inkeep/open-knowledge

Beautiful, AI-native markdown IDE and LLM wiki

OpenKnowledge

OpenKnowledge is a free, locally‑run markdown editor that blends the feel of a WYSIWYG document tool (think Google Docs or Notion) with deep AI‑assisted authoring. It’s built for people who keep knowledge in markdown – wikis, specs, second‑brain notes – and want large‑language‑model helpers (Claude, Codex, etc.) right inside the editor.

What it does

  • True WYSIWYG editing – you see the final formatted markdown as you type.
  • Cross‑platform desktop app (macOS, Windows, Linux) and a web UI that can be launched locally via a CLI.
  • Side‑by‑side AI editing – connect to Claude, Codex, OpenCode, Pi and any other LLM harness through a “MCP/CLI” bridge. The AI can draft, rewrite, or search your documents.
  • Built‑in MCP, skills, and agentic search for creating LLM‑backed wikis, second‑brain knowledge graphs, or structured specs.
  • Team sharing & auto‑sync – under the hood it uses a git/GitHub workflow, so collaborators can push/pull changes without a separate service.
  • Embeddable HTML & rich components for engineering specs, visual reports, etc.

How to get it

Desktop

  1. Download the installer from openknowledge.ai/download or the latest GitHub release.
  2. macOS (Apple Silicon) – drag the app to Applications.
  3. Windows 10+ – run the setup (no admin needed).
  4. Linux – install the provided .deb or .rpm.

Web / CLI

npm install -g @inkeep/open-knowledge   # install the CLI package
cd your‑project
ok init          # scaffolds a folder and wires up AI editors
ok start --open  # launches a local web server and opens the editor in your browser

Requires Node 24+ and git.

Typical workflow

  1. Open a folder that already contains .md/.mdx files (e.g., an Obsidian vault, a code repo, a documentation site).
  2. The editor shows a file navigator, search bar, tabs, and a graph view of wiki links.
  3. Use the AI pane to ask Claude, Codex, etc., to draft a section, improve wording, or perform “agentic search” across your knowledge base.
  4. When you’re ready to collaborate, enable the git sync option – the app will push/pull to a GitHub repo automatically.
  5. Export notes as embeddable HTML or keep them as markdown for downstream tooling.

Who it’s for

  • Developers or technical writers who already store docs in markdown and want a richer editing experience.
  • Teams building LLM‑backed wikis or “second‑brain” knowledge graphs.
  • Anyone who likes the convenience of Notion‑style editing but needs the privacy of a local, open‑source tool.

Contributing & support

  • Open issues on GitHub for bugs or feature ideas.
  • Small pull requests are welcomed; larger changes should start with an issue.
  • Community chat lives on Discord; product updates are posted on X (Twitter).

License

OpenKnowledge is released under GPL‑3.0‑or‑later, an OSI‑approved open‑source license.

TL;DR

OpenKnowledge is a locally‑hosted, WYSIWYG markdown editor that integrates LLMs (Claude, Codex, etc.) for AI‑assisted writing, supports desktop and web deployments, and offers git‑based team sync—all for free and open source.

Related

  • Dispatch
    OpenKnowledge: An AI-First Open Source Alternative to Obsidian and Notion

    OpenKnowledge is an open-source, WYSIWYG markdown editor for macOS that integrates directly with Claude, Codex, and Cursor to create an AI-powered second brain using Git-based synchronization.

  • Project
    langchain-ai/openwiki

    OpenWiki is a Node‑based tool that lets LLM coding agents automatically generate, query, and keep up‑to‑date a linked Markdown wiki inside a code repository. It integrates with many agents, supports parallel page generation, workspace linking, visual graph browsing, and CI‑driven updates, all while storing plain Markdown you own.

  • Project
    vercel-labs/lat.md

    A knowledge graph for codebases written in markdown that links documentation to source code, helping AI agents and humans maintain and navigate domain context.

  • Project
    nvk/llm-wiki

    A knowledge management framework that enables AI agents to research, compile, and maintain structured wikis for personal projects and complex information gathering.

  • Project
    SamurAIGPT/llm-wiki-agent

    LLM Wiki Agent is a local, agent‑driven system that ingests PDFs, DOCX, markdown, etc., extracts entities and concepts, builds an ever‑growing inter‑linked markdown wiki, flags contradictions, and generates a visual knowledge graph—all without a server or database.