AI tools for research: RAG and documents
Retrieval tools that let agents search documents, PDFs and knowledge bases and answer from them (RAG). Of the 147 tools on our research page, 18 fit this narrower job. By pricing: 12 open source, 2 free or freemium, 1 paid, usage-based or enterprise, 3 pricing on the maker's site. The most-starred open repos here are Crawl4AI (85,667 stars), MindsHub (39,800 stars), ScrapeGraphAI (31,882 stars). Most come from the MCP & infra (9), research (4), browser/computer use (2) categories.
Crawl4AI
Open-source crawler that turns websites into clean, LLM-ready Markdown for agents and RAG pipelines.
Added
MindsHub
MindsDB's agent workspace for research, analysis, documents and coding, with a model router, a scoped vault for connected data and swappable open-source agent harnesses.
Added
ScrapeGraphAI
Python library that uses LLMs and graph logic to build scraping pipelines: describe the data you want and it extracts it from websites or documents.
Added
Chroma
Open-source search and vector database widely used for agent memory and RAG.
Added
txtai
All-in-one Python framework for semantic search, LLM orchestration and agents built on an embeddings database of vector, graph and relational indexes.
Added
LanceDB
Open-source multimodal vector database for search, RAG and agent memory.
Added
Activeloop
Deep Lake, a multimodal database for AI that stores vectors, images, text and video so agents and RAG apps can search and retrieve them.
Added
LobsterAI
NetEase Youdao's desktop agent for data analysis, slides, documents and web research.
Added
SimpleMem
Research-backed lifelong memory library for LLM agents that stores, compresses and retrieves text and multimodal memories, usable over MCP.
Added
seekdb
AI-native search database for agent storage combining vector, text and structured data.
Added
Claude Scientific Writer
K-Dense's general-purpose scientific writing agent for Claude that drafts research papers and documents.
Added
MemFree
Hybrid AI search engine that answers from your knowledge base and the web, and generates UI pages.
Added
Ref
Token-efficient documentation search for coding agents.
Added
Lucid MCP
Lucid's MCP connector for creating, searching, editing and sharing Lucidchart and Lucid documents from AI tools.
Added
Altmetric MCP
Altmetric's MCP server for tracking research attention across news, policy documents and social media.
Added
Brandfetch MCP
Brandfetch's MCP server for searching brands and retrieving logos, design assets and company data.
Added
Google Deep Review
Google Research's multi-agent system that checks research papers, design docs, and legal or financial documents for logical gaps and unsupported claims.
Added
Hebbia
AI platform for finance and legal teams that runs agents across large document sets.
Added
GitHub repos (14)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| Crawl4AI ↗ | 85,667 | Apache License 2.0 | 2026-10-15 |
| MindsHub ↗ | 39,800 | MIT | 2026-09-10 |
| ScrapeGraphAI ↗ | 31,882 | — | — |
| Chroma ↗ | 29,512 | Apache License 2.0 | 2026-10-17 |
| txtai ↗ | 13,024 | — | — |
| LanceDB ↗ | 11,684 | Apache License 2.0 | 2026-10-16 |
| Activeloop ↗ | 9,252 | Apache License 2.0 | 2026-05-21 |
| LobsterAI ↗ | 6,119 | MIT | 2026-10-16 |
| SimpleMem ↗ | 3,836 | — | — |
| seekdb ↗ | 3,157 | Apache License 2.0 | 2026-10-16 |
| Claude Scientific Writer ↗ | 2,491 | — | — |
| MemFree ↗ | 1,515 | — | — |
| Ref ↗ | 1,183 | MIT | 2026-09-28 |
| Lucid MCP ↗ | 3 | — | — |
14 repos. Stars and licence come from each repo, checked when the listing was last verified.
FAQ
What are the best AI tools for research focused on RAG and documents?
We list 18. The first three by GitHub stars and featured status are Crawl4AI: Open-source crawler that turns websites into clean, LLM-ready Markdown for agents and RAG pipelines.; MindsHub: MindsDB's agent workspace for research, analysis, documents and coding, with a model router, a scoped vault for connected data and swappable open-source agent harnesses.; ScrapeGraphAI: Python library that uses LLMs and graph logic to build scraping pipelines: describe the data you want and it extracts it from websites or documents.
Are there free or open-source options?
Yes: 12 open source, 2 free or freemium, 1 paid, usage-based or enterprise, 3 pricing on the maker's site. Pricing is as each maker states it.
More from research
Tools are grouped by what each says it does. Missing one? Submit it free.