Free AI document and RAG tools (2026)

AI document and RAG tools that you can use without paying: open-source projects plus tools with a free plan. Here are the top 25 of 39 from the AgentScout directory.

How we picked and ranked: tools are matched by category, the pricing each maker states and what each tool says it does. They are ranked by GitHub stars as recorded on each listing (link checks 2026-10-18); tools without a tracked repo follow, by listing maturity. No paid placements.

1. M

   1. MarkItDown

   MCP & infraOpen source★ 190,824 GitHub stars

   Microsoft's Python tool and MCP server that converts PDFs, Office documents, images, audio and web pages to Markdown for LLM and agent pipelines.

   Pricing (as stated): Open source · Mature

2. G

   2. Graphify

   codingOpen source★ 127,237 GitHub stars

   Turns a codebase plus its docs, SQL schemas, configs and PDFs into a knowledge graph that coding agents can query.

   Pricing (as stated): Open source · Mature

3. R

   3. RAGFlow

   frameworksOpen source + cloud★ 92,335 GitHub stars

   Open-source RAG engine with deep document parsing and agent features for building grounded question-answering over your files.

   Pricing (as stated): Open source + cloud · Mature

4. C

   4. Crawl4AI

   browser/computer useOpen source★ 85,667 GitHub stars

   Open-source crawler that turns websites into clean, LLM-ready Markdown for agents and RAG pipelines.

   Pricing (as stated): Open source · Mature

5. H

   5. Headroom

   MCP & infraOpen source★ 75,629 GitHub stars

   Library, proxy and MCP server that compresses tool outputs, logs, files and RAG chunks locally before they reach the LLM, cutting tokens for coding agents.

   Pricing (as stated): Open source · Mature

6. A

   6. AnythingLLM

   personal agentsOpen source + cloud★ 67,210 GitHub stars

   Local-first desktop and server app for chatting with your documents, running agents and connecting any LLM.

   Pricing (as stated): Open source + cloud · Mature

7. P

   7. PPT Master

   productivityOpen source★ 63,293 GitHub stars

   AI tool that turns documents or topics into native, editable PowerPoint decks with real shapes, charts, transitions and narration from speaker notes.

   Pricing (as stated): Open source · Mature

8. C

   8. Context7

   MCP & infraFreemium★ 63,157 GitHub stars

   MCP server and platform that feeds coding agents up-to-date, version-specific library documentation.

   Pricing (as stated): Freemium · Mature

9. P

   9. PrivateGPT

   frameworksOpen source★ 57,594 GitHub stars

   Open-source API layer that turns local models into private AI applications, with RAG, tools, skills, MCP and text-to-SQL on any OpenAI-compatible server.

   Pricing (as stated): Open source · Mature

10. L

    10. LlamaIndex

    frameworksOpen source + cloud★ 52,485 GitHub stars

    Framework for agents over your data (RAG, document agents).

    Pricing (as stated): Open source + paid cloud · Mature

11. A

    11. AstrBot

    frameworksOpen source★ 42,095 GitHub stars

    Open-source agent chatbot platform and framework that connects LLMs, plugins and tools to mainstream messaging apps for assistants, support bots and knowledge bases.

    Pricing (as stated): Open source · Mature

12. M

    12. MindsHub

    productivityOpen source + cloud★ 39,800 GitHub stars

    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.

    Pricing (as stated): Open source + cloud · Mature

13. P

    13. PageIndex

    frameworksOpen source + cloud★ 39,186 GitHub stars

    Document index for reasoning-based, vectorless RAG that lets agents navigate long documents like a table of contents.

    Pricing (as stated): Open source + cloud · Mature

14. D

    14. DSPy

    frameworksOpen source★ 38,676 GitHub stars

    Stanford framework for programming rather than prompting language models, with optimizers that tune prompts and weights for RAG pipelines and agent loops.

    Pricing (as stated): Open source · Mature

15. S

    15. ScrapeGraphAI

    browser/computer useOpen source + cloud★ 31,882 GitHub stars

    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.

    Pricing (as stated): Open source + cloud · Mature

16. C

    16. Chroma

    MCP & infraOpen source + cloud★ 29,512 GitHub stars

    Open-source search and vector database widely used for agent memory and RAG.

    Pricing (as stated): Open source + cloud · Mature

17. H

    17. Haystack

    frameworksOpen source + cloud★ 26,748 GitHub stars

    Open-source orchestration framework for building production LLM apps, RAG and agents.

    Pricing (as stated): Open source + cloud · Mature

18. O

    18. Opik

    evals & observabilityOpen source + cloud★ 22,700 GitHub stars

    Comet's open-source platform for tracing, evaluating and monitoring LLM apps, RAG systems and agent workflows, self-hosted or in the cloud.

    Pricing (as stated): Open source + cloud · Mature

19. L

    19. llmware

    frameworksOpen source★ 14,814 GitHub stars

    Framework for building private, local RAG and agent applications with small specialized models on AI PCs, edge and self-hosted setups.

    Pricing (as stated): Open source · Mature

20. L

    20. LanceDB

    MCP & infraOpen source + cloud★ 11,684 GitHub stars

    Open-source multimodal vector database for search, RAG and agent memory.

    Pricing (as stated): Open source + cloud · Mature

21. A

    21. Activeloop

    MCP & infraOpen source + cloud★ 9,252 GitHub stars

    Deep Lake, a multimodal database for AI that stores vectors, images, text and video so agents and RAG apps can search and retrieve them.

    Pricing (as stated): Open source + cloud · Mature

22. U

    22. Unstract

    no-code buildersOpen source + cloud★ 7,285 GitHub stars

    LLM-powered platform for extracting structured data from documents via APIs and ETL pipelines.

    Pricing (as stated): Open source + cloud · Mature

23. C

    23. Craft Agents

    productivityOpen source★ 7,262 GitHub stars

    Desktop app from the makers of Craft for working with agents in a document-first way; the agent sets up APIs and MCP servers for you and sessions can be shared.

    Pricing (as stated): Open source · Mature

24. L

    24. LobsterAI

    personal agentsOpen source★ 6,119 GitHub stars

    NetEase Youdao's desktop agent for data analysis, slides, documents and web research.

    Pricing (as stated): Open source · Mature

25. U

    25. UltraRAG

    frameworksOpen source★ 5,729 GitHub stars

    Low-code MCP-based framework from OpenBMB for building and debugging complex RAG pipelines with visible reasoning logic.

    Pricing (as stated): Open source · Mature

FAQ

What are the best free AI document and RAG tools?

Ranked by tracked GitHub stars, the top free AI document and RAG tools in our directory are MarkItDown, Graphify, RAGFlow, Crawl4AI, Headroom. Stars measure popularity, not fit, so compare a few against your own task.

How many free AI document and RAG tools does AgentScout list?

39 tools match. This page shows the top 25. Pricing mix on this page: Open source (12), Open source + cloud (12), Freemium (1).

Are these tools really free?

Pricing is what each maker states on their site. Open-source tools are free to self-host but may need a paid model API key or offer paid cloud plans; freemium tools have a free plan with limits. Check each official site.

Where can I see every tool for working with documents?

Our task page lists all 59 tools we match to working with documents.

Related: All tools for working with documents · frameworks (13) · MCP & infra (9) · research (3) · personal agents (3)

By role: For customer support teams · For researchers

All popular searches · AI agents by role · Free tools

Best-of lists: RAGFlow alternatives · All best lists

Facts come from our directory listings; pricing is as each maker states it and can change. Check official sites before you choose.