python, rag, retrieval-augmented-generation with R2R.

AdalFlow

SylphAI-Inc/AdalFlow

AdalFlow: The library to build & auto-optimize LLM applications.

Choose AdalFlow if…

• you want the more recently updated codebase
• you specifically need agent or ai

Shares python, question-answering, rag with R2R.

LightRAG

HKUDS/LightRAG

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

Choose LightRAG if…

• you want the more widely starred option (40.5k)
• you want the more recently updated codebase
• you specifically need docling or genai

Shares large-language-models, rag, retrieval-augmented-generation with R2R.

code-graph-rag

vitali87/code-graph-rag

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

Choose code-graph-rag if…

• you want something your agent can install directly rather than a library to wire up yourself
• you want the more recently updated codebase
• you specifically need ai or ast

Shares python, rag, retrieval-augmented-generation with R2R.

PocketFlow

The-Pocket/PocketFlow

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

Choose PocketFlow if…

• you want the more recently updated codebase
• you specifically need agentic-ai or agentic-framework

Shares artificial-intelligence, large-language-models, retrieval-augmented-generation with R2R.

headroom

headroomlabs-ai/headroom

Compress 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.

Choose headroom if…

• Apache License 2.0 suits your use better than MIT License
• you want something your agent can install directly rather than a library to wire up yourself
• you want the more widely starred option (78.7k)
• you want the more recently updated codebase

Shares python, rag with R2R.

GenAI-Showcase

mongodb-developer/GenAI-Showcase

MongoDB's Generative AI Showcase: an exhaustive collection of examples and sample applications covering Retrieval-Augmented Generation (RAG), AI agents, and industry-specific use cases.

Choose GenAI-Showcase if…

• you would rather work in Jupyter Notebook than Python
• you want the more recently updated codebase
• you specifically need agents or atlas

Shares artificial-intelligence, python, rag with R2R.

langchain

langchain-ai/langchain

The agent engineering platform.

Choose langchain if…

• you want the more widely starred option (148.9k)
• you want the more recently updated codebase
• you specifically need agents or ai

Shares python, rag with R2R.

mem0

mem0ai/mem0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

Choose mem0 if…

• Apache License 2.0 suits your use better than MIT License
• you want the more widely starred option (68.3k)
• you want the more recently updated codebase
• you specifically need agentic-memory or agentic-memory-system

Shares python, rag with R2R.

langgraph

langchain-ai/langgraph

Build resilient agents.

Choose langgraph if…

• you want the more widely starred option (44.4k)
• you want the more recently updated codebase
• you specifically need agents or ai

Shares python, rag with R2R.

PageIndex

VectifyAI/PageIndex

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Choose PageIndex if…

• you want the more widely starred option (40.0k)
• you want the more recently updated codebase
• you specifically need agentic-ai or agents

Shares rag, retrieval-augmented-generation with R2R.

Langchain-Chatchat

chatchat-space/Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

Choose Langchain-Chatchat if…

• Apache License 2.0 suits your use better than MIT License
• you want the more widely starred option (38.7k)
• you specifically need chatbot or chatchat

Shares rag, retrieval-augmented-generation with R2R.