Tools
Everything here is meant to leave with you. Run a tool in the page, copy a prompt, or load an adapter onto the model already running on your machine.
Convert
Convert an image between PNG, JPEG, WebP and AVIF. The file never leaves the page — it is a canvas here, and Pillow in Python.
- format png, jpeg, webp or avif
- quality 1-100 for the lossy formats
- three doors web page, assistant, or thl convert
Extract
Documents to Markdown with the structure still attached. Headings stay headings and pages stay marked, because that is what the next stage splits on.
- unaided text, markdown, html and csv, right here
- with the package pdf, word, slides, sheets, epub
- never invented no outline means no headings
Chunk
Split a document along its own headings rather than every 512th character. Size is the constraint, not the organising principle.
- citable every chunk knows its heading and page
- jsonl one record per line, greppable and streamable
- in the tab pure logic, nothing to install
Tokenize
How big is this, and what will it cost to embed? A measuring instrument — not a stage, because embedding models tokenize internally with their own vocabulary.
- distribution median, 95th, and the long tail
- overflow which pieces would be truncated silently
- three counters exact, OpenAI, or no download at all
Assistant
Say what you want and it runs the matching tool right here in the page. Rules rather than a model — instant, offline, nothing to install.
- routing matched against the same tool spec
- no model nothing to download, works on arrival
- files stay on your machine
Prompts
A prompt library for real use cases. Copy one and paste it into whatever model you already run.
- filtered by the job you are doing
- one click copy straight to clipboard
- model agnostic works with anything local
LoRA Adapters
Small fine-tuned adapters that stack onto a base model already installed on your machine.
- stackable sits on a model you already have
- local no hosted inference anywhere
- status in training, none downloadable yet