Best AI agents for working with documents (2026)
Tools that let agents read, search and answer questions over your documents and files. We list 62 tools for working with documents below, each with a link-checked page, pricing as the maker states it and alternatives.
Updated
62 tools: 40 open source, 2 source-available, 11 free or freemium, 4 paid, usage-based or enterprise, 5 pricing on the maker's site.
Scraping and crawling (6)
ByteFlow
ByteFlow is a no-code builder for AI agents on top of the systems a company already runs (ERP, CRM, in-house and legacy apps) through APIs or a browser agent. Agents prepare the work, such as a CRM update or ERP entry, and a person approves it with one tap. Includes voice agents in 10+ Indian languages and document extraction.
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
Sparrow
Open-source tool for structured data extraction from documents and images with ML, LLMs and vision LLMs, plus agentic workflows.
Added
Extend MCP
Extend's MCP server for turning documents into structured data: parse, extract, classify, split and fill PDF forms.
Added
LlamaParse
LlamaIndex's document processing platform that parses PDFs, scans and Office files into markdown or JSON and extracts, classifies and indexes them for agents.
Added
Unstract
LLM-powered platform for extracting structured data from documents via APIs and ETL pipelines.
Added
Research and reports (5)
Claude Scientific Writer
K-Dense's general-purpose scientific writing agent for Claude that drafts research papers and documents.
Added
Altmetric MCP
Altmetric's MCP server for tracking research attention across news, policy documents and social media.
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
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
LobsterAI
NetEase Youdao's desktop agent for data analysis, slides, documents and web research.
Added
More tools (51)
OpenKnowledge
OpenKnowledge is a free, local-first markdown editor and knowledge base built for working alongside AI agents. It looks and feels like a Notion-style WYSIWYG editor, with callouts, tabs, Mermaid diagrams and media blocks, but every page stays a plain markdown file on your disk. Coding agents such as Claude Code, Codex, Cursor, Gemini CLI and dozens of others can read and write the same files through its integrations, so specs, team wikis and LLM wikis stay in one place that both people and agents keep up to date. It ships as a desktop app plus a web UI and CLI.
Added
Wren Pre-sign Check
Wren Pre-sign Check is a pay-per-call x402 API that an AI agent calls before it signs anything with its wallet. Send a transaction (to + data), an EIP-712 typed-data payload or untrusted text, and it returns block, review or allow, the decoded call in plain words and every finding: unlimited approvals, Permit and Permit2 signatures, setApprovalForAll, EIP-7702 delegation, contract deployment and injected instructions. With an optional wren-guard policy (allowlist, spenders, caps) it also blocks unknown recipients, over-cap amounts and lookalike addresses. It is a static check and stores nothing you send; free demos show real output.
Added
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.
Added
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.
Added
Bops
Bops, from Orgo, is a Mac app for a team of AI bots that handle business ops such as inbox triage, CRM follow-ups, invoices and reports, each with its own cloud computer, email address, phone number and shared memory.
Added
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.
Added
Pixeltable
Multimodal data layer that combines storage, transforms, indexing and retrieval in one Python library for building agents over images, video and documents.
Added
Dynamiq
Python orchestration framework for building agentic and RAG applications from reusable nodes and workflows.
Added
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.
Added
PPT Master
AI tool that turns documents or topics into native, editable PowerPoint decks with real shapes, charts, transitions and narration from speaker notes.
Added
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.
Added
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.
Added
FastGPT
AI agent building platform with knowledge-base RAG, data processing and a visual workflow editor for deploying question-answering and automation apps.
Added
llmware
Framework for building private, local RAG and agent applications with small specialized models on AI PCs, edge and self-hosted setups.
Added
OpenAgent
Self-hostable personal AI assistant shipped as one binary, combining LLMs, a knowledge base and agent loops with computer, browser and coding use.
Added
5ire
Cross-platform desktop AI assistant and MCP client with a local knowledge base and support for major model providers.
Added
Zep
Context layer that unifies business data, documents and conversations into memory so agents complete tasks correctly.
Added
Knowhere
Document parsing and retrieval system that turns messy files into structured, navigable memory for AI agents and RAG.
Added
Yuanjing Wanwu
China Unicom's enterprise, multi-tenant platform for building agents, workflows and RAG apps with model management.
Added
Ui.Vision RPA
Browser and desktop automation extension with OCR and image recognition, plus an MCP server so AI agents can create and run macros.
Added
Langchain.rb
Ruby library for building LLM-powered applications, RAG and assistants.
Added
Qdrant MCP Server
Official Qdrant MCP server that lets agents store and retrieve memories and documents in the Qdrant vector database.
Added
MemFree
Hybrid AI search engine that answers from your knowledge base and the web, and generates UI pages.
Added
BaseAI
Web AI framework from Langbase for building AI agents with memory (RAG) and deploying them serverless.
Added
Lucid MCP
Lucid's MCP connector for creating, searching, editing and sharing Lucidchart and Lucid documents from AI tools.
Added
PandaDoc MCP
PandaDoc's MCP server for creating, sending, signing and tracking documents from AI assistants.
Added
Guru MCP
Guru's remote MCP server that connects AI tools to your company's Guru knowledge base.
Added
Instinct
Personal assistant you text or call that works across your Gmail, calendar, documents and a cloud browser to get tasks done.
Added
LM Studio
Desktop app for running local and open models, with Bionic, its agent for work and code that creates documents, slides, PDFs and software.
Added
PrintFriendly MCP
PrintFriendly's MCP server for reading clean web pages and creating PDF, Word and Markdown documents.
Added
Studocu MCP
Studocu's MCP server for finding study documents, courses and institutions and managing study projects and quizzes.
Added
Unlayer MCP
Unlayer's MCP server for generating and editing email, page and PDF document templates.
Added
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.
Added
ImageSorcery MCP
Local MCP server that gives AI assistants object detection, OCR, cropping, background removal and drawing tools, running computer vision models on your own machine.
Added
EyePop.ai
SDK-first vision platform where you define what to detect and it builds detection, tracking, OCR and VLM pipelines, with a Video Agent and agent skills, deployable to cloud, edge or on-prem.
Added
Graphify
Turns a codebase plus its docs, SQL schemas, configs and PDFs into a knowledge graph that coding agents can query.
Added
RAGFlow
Open-source RAG engine with deep document parsing and agent features for building grounded question-answering over your files.
Added
AnythingLLM
Local-first desktop and server app for chatting with your documents, running agents and connecting any LLM.
Added
LlamaIndex
Framework for agents over your data (RAG, document agents).
Added
PageIndex
Document index for reasoning-based, vectorless RAG that lets agents navigate long documents like a table of contents.
Added
Chroma
Open-source search and vector database widely used for agent memory and RAG.
Added
Haystack
Open-source orchestration framework for building production LLM apps, RAG and agents.
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
Code-Graph-RAG
Graph-based RAG for monorepos that lets agents query and edit multi-language code.
Added
DocETL
System for agentic, LLM-powered document processing and ETL pipelines from UC Berkeley.
Added
Agentset
Open-source RAG platform for building agents and apps that answer accurately from your documents.
Added
PayPal MCP
PayPal's MCP server for invoices, orders, payments and other PayPal operations from agents.
Added
Accordio AI
Adds time tracking, contract signing, invoicing and payments to Claude through a free MCP connector.
Added
Hebbia
AI platform for finance and legal teams that runs agents across large document sets.
Added
Mastra
TypeScript framework for agents, workflows and RAG.
Added
GitHub repos (49)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| MarkItDown ↗ | 190,824 | MIT | 2026-10-20 |
| Graphify ↗ | 127,237 | Apache License 2.0 | 2026-10-20 |
| RAGFlow ↗ | 92,335 | Apache License 2.0 | 2026-10-21 |
| Understand-Anything ↗ | 87,175 | — | 2026-10-21 |
| AnythingLLM ↗ | 67,210 | MIT | 2026-10-20 |
| PPT Master ↗ | 63,293 | MIT | 2026-10-21 |
| PrivateGPT ↗ | 57,594 | Apache License 2.0 | 2026-10-20 |
| LlamaIndex ↗ | 52,485 | MIT | 2026-10-14 |
| AstrBot ↗ | 42,095 | GNU Affero General Public License v3.0 | 2026-10-21 |
| MindsHub ↗ | 39,800 | MIT | 2026-10-19 |
| PageIndex ↗ | 39,186 | MIT | 2026-10-21 |
| ScrapeGraphAI ↗ | 31,882 | MIT | 2026-10-06 |
| FastGPT ↗ | 29,851 | FastGPT Open Source License (Apache 2.0 with additional conditions) | 2026-10-21 |
| Chroma ↗ | 29,512 | Apache License 2.0 | 2026-10-17 |
| Haystack ↗ | 26,748 | Apache License 2.0 | 2026-10-21 |
Top 15 of 49 by stars. Stars and licence come from each repo, checked when the listing was last verified.
Related tasks
Popular with: Customer support teams · Researchers · Data engineers · Related searches: Open-source AI document and RAG tools
Tools are matched to tasks by category, use cases and what each tool says it does. Missing one? Submit it free.