Open-source AI document and RAG tools (2026)
AI document and RAG tools with public source code you can read, self-host and extend. Here are the top 25 of 40 from the AgentScout directory.
Updated
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 2026-10-21); tools without a tracked repo follow, by listing maturity. No paid placements.
1. MarkItDown
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. Graphify
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. RAGFlow
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. Understand-Anything
Turns any codebase, knowledge base or docs folder into an interactive knowledge graph you can explore and question, working inside Claude Code, Codex, Cursor, Copilot and Gemini CLI.
Pricing (as stated): Open source · Mature
5. AnythingLLM
Local-first desktop and server app for chatting with your documents, running agents and connecting any LLM.
Pricing (as stated): Open source + cloud · Mature
6. PPT Master
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
7. PrivateGPT
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
8. LlamaIndex
Framework for agents over your data (RAG, document agents).
Pricing (as stated): Open source + paid cloud · Mature
9. AstrBot
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
10. 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.
Pricing (as stated): Open source + cloud · Mature
11. PageIndex
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
12. 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.
Pricing (as stated): Open source + cloud · Mature
13. Chroma
Open-source search and vector database widely used for agent memory and RAG.
Pricing (as stated): Open source + cloud · Mature
14. Haystack
Open-source orchestration framework for building production LLM apps, RAG and agents.
Pricing (as stated): Open source + cloud · Mature
15. llmware
Framework for building private, local RAG and agent applications with small specialized models on AI PCs, edge and self-hosted setups.
Pricing (as stated): Free and open source (Apache-2.0) · Mature
16. LanceDB
Open-source multimodal vector database for search, RAG and agent memory.
Pricing (as stated): Open source + cloud · Mature
17. xerj
A local-first search engine and MCP server for agents: one Rust binary indexes code, docs, logs, CSV/JSONL and PDFs for full-text, vector and hybrid search plus agent memory, behind an Elasticsearch-compatible API.
Pricing (as stated): Free Community edition (Apache-2.0); paid Professional and Enterprise support. · Mature
18. 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.
Pricing (as stated): Open source + cloud · Mature
19. Universal Modder
Skills, tools and a shared knowledge base that let Claude Code and other coding agents mod PC games you own, from engine recon to in-game testing.
Pricing (as stated): Open source · Mature
20. Unstract
LLM-powered platform for extracting structured data from documents via APIs and ETL pipelines.
Pricing (as stated): Open source + cloud · Mature
21. Craft Agents
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
22. LobsterAI
NetEase Youdao's desktop agent for data analysis, slides, documents and web research.
Pricing (as stated): Open source · Mature
23. OpenAgent
Self-hostable personal AI assistant shipped as one binary, combining LLMs, a knowledge base and agent loops with computer, browser and coding use.
Pricing (as stated): Open source · Mature
24. Code-Graph-RAG
Graph-based RAG for monorepos that lets agents query and edit multi-language code.
Pricing (as stated): Open source · Mature
25. Sparrow
Open-source tool for structured data extraction from documents and images with ML, LLMs and vision LLMs, plus agentic workflows.
Pricing (as stated): Open source · Mature
FAQ
What are the best open-source AI document and RAG tools?
Ranked by tracked GitHub stars, the top open-source AI document and RAG tools in our directory are MarkItDown, Graphify, RAGFlow, Understand-Anything, AnythingLLM. Stars measure popularity, not fit, so compare a few against your own task.
How many open-source AI document and RAG tools does AgentScout list?
40 tools match. This page shows the top 25. Pricing mix on this page: Open source (14), Open source + cloud (11).
How much do these tools cost?
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 62 tools we match to working with documents.
Related: All tools for working with documents · memory & RAG (12) · frameworks (8) · productivity (4) · coding (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
Related categories: Memory & RAG · Frameworks · Coding · Personal agents · Productivity
Facts come from our directory listings; pricing is as each maker states it and can change. Check official sites before you choose.