When the connection drops, Project NOMAD keeps serving offline Wikipedia, Khan Academy courses, maps, and an optional private AI assistant from a single Debian-based Linux server. The core needs only about 5 GB of disk and under 1 GB of RAM. Content is what fills the drive, and a setup wizard sorts it into Essential, Standard, and Comprehensive tiers while a storage bar tracks the running total. Wikipedia runs from a quick-reference set of the top 100,000 articles to the complete English edition with images at about 121 GB, and Kiwix also serves medical references, survival and repair guides, and Project Gutenberg ebooks. Kolibri adds Khan Academy courses with multi-user progress tracking, and any browser on the network can study. Offline maps cover the whole globe, single countries, or regions, with markers you can search, color, and navigate to by coordinate. The AI assistant is the heavy part, bringing the install to roughly 25 GB. It chats through Ollama or any OpenAI-compatible server such as LM Studio, searches uploaded documents, lists sources with dates when known, and lets vision models read attached images. CyberChef handles encoding and hashing, and FlatNotes keeps Markdown notes. The Supply Depot adds one-click apps or your own Docker containers. Opt-in auto-updates for the Command Center, installed apps, and downloaded content run inside a window you set. 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.

Websites such as Wikipedia, Project Gutenberg, and Stack Overflow pack into single ZIM files, and Kiwix Serve publishes a folder of them as a searchable library that opens in any browser, with no connection to the originals. Point it at individual files, a directory, or a library file, and visitors get a welcome page where they filter books by language, category, or words in the title and description. Each book opens in a built-in viewer without downloading the archive, with toolbar buttons for the library, a random article, and in-book search. Title suggestions appear as you type, and full-text search returns highlighted snippets from indexed books, across several at once when they share a language. OPDS catalogs let reader apps browse and fetch the collection, and the library reloads automatically when its file changes. Admins can swap in a custom welcome page, publish under a URL prefix, hide the library button or search box, block links that leave the archive, and cap connections per visitor. Interface translations cover dozens of languages. Universities, community networks, and home labs get a reference shelf that stays available when the original sites are slow, blocked, or gone, with developer documentation and Q&A always within reach. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

OpenNotebookLM is a self-hosted research workspace that reads your sources with you, answering questions only from the material you gave it and showing the passage behind every claim. Import papers, spreadsheets, recordings, web pages, PDF links, YouTube videos or playlists, Markdown folders, Obsidian vaults, and Git repositories, then select which sources the chat may use as evidence. Stream answers with follow-up questions, hover any numbered citation to inspect the supporting passage and page, and let the app flag citations that look unsupported before you trust them. The Studio turns the same sources into cited reports in briefing, study guide, FAQ, or timeline formats, expandable mind maps you can pan and question, two-host audio overviews in deep dive, brief, critique, or debate styles, narrated slides exportable to PowerPoint, and tables whose cells carry their own citations. Generate flashcards and timed quizzes from what you read, mark cards for review, and resume saved progress later. Save cited answers and Studio outputs as notes, convert notes back into searchable sources, and export almost anything: conversations, projects, mind maps as SVG, flashcards as Anki text, audio as MP3. Share projects with viewer or editor roles, keep conversations private per person, and bring Claude, OpenAI, any OpenAI-compatible provider, or a local Ollama model, with extraction, OCR, Whisper transcription, and Kokoro audio synthesis running on your own server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Insights LM gives you a NotebookLM-style research assistant that runs on your own infrastructure and answers strictly from the documents you feed it. Build a notebook for a project, drop in PDFs, pasted text, website links, and audio files, then ask questions in plain language and get answers grounded in those sources rather than the open internet. Every answer carries citations you can click to jump straight to the passage it came from, so verifying a claim takes seconds instead of a fresh search. Findings worth keeping become notes saved alongside the notebook, building a private knowledge base that grows with your research. When reading is too slow, generate an audio overview and listen to two hosts discuss your material like a podcast episode, perfect for absorbing a long report on a walk. Teams use it to interrogate internal documentation, onboard new hires against company knowledge, and brief themselves before meetings without uploading confidential files to a third-party service. Because the whole stack is yours, you choose which AI models do the reading, including local models for fully private work. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Instead of burying your documents in a vector index you cannot inspect, LLM Wiki v2 files them into a Markdown wiki you can read, browse, and question. Drop text, Markdown, or PDF files anywhere on the page and each one is catalogued automatically, filed into a folder that says what it holds, and linked to the notes it relates to. Ask a question and the answer cites the exact notes it used, with clickable sources you can open, verify, and correct. New documents update the note on their subject instead of piling up as disconnected chunks, so what you teach it stays taught. A small classifier routes filing and questions through the folder tree, keeping the wiki quick and cheap as it grows, and you can browse the tree, follow see-also links, move or delete notes, and watch the tokens spent by both the model and the classifier. Connect OpenRouter, OpenAI, Gemini, a local Ollama, or any compatible endpoint, and expose the same wiki to Claude Code or Codex as long-term memory they can recall from and write to. Because every note is plain Markdown in a folder you own, the whole knowledge base can live in git beside your other files. 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.

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.

A self-hosted "second brain": Khoj indexes your own files and answers questions from them, parsing Markdown (whole Obsidian vaults included), org-mode, PDF, Word, plain text, Notion pages, GitHub repositories, and images described by a vision model, then embedding everything with sentence-transformers into a vector index for semantic search and RAG with cited sources. Any LLM backend works: local models like Llama, Qwen, or Mistral via Ollama, or cloud models like GPT, Claude, and Gemini. You can build custom agents, each with its own persona, scoped knowledge base, chat model, and tools such as web search and code execution. Scheduled automations run recurring research and deliver newsletters or notifications to your inbox, and research mode performs multi-hop web searches with inline citations. Access it from a browser, the Obsidian plugin, Emacs, desktop, or WhatsApp - all clients connect to the same self-hosted instance, making Khoj one of the few AI assistants Emacs users can point at decades of org files. Semantic search means recall works without exact keywords: "that paper about forecasting with transformers" surfaces the right PDF even when you cannot remember its title. Switching LLM backends never requires re-indexing your documents, and with a local model via Ollama, even inference stays on hardware you control - journals, research, and private notes are never sent anywhere. Python/FastAPI stack, AGPL-licensed, with PostgreSQL storage.

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.

Human rights teams, legal researchers, and archivists use Uwazi to turn scattered documents and case records into searchable, structured collections that the public or trusted partners can explore online. You design templates that define exactly which fields each record carries, from dates and locations to people, organizations, and document types, then import material through the interface or in bulk from CSV files. Uploaded PDFs and documents become full-text searchable, so a phrase buried inside a scanned report is as findable as the metadata typed beside it. Relationships connect related entities across the collection, letting you trace how a person, an event, and a piece of evidence fit together instead of keeping them in isolated folders. Curators build public pages with live filters, maps, and visualizations drawn directly from collection data, while granular permissions decide which records stay private, which are shared with specific groups, and which are published for everyone. Multi-language support lets the same collection serve readers in several languages, and activity logs keep an audit trail of edits. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With DSpace, a library or research office can give every thesis, journal article, and dataset its own permanent web address, a searchable metadata record, and files visitors download from the archive. Content sits in a tree of communities and collections, and each collection decides who may deposit and how many review steps follow; reviewers accept a submission or reject it with a note that sends it back to the author. Embargoes hold files back until a set date, access policies limit other files to chosen groups, and sign-in works through LDAP, Shibboleth, SAML, OpenID Connect, or ORCID. Search covers metadata and the extracted full text of uploaded files, facets narrow the results, and browse pages sort by title, issue date, author, or subject. Editors can correct a published item through the submission form. Administrators inspect an audit trail and rewrite homepage news from an admin form. Entity types for people, organizations, projects, journals, and datasets link each publication to the work behind it, and DOIs can be registered through Crossref. Optional settings let authors keep an email address private on their researcher profile and download their own restricted files. Usage reports count visits, downloads, and top countries per item. REST, OAI-PMH, SWORD, and Google Scholar metadata connect the archive to harvesters, deposit tools, and search engines. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD-3-Clause licensed.

A small library deserves real library software, not a spreadsheet with aspirations: Pinakes runs the whole operation, from the barcode on the spine to the reminder in a reader's inbox. Catalogers add a book by ISBN and watch metadata and covers arrive from Open Library and Google Books, then file it under Dewey categories with barcodes for every physical copy. Circulation handles requests, approvals, pickups, renewals, and returns, with FIFO reservation queues that notify the next reader the moment a copy frees up, and due dates that respect the library's own closure calendar. Patrons browse a public catalog with instant search and filters, reserve from home, renew loans, read ebooks and listen to audiobooks in the browser, and get due-date reminders automatically. The same installation can describe archives to ISAD(G) standards, exchange records through MARC, SRU, Z39.50, and OAI-PMH, and present digitized pages through IIIF viewers. Sixteen bundled plugins, custom staff roles, a homepage editor, and ten themes make it feel like your library, and it installs on ordinary shared hosting with a guided setup. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

Your e-reader knows exactly where you stopped reading, and Sake makes your whole library know it too, with a self-hosted web library that syncs KOReader progress, notes, and highlights across every device you own. Browse your collection in a clean web app with covers, metadata, shelves, ratings, and reading state, and organize it with rule-based shelves that file new books automatically according to conditions you define. Pair a KOReader device once and progress uploads in the background when the reader sleeps, new books download on request, and highlights land in a searchable annotations hub where you can edit notes inline and export them as Markdown or JSON. An existing on-device library can be exported back into the web app complete with its sidecar data, so years of reading history move with you. Search providers including Open Library, Project Gutenberg, and Anna's Archive (through Libgen mirrors) put new books one query away from your shelves, and metadata lookups enrich them from Google Books, Open Library, or Hardcover. OPDS and WebDAV endpoints serve any compatible reader app with optional separate Basic-auth passwords, the built-in plugin updater keeps the KOReader plugin current without manual file copying, and reading statistics chart your habits across the library. The installable progressive web app keeps the library one tap away on phones and tablets. 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.

Most wikis die of flat page-and-tag sprawl; BookStack's defining decision is enforced structure - an MIT-licensed PHP/Laravel platform (over MySQL) where content lives in a hierarchy of shelves, books, chapters, and pages, the way a physical library works. A shelf maps to a department, a book to "Engineering Runbooks," a chapter to "Database Procedures," a page to the actual document. That opinionation removes the "where does this go?" friction and keeps knowledge bases tidy as they grow. Editing works both ways: a clean WYSIWYG editor for most users, a Markdown editor with live preview for those who prefer it - switchable per page. Full-text search spans all books or scopes to one, with direct links to individual paragraphs, and include tags let you embed one page's content inside another so shared blocks update everywhere at once. Every edit creates a diffable, revertible revision. Page templates standardize recurring formats, tags add cross-cutting categorization, and built-in diagrams.net integration draws architecture diagrams in place. Authentication covers email/password plus OIDC, SAML2, LDAP, and social login; a full role and permission system locks content down per shelf, book, or page. Pages and books export to PDF, HTML, plain text, and Markdown, a REST API automates content, and the whole thing runs happily on the cheapest VPS you can find.

In seven wizard steps, PandaWiki sets up a product docs, manual, FAQ, or blog site whose built-in AI answers visitors using only your own content. Those visitors can chat with an assistant that cites its sources and accepts image questions, or switch to a docs-only search that lists ranked pages with summaries. Publishing stays under control: each document has three switches, visible in navigation, reachable by URL, and answerable by AI, and nothing appears or gets learned until it is published. Authors write in a Markdown and HTML editor, or import from URLs, RSS and Atom feeds, sitemaps, offline .txt, .md, .xlsx, .docx, and .pdf files, Notion, Yuque, SiYuan, Wiki.js, Feishu, Confluence, and DingTalk. Pages export to Word, PDF, or Markdown. The wizard covers models, domain, HTTP or HTTPS ports, import, publishing, answer testing, and page decoration. One knowledge base can also feed a web widget and DingTalk, Feishu, WeCom, and Discord bots. Administrators get a dashboard of visits, questions, visitor regions, hot documents, and referring domains. Chat models come from Baizhi Cloud, DeepSeek, OpenAI, or Ollama, while vector and reranking models are built in. The open-source edition covers one wiki site, 300 documents, and one admin, and its console and documentation are in Chinese. 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.

SourceWeft is an AI workstation you host yourself, where agents, your documents, and your model keys work in one place instead of scattering across chat tabs you do not control. Describe a job and a lead agent breaks it down, handing research, exploration, and execution to focused sub-agents that share the same working context and files. Agents draw on a skill library covering presentations, HTML pages, images, meeting summaries, and study guides, and you can add your own skills so good workflows become repeatable. MCP servers, web search, and web extraction connect agents to outside tools, while approved commands run inside a sandboxed environment that cannot touch the rest of your server. Feed it PDFs, web pages, notes, YouTube videos, Notion, Drive, Gmail, or Slack, then follow citations from any answer back to the source material it came from. Bring your own keys for the chat and indexing models you prefer, organize the team into workspaces with roles and access controls, and pick up any conversation from the web app or desktop clients. 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.