Chat with your own documents: AnythingLLM, from Mintplex Labs, wraps retrieval-augmented generation (RAG) in an open-source application anyone can run. You organize content into workspaces, each an isolated namespace with its own documents, vector embeddings, chat history, and settings, so one instance can hold several separate knowledge bases. Upload PDFs, DOCX, TXT, and other formats, or scrape web pages; the built-in collector parses and chunks them into a vector database (LanceDB by default, with Pinecone, Chroma, Qdrant, and others supported). Answers cite their source documents. It works with both cloud LLMs (OpenAI, Anthropic, Gemini) and local ones via Ollama or LM Studio, and the embedding model is separately configurable. Beyond RAG chat, it includes AI agents that can browse the web and run tools, an embeddable chat widget for your website, a developer API, and multi-user mode with admin, manager, and default roles plus per-workspace access control. Context assembly is smarter than naive RAG: pinned documents, attached files, vector search hits, and recent chat history are combined under a token budget so the model's context window is filled efficiently, and each workspace supports multiple independent conversation threads against the same knowledge base. Because the embedding model, vector store, and chat LLM are all independently swappable, you can move between providers without re-ingesting a single document. The stack is Node.js with a React frontend, MIT-licensed.

Kotaemon is a document QA platform that combines advanced RAG techniques with a clean Gradio-based web interface for chatting with your documents. Built by Cinnamon, the Python backend supports any LLM provider including OpenAI, Azure OpenAI, Cohere, Groq, and local models via Ollama and llama-cpp-python, with a model management panel for configuring LLM and embedding providers from the UI. The default hybrid RAG pipeline combines full-text keyword retrieval with vector similarity search and applies re-ranking to ensure optimal result quality, while multi-modal document parsing extracts content from tables and figures alongside text. Advanced citations link every answer to specific source passages with relevance scores, viewable directly in the built-in PDF viewer with highlighted text spans. GraphRAG indexing via NanoGraphRAG, LightRAG, or Microsoft GraphRAG builds knowledge graphs from document collections for relationship-aware retrieval. Agent-based reasoning supports question decomposition for multi-hop queries using ReAct and ReWOO strategies. Multi-user authentication organizes documents into private and public collections with sharing and collaboration features. The platform supports Docker deployment in lite, full, and Ollama-bundled variants, runs on port 7860, and stores application data in a persistent volume. MCP tool integration enables external system connections for extended retrieval capabilities. On RepoCloud, deploy Kotaemon on a dedicated VPS with Docker, root SSH access, and complete control over your document AI infrastructure, all under the Apache 2.0 license.

RAGFlow has established itself as one of the most widely adopted open-source RAG engines available, powering production AI systems that demand traceable, hallucination-free answers from complex enterprise data. The platform processes PDF, DOCX, Excel, and PPT files through vision-based deep document understanding with layout analysis and OCR, extracting structured knowledge from tables, charts, and images that simpler parsers miss entirely. RAGFlow's hybrid retrieval pipeline combines vector search with BM25 keyword matching and multi-stage reranking across configurable document stores including Elasticsearch, InfiniFlow's Infinity engine, OpenSearch, and OceanBase. Developers connect any combination of LLM providers — OpenAI, DeepSeek, Anthropic Claude, Google Gemini, and locally-hosted models via Ollama — through a unified configuration layer. The visual agent workflow system enables multi-step reasoning chains with persistent memory, tool calling, and pre-built templates for common enterprise scenarios. RAGFlow synchronizes data from Confluence, S3, Notion, and Google Drive, and delivers answers through chat integrations with Feishu, Discord, Telegram, and Line. The Python SDK and RESTful API on port 9380 provide programmatic access to knowledge base management, document parsing, and conversational retrieval. The full stack deploys via Docker Compose with MySQL for metadata, Redis for task orchestration, and MinIO for object storage. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

With 2,600+ GitHub stars since its May 2026 open-source launch, Knowhere solves the last-mile problem of document intelligence for AI systems — transforming complex unstructured PDFs, reports, and multi-page documents into structured JSON chunks that LLMs can consume without hallucination. The platform processes documents through an AI-native parsing pipeline that handles 20+ page documents with deep hierarchies, intricate tables, and multimodal content including images with OCR, achieving 95% precision in information extraction while reducing token costs by 50% compared to raw document ingestion. The knowledge tree architecture maintains historical context across multiple documents, enabling cross-document graph navigation for agentic retrieval that goes beyond simple chunk-based RAG. Built on Python 3.11+ with MinerU as the default PDF parser, the backend API runs alongside async workers that process document ingestion, graph construction, and embedding generation. The self-hosted Docker Compose stack packages the API server, processing workers, and Next.js dashboard for managing API keys, webhooks, and document-processing jobs, backed by PostgreSQL and Redis. Both Python and Node.js SDKs provide programmatic access for integration into existing AI pipelines and agent frameworks. LLM providers include DeepSeek and Alibaba Cloud DashScope with configurable key rotation for rate-limit management. Deploy on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Your documents change every day, and your RAG answers should change with them: Serviette keeps a chat and REST API continuously in sync with the files you point it at, no re-indexing jobs to remember. Point it at a local folder, Google Drive, S3 or MinIO bucket, SharePoint library, or even an FTP or WebDAV share, and edits, additions, and deletions flow into the index in real time. One YAML file, or the interactive wizard, chooses among eight vector databases, from embedded DuckDB with zero setup to pgvector, Qdrant, Milvus, Chroma, Weaviate, Pinecone, or MongoDB Atlas. Text, Office files, PDFs with tables, and scanned images are parsed and answerable by default, with audio and video joining when you add the keys. Embeddings can run fully locally with no credentials, and keyless answers simply quote the retrieved passages with their sources. The indexer and the stateless server scale independently, the server shards across workers with one config line, and both a ChatGPT-style web chat and a versioned /api/v1 retrieval API answer on the same port. A free license key from Pathway activates the engine, and benchmarks cover corpora up to 50 GB of text. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Retrieval-augmented chatbots on your own knowledge base - that is the whole mission of Dialoqbase, an open-source bot-building platform. Feed it content through a broad set of data loaders - web pages and full crawls, sitemaps, PDFs, DOCX, CSV, plain text, GitHub repositories, YouTube videos, and MP3/MP4 audio - and it handles the whole RAG pipeline in one self-contained app: chunking, embedding, vector storage, and LLM querying. The distinguishing architecture choice is PostgreSQL with pgvector for embedding storage and similarity search, which removes the separate vector-database dependency, and Redis-backed Bull queues for ingesting large documents without blocking the API. Model choice is wide open: OpenAI, Anthropic Claude, Google Gemini, Cohere, Fireworks, Hugging Face, local models via Ollama, and any OpenAI-compatible endpoint, with an equally broad list of embedding providers. Finished bots embed on any website with customizable styling or deploy to Telegram, Discord, and WhatsApp, and an API creates and manages bots programmatically. Multi-user support adds registration limits and per-user bot quotas. MIT-licensed and free for commercial use.

Receipts, contracts, and letters that arrive as pixels rather than text: Papermerge is a document management system built specifically for scanned documents. Upload a PDF, TIFF, JPEG, or PNG and OCR runs automatically, with a real-time status indicator beside the document title; under the hood it drives OCRmyPDF and Tesseract, supporting 130+ languages and producing a new document version with a selectable, searchable text layer you can download. Full-text search runs across everything, with multiple search-engine backends (Xapian by default). The interface deliberately mimics a modern desktop file browser: dual-panel commander, drag and drop, hierarchical folders, and colored tags on documents and folders. Page management fixes what scanners get wrong - delete blank pages, rotate, reorder, merge, extract, and move strayed pages between documents, powered by PikePDF. Document types act as categories, each with its own custom metadata fields, so invoices carry vendor and amount while contracts carry parties and dates. Versioning preserves every state of a document. Multi-user support includes groups, group ownership, permission management, and document/folder sharing between users and groups, and an OpenAPI-compliant REST API automates ingestion from scanners or scripts. Apache-licensed, ideal for long-term digital archives.

A pile of paper becomes a searchable digital archive under Paperless-ngx, the community-maintained document management system. The pipeline is what makes it work: drop a file into the consumption folder (or let it poll an email inbox), and a worker hashes it for duplicate detection, routes it by type, runs OCRmyPDF with Tesseract (100+ languages) on anything without a text layer, and produces an archivable PDF/A with invisible selectable text embedded - so Ctrl+F works on your scans. Then the smart part: a scikit-learn classifier (TF-IDF plus multi-label prediction) trained on your own tagged documents automatically assigns tags, correspondents, and document types to new arrivals, alongside rule-based exact, keyword, and regex matching for deterministic cases. Full-text search includes relevance ranking, match highlighting, autocomplete, and "more like this" similarity search. Apache Tika integration extends consumption to Word, Excel, PowerPoint, and LibreOffice formats. The Django/Angular app adds custom fields, saved views on a customizable dashboard, bulk editing, workflow automation triggered on upload or matching, shareable public links with expiration, and a robust permissions system with per-document access control. Metadata lives in PostgreSQL with Redis-queued Celery workers processing documents in parallel. Your tax records, invoices, and contracts stay on your server - searchable in seconds, never in someone else's cloud.

Convert paper archives, email attachments, and PDF records into an organized digital repository with Docspell, an open-source document management system that automates optical character recognition, metadata extraction, and full-text search. Users can ingest receipts and invoices through network scanners, monitored IMAP email mailboxes, mobile uploads, or drag-and-drop browser tools. The background processing pipeline executes optical character recognition via Tesseract, enhances image contrast with unpaper, and extracts text from Word documents and PDFs. Machine learning algorithms analyze document syntax to predict correspondents, suggest relevant organization tags, and identify due dates automatically. Team members can search their entire filing cabinet using complex Boolean queries and full-text indexing powered by Apache Solr or PostgreSQL. Administrators can configure multi-user collectives with isolated permissions, define custom metadata attributes, set up webhooks, and share time-limited document download links. Users can also merge multi-page scans, track processing job queues, and export curated document collections for tax filings or legal audits. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GNU AGPL v3.0 licensed.

Every scan and PDF you drop into Teedy becomes searchable text in a self-hosted document archive, filed by nested tags instead of folders. OCR reads images in more than twenty languages, and the search box offers suggestions and highlights matches, even inside ODT, DOCX, and PPTX files. Video files are supported as well. Each record carries Dublin Core fields plus custom metadata of your own design, with comments and earlier file versions attached. When a document needs a second pair of eyes, workflow steps with assigned reviewers move it along in order until someone signs off. Pull in EML emails, let the server poll an inbox, or point the bulk importer at a whole folder, and incoming paperwork needs no manual filing. Share a single document through a public link, or keep it behind user and group permissions with a storage quota for each person. LDAP and two-factor authentication guard sign-in, 256-bit AES encryption protects stored files, and an audit log records who changed what. Webhooks alert other services, a documented REST API lets scripts take part, and an Android client carries the archive on a phone. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-2.0 licensed.

Adobe Acrobat and Smallpdf, answered by a self-hosted Java web application: Stirling PDF processes every file with its 60+ tools on your own server and deletes it after the task completes. Nothing is uploaded to a third party, which is the whole point for contracts, invoices, and medical records. The toolbox covers page operations (merge, split at page numbers or scanned dividers, rotate, reorder, crop, extract), conversion in both directions between PDF and Word, Excel, PowerPoint, images, HTML, and Markdown, OCR that turns scans into searchable PDFs via Tesseract/OCRmyPDF (including PDF/A archival conversion), and security tools for passwords, permissions, watermarks, signatures, and true UI-driven text redaction. A built-in viewer handles annotation, drawing, and text or image insertion, and V2 added stateful processing - upload once, chain multiple tools - plus undo/redo history. For automation, nearly every tool has a REST API endpoint, no-code pipelines combine operations into custom logic chains, and watched folders process files automatically. Enterprise deployments get SSO, user management, and audit logging; the interface ships in 40+ languages. With 84K+ GitHub stars it is the most popular PDF tool in self-hosting, replacing $20/month Acrobat subscriptions with flat infrastructure cost.

Contracts signed on your own server: DocuSeal is the most feature-complete open-source, self-hosted alternative to DocuSign. A WYSIWYG builder turns any PDF into a fillable form with 14 field types: signature, initials, date, file upload, checkbox, dropdown, radio, stamp, and more. Documents route to multiple submitters in sequence or parallel, with automated SMTP email notifications, reminders, and a mobile-optimized signing experience that works on any device without an account. Every completed document carries an automatic PDF eSignature with verification and an audit trail. Templates are reusable and can also be generated programmatically - from HTML via API or from PDFs and DOCX files with embedded field tags - and the REST API plus webhooks drive full workflow automation, with embedded signing forms and form builders for React, Vue, Angular, and plain JavaScript. Files store on disk or in S3, Google Cloud Storage, or Azure. The UI ships in 7 languages with signing in 14. Runs on SQLite, PostgreSQL, or MySQL; AGPL-3.0 licensed with unlimited documents and no per-signature fees.

With 6,700 GitHub stars, 79 releases, and 40 contributors since its October 2023 launch, OpenSign delivers a fully free electronic signature platform that removes the per-envelope pricing and seat limits of commercial e-signing services. The React-based frontend provides a drag-and-drop interface for placing signature fields, initials, date stamps, text inputs, and checkboxes onto PDF documents, while the Parse Server backend built on Node.js handles document routing through configurable multi-signer workflows with sequential or parallel signing order. Guest signers authenticate via one-time-password email verification without requiring account creation, while registered users manage documents through OpenSign Drive — a centralized vault with folder organization and status tracking across draft, in-progress, completed, and declined states. Every signing action generates tamper-proof audit trails logging timestamps, IP addresses, email addresses, and phone numbers, culminating in a detailed completion certificate attached to the finished document. The REST API v1.2 exposes endpoints for document creation, template dispatch, self-signing, and real-time webhook notifications on document lifecycle events, with regional deployments available in US and EU. PDF templates with pre-placed widgets enable repeated dispatch to different signers in a single API call. Custom branding controls email invitation templates, signing page appearance, and completion certificate styling. Deploy via Docker Compose with MongoDB, Caddy reverse proxy, and automatic HTTPS provisioning. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3 licensed.

Thesys is a research workspace where you search academic papers, build your own library, and ask questions that answer with citations you can click straight onto the highlighted passage of the PDF. Discovery searches OpenAlex and arXiv in one pool, so a paper you find can be previewed and added to your library without leaving the workspace. Uploaded PDFs are ingested locally, and when you ask a question the answer cites its sources in the document, jumping the preview to the retrieved passage with either a full-passage or a tighter focused highlight. Reader mode opens a paper full-width so you can select any span of text and ask about that exact passage. Document summaries follow a consistent structure of problem statement, methodology, key findings, limitations, and metrics, with citations that still land on the source text. Figures and flowcharts are described during ingest, so questions and summaries can reference them too. When two papers disagree, Compare mode takes one claim and classifies each retrieved pair as corroboratory, contradictory, or neutral, with confidence shown in a side panel. Your bibliography exports as BibTeX, RIS, EndNote, or CSV for whatever reference manager you already use. Papers, embeddings, and chat history stay on your own disk the whole time. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

A private ChatGPT built with Next.js: Lobe Chat is the open-source AI chat interface teams self-host instead. Its main advantage is provider breadth: one interface connects to 40+ model providers, including OpenAI, Anthropic Claude, Google Gemini, Mistral, Groq, AWS Bedrock, Azure, and local models served through Ollama, so you can switch models per conversation and compare outputs. It handles multi-modal work: image recognition, image generation, text-to-speech, and speech-to-text. A plugin system based on function calling and the Model Context Protocol (MCP) adds external tools like web search and code execution. Run it in standalone mode as a single container with settings in browser storage, or in database mode with PostgreSQL and S3-compatible storage for persistent history, multi-user auth, and RAG knowledge bases built from uploaded documents with pgvector retrieval. Because tools arrive through function calling and MCP rather than a proprietary plugin format, custom internal tools can be exposed to the assistant with a standard server over STDIO or HTTP. Hundreds of pre-configured assistant roles import from the community marketplace. For teams the cost model matters: provider API keys billed per token typically undercut a ChatGPT Plus seat per person, and self-hosting keeps API keys, uploaded files, embeddings, and conversation history entirely on your own server.