Sandbox
@inkeep/open-knowledge

Markdown editor and LLM wiki for agent workflows

OpenKnowledge is a local markdown editor for notes, specs, and knowledge bases that works like a wiki. It combines a WYSIWYG editor, file navigation, search, graph links, and side-by-side AI editing so you can keep documents and agents in the same workspace.

4,149 stars271 forksTypeScriptUpdated 6d ago
Who it's for

Builders who manage markdown notes, specs, or second-brain docs and want Claude, Codex, or Cursor to work with them.

What it delivers

You can edit knowledge bases and specs in one place while your agent reads, writes, and searches the same files.

What it does

WYSIWYG markdown editing

Edit markdown files in a Google Docs-like interface instead of raw text.

Desktop and web app

Use the same editor as a desktop app on macOS, Windows, and Linux or as a local web app.

Agent integrations

Works with Claude, Codex, Cursor, OpenCode, and other harnesses through MCP and CLI.

Knowledge base starter packs

Includes out-of-the-box support for LLM wikis, second brains, specs, and notes.

Git-based sync and sharing

Uses git and GitHub under the hood for optional team sharing and auto-sync.

Embeddable content

Supports embeddable HTML and rich components for specs and visual reports.

How to get it

  1. 1Web app — on any platform (including Intel Macs and servers), run the same editor as a…
    npm install -g @inkeep/open-knowledge
    cd your-project
    ok init          # scaffold the project + wire up your AI editors (Claude Code, Claude Desktop, Cursor, Codex, OpenCode, OpenClaw)
    ok start --open  # serve the web editor and open it in your browser

README

OpenKnowledgeOpenKnowledge

OpenKnowledge is a beautiful markdown editor with integrations with Claude, Codex, and other harnesses. For knowledge bases, LLM wikis, specs, and notes. Private, local, and free.

website   •   desktop app   •   web UI + cli   •   𝕏   •   discord

OpenKnowledge editor with an AI agent drafting a launch recap

Features

Highlights:

  • Full true WYSIWYG so that editing markdown files feels like editing a Google Doc or Notion page.
  • Desktop app (macOS, Windows, Linux) and web UI with file navigator, search, tabs, graph wiki link viewer, and more.
  • Integrated side-by-side AI-editing with Claude, Codex, OpenCode, Pi and others. Can be used with any harness/agent via MCP/CLI.
  • Out-of-the-box MCP, skills, and agentic search for LLM Wikis, second brains, and knowledge graphs.
  • No-code Team sharing and Auto-sync powered by git/GitHub under the hood.
  • Embeddable HTML and rich components for writing engineering specs and visualized reports.

Install

Desktop app — download it from openknowledge.ai/download (or grab an installer from the latest release):

  • macOS (Apple Silicon): open the DMG and drag OpenKnowledge to Applications.
  • Windows 10+ (x64 / Arm64): run the Setup installer — per-user, no admin prompt.
  • Linux (x64 / arm64): install the deb (Debian/Ubuntu) or rpm (Fedora/RHEL) package.

Web app — on any platform (including Intel Macs and servers), run the same editor as a local web app via the CLI (Node.js 24+ and git required):

npm install -g @inkeep/open-knowledge
cd your-project
ok init          # scaffold the project + wire up your AI editors (Claude Code, Claude Desktop, Cursor, Codex, OpenCode, OpenClaw)
ok start --open  # serve the web editor and open it in your browser

Usage

Use OpenKnowledge by opening any existing folder on your computer that contains markdown or mdx files. The app can be used with existing codebases, wikis, Obsidian vaults, etc.

Think of it as Notion meets VS Code.

You can use it simply as a rich, WYSIWYG markdown editor to start. For existing files or plain notes/docs.

To get more complex, you can use the starter packs to create LLM Wikis, second brains, or more structured knowledge bases.

Either way, the app will walk you through installing the MCP and skills for agent harnesses detected on your computer. These are designed to help agents with enriched search + authoring of documents.

Git/GitHub based sync and sharing can optionally be enabled.

Docs for general usage: https://openknowledge.ai/docs.

Contributions

Public pull requests or issues are welcome!

See CONTRIBUTING.md for details.

License

OpenKnowledge is licensed under GNU General Public License v3.0 or later, an OSI-Approved open source license.

Community & Support

Feel free to file an issue or ask questions on the Discord community. We're always looking for ideas and requests.

⭐️ If you'd like to support this project, consider starring the repo ⭐️

🔔 Follow us on 𝕏 for product updates. 🔔

Files in the repo

Repository payload30 top-level entries
  • .changeset
  • .github
  • assets
  • docs
  • lint-plugins
  • packages
  • patches
  • scripts
  • test-support
  • .env.example
  • .gitignore
  • .node-version
  • .npmrc
  • AGENTS.md
  • biome.jsonc
  • CLA.md
  • CONTRIBUTING.md
  • knip.config.ts
  • LICENSE
  • no-comments.config.jsonc
  • oxlint.config.ts
  • package.json
  • pnpm-lock.yaml
  • pnpm-workspace.yaml
  • PRECEDENTS.md
  • README.md
  • THIRD_PARTY_NOTICES.md
  • tsconfig.json
  • turbo.json
  • vitest.scripts.config.ts

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More tools

JuliusBrussee/
caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

105k
1 add
MemPalace/
mempalace

The best-benchmarked open-source AI memory system. And it's free.

59k
stablyai/
orca

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

66k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

132k

Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors

64k
headroomlabs-ai/
headroom

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

71k