A local-first journal that makes continuity visible.

Write in daily pages. A model running on your own machine opens each day, responds when you ask, and suggests traces. Not a chat wrapper, but a navigable archive built around time and return.

Registration at llamora.app is closed for now. You can run your own.

Llamora showing a daily page: the day opening, entries with their traces, and the model's response.

Daily pages

A new page opens each day. You write; the model responds only when asked. Each morning it opens the day with a few lines drawn from recent entries and a digest of the day before. Everything stays anchored to its date.

The calendar, with a summary of the hovered day beside it.
The calendar is the main way around. Hover a day to see what it held.

Photos, too

Drop images onto an entry, or pick them from your phone (HEIC included), and open them full size to look back. They are stripped of location and other metadata, then stored encrypted. With a model that can see, replies take them into account.

A photo of the eclipse opened full size over the page.

Markdown supported

Write in Markdown when a longer entry wants some shape. Headings, lists, quotes and emphasis render as you would expect, and stay plain text underneath.

An entry written in Markdown, with a heading, a bulleted list and a quote.

Traces

After you write, the model can suggest a few traces: light labels that make it easier to return later. Keep the ones that fit. Over time they show where something recurs, what it appears alongside, and which days it touches.

Suggested traces for an entry: mindfulness, peace, solitude, stillness.
The traces view: a list of traces, and for the selected one a year-long heatmap, related traces and a summary.
Each trace gets its own page: a year at a glance, what it keeps company with, and a summary of how it has changed.

Search by meaning

Find past entries by what they were about, not only the words you used. Results are ranked across your whole journal, with matching traces highlighted.

Search results for solitude, each with its traces.

On your phone

The same journal, laid out for a small screen and a thumb. Write on the way, add a photo from the camera roll, read it back at your desk.

A daily page on a phone.

Private by design

Stays on your machine

The model runs locally and the archive stays with it. Llamora makes no outbound requests: no telemetry, no analytics, no phoning home.

Encrypted at rest

Entries, responses, traces, search and photos are encrypted before they are stored. Your password unlocks a key that lives only in memory while you are signed in.

No evaluation

The model can respond and suggest, but it never scores entries, infers traits or builds a profile of you. The record is yours to interpret.

Get started

You need uv and a model server with an OpenAI-compatible API, such as llama.cpp. 

# 1. Start a local model
llama-server -hf bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M \
  --port 8081 --jinja

# 2. Install and run Llamora
uv sync
LLAMORA_LLM__UPSTREAM__HOST=http://127.0.0.1:8081 uv run llamora-server dev

Then open http://localhost:5000 and create an account. The README covers the demo journal, configuration and running in production.