Crosstalk-Solutions/project-nomad

Project NOMAD is an offline-first knowledge and education server. Wikipedia, thousands of books, courses, maps, and optional local AI, all running on hardware you own with no internet required.

What it solves

Project NOMAD is a self-contained, offline-first knowledge and education server. It solves the problem of losing access to critical information, tools, and AI assistance when internet connectivity is unavailable or unreliable. It bundles a local AI chat with a knowledge base, offline encyclopedias, educational courses, maps, and data tools into one manageable system.

How it works

NOMAD is a management UI ("Command Center") and API that orchestrates a collection of containerized tools via Docker. It handles installation, configuration, and updates for all included services. The AI chat runs locally using Ollama (or OpenAI-compatible servers like LM Studio) and supports document upload with semantic search (RAG) via Qdrant. Offline content like Wikipedia and medical references is served through Kiwix, education through Kolibri, maps through ProtoMaps, and data tools through CyberChef. A setup wizard guides first-time configuration, and automatic updates can be scheduled.

Who it’s for

NOMAD is aimed at individuals and organizations that need reliable offline access to knowledge and AI tools — such as emergency preparedness, remote or disconnected environments, education in low-connectivity areas, and self-hosters who want a private, local AI and knowledge stack. It is designed for Debian-based systems and recommends a GPU-backed device for running AI models.

Highlights

  • Offline-first design: no internet required after initial installation, with zero built-in telemetry
  • Local AI chat with document upload and semantic search (RAG) via Ollama and Qdrant
  • Bundles offline Wikipedia, medical references, ebooks, Khan Academy courses, maps, and data tools
  • One-click app catalog ("Supply Depot") plus support for running custom Docker containers
  • Opt-in automatic updates for core software, apps, and offline content
  • Community benchmark leaderboard for comparing hardware builds
  • Apache 2.0 licensed

Related

  • Project
    docker/genai-stack

    A Docker-based starter stack for building GenAI applications, featuring integrated LLMs and Neo4j for RAG and knowledge graph capabilities.

  • Project
    desplega-ai/agent-swarm

    agent‑swarm is an open‑source platform that turns a lead AI agent into a task‑routing hub, delegating work to containerised worker agents (Claude Code, Codex, etc.). It integrates with Slack, GitHub, email, and many other tools, persisting context via vector memory, and can automatically generate PRs, replies, or scheduled scripts. The system is model‑agnostic, runs via Docker (or Helm on Kubernetes), and is licensed under MIT.

  • Project
    swarmclawai/swarmvault

    A local-first LLM wiki and knowledge graph builder that transforms documents, code, and URLs into a structured markdown knowledge base for humans and AI agents.

  • Project
    cropflre/nowen-note

    An open-source, self-hosted knowledge base and task workbench that integrates rich-text/Markdown notes with AI RAG capabilities for private data management.

  • Project
    lfnovo/open-notebook

    An open-source, privacy-focused alternative to Notebook LM that lets you organize research and chat with your data using local or cloud AI models.