Grape
Local first storage for freelancers

Work with no wifi and no worry.

Grape keeps four client folders in a database on your own machine, so when you switch clients a dead connection changes nothing about what you can open.
Writing, reading, organising, drawing and recording all work offline
You pick where the database file sits
Export any note, or the whole library, as Markdown, HTML or PDF
Run the AI locally through Ollama or LM Studio if you prefer

No account to start

Download, open, write. Accounts only matter for the paid plans.

Your choice of AI provider

OpenAI, Anthropic, Google, Groq, DeepSeek, OpenRouter, Ollama and more.

Export whenever you want

Markdown, HTML or PDF, one note at a time or the whole library.

You pick where the file sits

Point the database at any folder on your machine, and move it later.

The plane, the tunnel, the cabin

Writing, search, drawing and recording all work with no connection.

Local models if you want them

Run the AI through Ollama or LM Studio and nothing leaves the machine.
Results

Three things that stop being a problem

Feature lists are easy to write and hard to care about. This is what changes for freelancers.

Switch clients without losing context

Ask what happened last with a client and start the call already caught up.

Turn the kickoff call into the brief

Record it, get the transcript, and ask for the scope and deliverables in writing.

Keep the admin somewhere you will look

Checklists, dates and follow ups in the same note as the work itself.
In practice

What that looks like for freelancers

A few moments in a normal week where the app earns its place.

New enquiry

Record the call, get the scope out of the transcript, and quote from that.

Delivery

One folder per client with the brief, the work notes and the checklist.

End of month

Ask what you delivered and what is still unpaid.
FAQ

Questions Before You Install It

The rest of them live in the help center.

Keep one clear head.

Briefs, calls, invoices to chase and the idea you had for a fifth project, in one library that costs nothing to start and works without a connection.