Introducing
AsanagiDB Logo
Desktop

The all-in-one graph database, AI memory and document-RAG layer tool.

Powered by AsanagiDB.

The Scarecrow, Jeff, and Sonny journeying along the Yellow Brick Road toward the Emerald City under a starry night skyAsanagiDB Desktop graph database application window looming in the sky

Give Them All A Brain

Give them all a brain

One brain for every assistant

An AI assistant forgets everything when its session ends. AsanagiDB Desktop gives it a memory that lasts: a graph of what it has learned and what it has read, kept on your Mac. Connect Claude Code today and another assistant tomorrow, and they share the same brain.

  • What one session learns, the next one knows.
  • Memories are linked to the documents they came from.
  • Open the brain in Explore and see every concept and connection.
A demonstration of a local Qwen model using GraphRAG in realtime. AsanagiDB Desktop shows the model's queries and graph traversals. You can then replay or step through the queries.
Visual Architecture

Built for exploration, from the ground up

Desktop app sidebar showing servers, databases, and exploration tools
Sidebar

Local or remote, one sidebar

Console toolbar and Apache TinkerPop Gremlin query editor
Console

Query in Gremlin

Interactive knowledge graph visualization with concepts and relations
Graph Canvas

See every result as a graph, a table or JSON

MCP

Connected in one command

Turn on MCP, copy one command into Terminal, and Claude Code connects to AsanagiDB Desktop. What it learns goes into a memory database in your workspace, and it is still there next session.

  • Assistants connect on this Mac only, with an access token you can replace at any time.
  • You choose what they can read. Other databases are read-only to them.
  • Works with Claude Code and other MCP clients.
Document RAG with folder indexing

Document RAG

Your documents, read once and remembered

Add a folder and your assistant reads the Markdown, text and PDF files in it, recording a summary of each section, its concepts and the questions it answers. A long PDF is split by its chapters and can be read over several sessions.

  • Folders are read-only. Your files stay where they are.
  • The memory keeps what your documents are about and where, not their text.
  • Edit a file and the app shows what is waiting to be read again.
has sectionmentionsrelatedaboutDocumentSectionConceptConceptMemory

True GraphRAG

GraphRAG, not a pile of chunks

Most RAG tools cut documents into chunks and fetch the ones whose embeddings sit closest to your question. AsanagiDB Desktop builds a graph instead. Each document is split into its sections, each section is linked to the concepts it covers, and concepts are linked to each other and to what your assistant remembers. A search starts at the concepts in your question and follows those links to the sections that discuss them. Then your assistant reads the exact text.

  • No embeddings and no vector store. Every link can be seen and queried.
  • Synonyms lead to one concept, so a search for Design by Contract finds what was written about Software Contracting.
  • Search returns the file and section, so answers can cite their source.
  • It is a real graph in a real graph database: query it in Gremlin, browse it in Explore.

Your files, your tools

Work with your favorite editor

Every document in the graph is a real file on your disk. Right-click it and open it in the app you already use. No vault, no special format, nothing to export.

Show Page

From a concept to the page it's on

Every section remembers where it is in its document. Right-click a section and choose Show Page, and the PDF opens at the page where the section starts, its first words highlighted. Right-click a concept and choose Show Pages to go through every section that mentions it, across all your documents.

Explore

Explore without writing a query

See every vertex and edge label with its count. Pick one to draw a sample as a graph, open a label to see its properties, and double-click a vertex to expand it.

Find

Search by drawing what you're looking for

Describe a pattern instead of writing a query. Each card is a vertex with the label and property values it should have, and cards connect through the edges between them. AsanagiDB Desktop turns the pattern into Gremlin as you build it and shows every match as a graph, each vertex marked with the card it matched.

  • Text, numbers, ranges and wildcards such as Eiff* or *contract*.
  • Conditions on edges too, such as the type of a relation.
  • Right-click any vertex and choose Find Vertices Like This.
  • Arrange the cards on a canvas, save the pattern, and undo any change.

Console

Gremlin, when you want it

Write Gremlin and see the result as a table, as JSON, or as a graph you can explore. The Console works the same on this Mac and on a server.

  • Press ⌘↩ to run a query. The queries you ran are in the history.
  • Results export to JSON and CSV, and the graph to PNG.

Local or remote

Runs on your Mac. Or on your server.

The AsanagiDB engine runs inside the app, and other tools can connect to it like a local server. Point the sidebar at an AsanagiDB server and the Console, Explore and Databases work the same way.

  • Separate workspaces, each with its own databases and memory.
  • Query results export to JSON and CSV, and the graph to PNG.

Free.

AsanagiDB Desktop is free on the Mac App Store. No account, no subscription.

Requires macOS 26 or later.

FAQ

Frequently asked questions

Is it really free?

Yes. There is no account to create, no subscription and no in-app purchase.

What do I need?

A Mac with macOS 26 or later.

Does my data leave my Mac?

No. Your databases, documents and memory stay in your workspace folder, and the app collects no data. It connects only to servers you add yourself. When you connect an AI assistant, what the assistant reads is sent to it and handled under that assistant's own privacy terms.

Which assistants can use it?

Claude Code connects with one command, copied from Settings. Other MCP clients connect the same way, over HTTP on this Mac with the access token.

What can my assistant read?

Markdown, plain text, reStructuredText, Org, AsciiDoc, LaTeX and PDF files in the folders you add. A scanned PDF has no text to read.

Does it copy my documents?

No. Folders are only read. The memory keeps summaries, concepts, questions and where each section is, not the text.

What query language does it use?

Gremlin. Each statement in a script gets its own result, shown as a graph, a table or JSON.

Do I have to write Gremlin?

No. Explore shows every label and draws a sample of it, and Find lets you draw the pattern you're looking for as cards. The Console is there when you want to write Gremlin yourself.

Can I use it with an AsanagiDB server?

Yes. Add the server in the sidebar; the password is kept in your Keychain. The connection isn't encrypted, so use it on a network you trust or through an SSH tunnel. The app warns you for any host other than this Mac.

How is it related to AsanagiDB?

It is the AsanagiDB engine with a Mac app around it, running on the Community license. If you have activated an AsanagiDB license on this Mac, the app uses that license instead.