Matrix LLM · iPhone, iPad and Mac
Ask your documents. On your Mac or iPhone, offline.
Add contracts, regulations or reports and ask in plain words. Every answer comes with the exact passage it is based on. The models run on the device, so your documents stay there.
Get it on the App StoreFree to download for iPhone, iPad and Mac. Interface in 22 languages.
The assistant
Tell it what you want. It works the app for you.
You don't need to know what a vector or a knowledge graph is. Ask in plain words: "Create a collection called Contracts", "Check all supplier contracts for notice periods", "Switch to the Paper style". The assistant uses the same tools an AI agent gets, and shows every step.
Asks before it acts
Anything that changes something appears as a card: what it will do and how much work it is, for example "About 40 model requests". It runs only after you tap Run.
Cannot delete
Deleting is not one of its tools. Settings it may change come from a fixed list, never keys or endpoints.
Opens the right view
After a step it shows the result: the collection, the table run, the term in the graph, the document.
Help built in
"How do I add files?" is answered by any model from a built-in guide, with a "Show me" link to the right place.
Stops when stuck
If the same action fails twice, it stops and says what went wrong and what you can do.
The limit
Working the app needs a model that can call tools. Apple's on-device model answers the help questions, not the app tasks.
The first five minutes
From download to the first answer with sources.
Pick a model
Apple's model on the device needs no download where the system offers it. Or one tap loads a small model. The search model downloads in the background, then everything works offline.
Try a sample collection
Three ready-made sets: a German sample contract, the official accident file of the US Airways flight that landed on the Hudson, and Wikipedia articles on the Panama Papers.
Add your own files
PDF, Word, Excel, PowerPoint, e-mails, e-books, ZIP archives, photos with text recognition. Or share a file to Matrix from any other app.
Ask a file right away
Attach it to a question with the paper clip. Afterwards keep it as a collection or discard it.
Tap a citation
It opens the exact passage, in PDFs with its page.
The one rule
The AI reads. Everything you could check is plain code.
The language model is only used where language understanding is needed. Splitting documents, following references, verifying quotes, correcting sources and logging every step is done by ordinary rules — reproducible, no AI judgement involved.
Throughout this page: AI means the model decides,rules means deterministic code does.
Every answer shows its sources
Down to the verbatim quote in the original. Clickable, checkable.
Your data stays home
Runs with local models on the device or inside your own network. Nothing has to leave.
Nothing happens in the dark
Every search, every hit, every automatic correction is logged and can be replayed.
Ask a question
It doesn't guess. It goes looking.
Ask once, and the model researches the documents itself — like a junior analyst with a strict supervisor.
Prepare the documents rules
Split along their real structure — articles, sections. Each piece gets a "meaning fingerprint" so search works on sense, not just words. References like "pursuant to Art. 92(1)" are linked to their target.
Search, read, search again AI
The model writes its own search queries, opens passages, follows references and keeps digging with the vocabulary it found — until it has enough evidence or runs out of budget.
Guard rails rules
A search budget caps the cost. Watchdogs stop it from going in circles. An answer given without searching at all is thrown away.
Answer only from what it found AI
Every statement is tagged with its source number: [1], [2], [3].
Check the answer rules
The checks in the next section run on every answer, then everything is shown with clickable sources and a full log.
Built-in fact check
It checks its own homework.
After every answer, a chain of plain-code checks goes over each citation.
Does the source exist?
Every [n] is validated against the list of sources actually retrieved.
Is the quote really there?
Quoted words are searched in the original. Not found → a warning sign on the answer.
Does that source actually say it?
Two independent signals — shared key terms (legal references count triple) and closeness in meaning.
Fix only when both agree
Then the marker is pointed to the right source and labelled "→ 3". Otherwise just a hint. The answer text itself is never rewritten.
Tables
Same question. Every row. As a table.
Pick a collection or upload your own list and ask every row the same question. Each answer has to fit columns you define: text, number, date, choice.
Validated, not trusted
Missing or wrongly typed fields show up right in the cell.
Lists fan out
Five items in one answer become five rows — each still linked to its source passage.
Redo just the bad rows
Re-run single rows with a stronger model. Duplicates are merged. Export to Excel.
Typical uses: a list of every obligation in a regulation with addressee, deadline and evidence · the same check across hundreds of contracts · first-pass screening of a customer list.
The knowledge graph
A map of who relates to what — with receipts.
The model reads every passage and pulls out things and relations: who is responsible for what, what mitigates which risk, who owns whom. Every single link carries a verbatim quote from the original.
Quotes are verified
A link whose quote can't be found is repaired first, not silently dropped. If the quote says the opposite ("must not…"), it's flagged.
Duplicates merged
"BaFin" and "Federal Financial Supervisory Authority" become one node — every merge is logged and can be undone by hand.
Lenses, not rewrites
Raw labels stay untouched; a switchable "lens" maps them onto your own vocabulary — no re-extraction needed.
Topics and summaries
The graph is split into clusters, each with a short summary: a table of contents for the whole corpus. Export to PowerPoint.
Nothing disappears quietly
Failing passages go to quarantine and are retried; every finding lands in a review queue.
Honest about quality
A local 30B-class model gives a fast first map — orientation, not proof. A frontier model gets close to "audit-ready".
Runs everywhere
One engine. Mac, iPhone, browser.
Everything important lives in a single core written in Rust. The apps on top are thin.
iPhone and iPad
Fully offline: search runs on the Neural Engine, chat with a local model on the GPU. Files come in through the share menu of any app.
Mac
The same app, plus a door for AI agents: Claude Code and others can use the running app through MCP.
Browser
A Linux container in your own network. Nothing to install for users.
Any model
Bring your own AI. Or none from outside at all.
One cockpit for every model connection — each assigned to the job it's good at.
On the device
Apple's built-in model without a download, or models from Hugging Face, searched and loaded inside the app.
Small specialists
Embedding and re-ranking models for search, also offline.
Company gateway
OpenAI-compatible or Azure endpoints behind your own infrastructure.
Cloud, deliberately
Direct providers where allowed — a conscious, per-case choice.
Per-model limits
Requests per minute, token budgets, parallelism — gentle on gateways and budgets.
Only what it can do
Tool use and reasoning are switched on only for models that actually support them.
Built for bad days
Tested against real outages, not sunny days.
Load balancing
Several endpoints as one pool; throttled members are routed around before a fallback model steps in.
Slow gateway? Stream.
When a proxy gets sluggish, the app switches to streaming so the connection doesn't time out.
Retry with judgement
Temporary errors are retried with growing waits; stubborn cases are skipped instead of killing the run.
Fallback model
If a model returns garbage, a backup model takes over — only for that one passage.
Background jobs
Long runs keep going in the background with visible progress; the app stays usable.
Cool-headed
Local models watch the device's temperature and slow down instead of overheating a laptop.
By the numbers
Measured, not felt.
Retrieval quality is tracked with fixed "golden" question sets and expected source passages — quality is judged on those, not on impressions.
Also in Claude Code
The same engine as a Claude Code plugin.
Claude Code can use Matrix as a tool. On 442 pages of EU regulations it answered on average in 42 instead of 126 seconds per question, with less than half the input tokens.
About the pluginWhere it stands
Free on the App Store.
For iPhone, iPad and Mac. Asking and tables work with the model on the device. For the knowledge graph, a local model gives a fast first map and a stronger model the one that holds up. The checks run either way and show where the output can be trusted.
Get it on the App StoreWrite to me