PageIndex alternatives

VectifyAI/PageIndex (39k stars, +63 this week): 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG. Why it matters: relevant for grounding LLMs in your own data.

Below are 8 other RAG / vector repos tracked by OSS Radar that share at least two GitHub topics with PageIndex, ordered by how many topics overlap, then by stars gained in the last 7 days. Topic overlap means a similar problem space, not a drop-in replacement, so check each project's README.

1. 1. infiniflow/ragflow

   +294/wkest.

   RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a… Why it matters: relevant for grounding LLMs in your own data.

   92k stars · Go · shared topics: agentic-ai, ai, ai-agents, context-engineering, rag, retrieval-augmented-generation

2. 2. NirDiamant/RAG_Techniques

   +84/wkest.

   A collection of runnable notebook tutorials covering techniques for building Retrieval-Augmented Generation (RAG) systems. Why it matters: relevant for grounding LLMs in your own data.

   30k stars · Jupyter Notebook · shared topics: ai, llm, rag, retrieval-augmented-generation, vector-database

3. 3. cocoindex-io/cocoindex

   +74/wkest.

   Incremental engine for long horizon agents 🌟 Star if you like it! Why it matters: relevant for grounding LLMs in your own data.

   12k stars · Rust · shared topics: ai, ai-agents, context-engineering, llm, rag

4. 4. HKUDS/LightRAG

   +77/wkest.

   [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation. Why it matters: relevant for grounding LLMs in your own data.

   40k stars · Python · shared topics: llm, rag, retrieval-augmented-generation

5. 5. HKUDS/DeepTutor

   +343/wkest.

   DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/. Why it matters: relevant for grounding LLMs in your own data.

   41k stars · Python · shared topics: ai-agents, rag

6. 6. deeplethe/utopia

   +109/wkest.

   World's first open-source enterprise world model. Why it matters: relevant for grounding LLMs in your own data.

   8.4k stars · Rust · shared topics: llm, rag

7. 7. opendataloader-project/opendataloader-pdf

   +81/wkest.

   PDF Parser for AI-ready data. Automate PDF accessibility. Open-source. Why it matters: relevant for grounding LLMs in your own data.

   30k stars · Java · shared topics: ai, rag

8. 8. cdcailf/cjkfold

   +77/wkest.

   Fold look-alike CJK glyphs (Kangxi radicals, CJK radical supplements) so text extracted from PDFs matches again. Why it matters: relevant for grounding LLMs in your own data.

   125 stars · Python · shared topics: rag, retrieval

More: all trending RAG / vector repos · compare PageIndex with the top 2