# OpenIntelligence — Chat With Your Files Offline

> Private, searchable knowledge bases with citation-backed Q&A for Apple devices. (iPhone/iPad app by Gunnar Hostetler.)

- Source: https://appshunter.io/ios/app/openintelligence/id6756559175 (this page in markdown: same URL + `.md`)
- Developer: [Gunnar Hostetler](https://appshunter.io/developer/1768599987)
- Category: Productivity, Utilities
- Price: Free with in-app purchases
- Rating: 4.80/5 from 4 App Store ratings · 1 written reviews indexed
- Age rating: 17+
- Requires: iOS 26.0 · 167 MB
- Languages: American English
- Released: 2026-01-30
- Data updated: 2026-09-03
- Monetization: freemium
- User reviews in markdown: https://appshunter.io/ios/app/openintelligence/id6756559175/reviews.md

## What is OpenIntelligence?

You already have the answers. They're just buried in a 300-page manual, a folder of contracts, a semester of lecture recordings, or a codebase you inherited.

OpenIntelligence reads what you import and answers questions about it in plain language, with citations you can tap to see exactly where each claim came from. And when your files don't actually contain the answer, it tells you so instead of guessing confidently.

ANSWERS START IN YOUR FILES

Not in a chatbot's imagination. OpenIntelligence searches your library first, pulls the exact passages that matter, and only then writes, using Apple's on-device Apple Intelligence models. Requires an Apple Intelligence-capable device: iPhone 15 Pro or later, or an M1-or-later iPad or Mac, on iOS/iPadOS/macOS 26. Your device already had the intelligence. This gives it your knowledge, and rules of evidence.

WHAT YOU CAN DO

- Summarize long documents, recordings, or entire libraries.
- Compare claims and details across multiple sources.
- Find exact facts, dates, specifications, measurements, and table values.
- Ask follow-up questions without losing the sources or the thread.
- Choose Standard for quick factual work, Deep Think for multi-step questions, or Maximum for broader evidence synthesis.

BRING YOUR OWN MATERIAL

Import PDFs, Office documents, text and Markdown files, CSVs, code, images and scans, audio, or video. Pages, Numbers and Keynote files need to be exported to PDF first. OpenIntelligence extracts text, uses Vision OCR where needed, transcribes speech, and builds a searchable index for each library.

HOW ANSWERS ARE BUILT

Exact keyword matching and semantic search work together to retrieve the passages that matter. Apple Foundation Models turn those passages into a natural-language response. Then the app checks its own answer against the passages it actually used, so you can inspect what it's standing on instead of taking its word.

If the sources do not establish an answer, the app flags weak support or abstains. No confident filler.

WHERE YOUR FILES GO (AND DON'T)

Reading your files, searching them, and choosing what to cite all happen on your device, start to finish, before anything is written. On-device answers need no connection at all. On a plane, in a dead zone, in a locked-down office, your library still works. Optional Apple Private Cloud Compute support for longer evidence-heavy questions is built and will enable in a future release on iOS and macOS 27; when it does, the app will show you exactly what would be sent and ask you to approve it first. Your material is never sent to a third-party AI provider.

ANSWERS YOU CAN INSPECT

Inline citations connect answers to their supporting pages and passages, one tap from claim to source. If you want more, response details go deeper: source snippets, retrieval quality, verification warnings, timing, and the route that actually produced the answer. The optional telemetry interface goes deeper when you want it and stays out of the way when you don't.

LIBRARIES THAT FIT YOUR WORK

Keep different subjects, projects, or clients in separate libraries. Choose Local Only or iCloud Drive for each library, and organize ongoing research in saved conversation threads. Siri and Shortcuts actions are available for common document and library workflows.

OpenIntelligence is built and maintained by one developer. Pro and Lifetime support directly fund continued development. To everyone already supporting the app: thank you. It has been a wild journey.

Privacy Policy: https://gunzino.me/openintelligence/privacy

## Key features

- Private knowledge base creation
- Citation-backed Q&A
- Supports 50+ file formats
- On-device transcription and indexing
- Hybrid search (keyword & vector)
- Multiple query modes
- Background file ingestion

## Pricing and in-app purchases

Base price: Free.

**Subscriptions**

| Subscription | Price | Period |
| --- | --- | --- |
| Pro Annual | $29.99 | per year |
| Pro Monthly | $5.99 | per month |

**One-time purchases**

| Purchase | Price | Type |
| --- | --- | --- |
| Lifetime Cohort | $59.99 | one-time |
| Document Pack | $2.99 | one-time |


## Recent user reviews (1 of 1)

All indexed reviews: https://appshunter.io/ios/app/openintelligence/id6756559175/reviews.md

### 4/5 — Pretty Incredible for Local LLM

*2026-03-26*

Awesome that it works on iPhone and iPad.  This is what Apple should have done in a sense with Apple Intelligence.

If the dev pivoted to integrate with OpenClaw gateways and also work with Claude Code; this app would be a game changer.

**Developer response:** Hey!  I appreciate the feedback.
As for the OpenClaw/Claude integrations, I could experiment with building a separate layer for it.  I think that’s a great idea.  Perhaps I make a roadmap with a feedback/ideas inbox 🤔

## Frequently asked questions about OpenIntelligence

### What is OpenIntelligence?

OpenIntelligence turns your files into private, searchable knowledge bases with citation-backed Q&A. It's built for Apple devices with Apple Intelligence capabilities, allowing you to import various file types and ask natural language questions.

### What file formats does OpenIntelligence support?

OpenIntelligence supports over 50 file formats, including documents (PDF, DOCX, XLSX, etc.), code (Swift, Python, JS, etc.), audio (M4A, MP3, WAV), and video (MP4, MOV). It extracts text, transcribes speech, and indexes vectors for comprehensive search.

### How does OpenIntelligence ensure privacy?

The app prioritizes local routing over Private Cloud Compute, leveraging the 20B Apple Foundation Model as the primary execution engine. This maximizes privacy and eliminates latency by keeping data processing on your device.

### What are the different query modes in OpenIntelligence?

OpenIntelligence offers three query modes: Standard for fast factual lookups, Deep Think for multi-step reasoning, and Maximum for exhaustive Neural Engine synthesis. It safely prevents auto-escalation to Deep Think loops when using constrained models.

### Does OpenIntelligence have ads?

No, OpenIntelligence does not contain advertisements. The app is free to use with optional subscription plans for enhanced features.

### What are the subscription plans for OpenIntelligence?

OpenIntelligence offers a Pro Monthly subscription for $5.99 and a Pro Annual subscription for $49.99. These plans likely provide access to advanced features or increased usage limits.

### How often is OpenIntelligence updated?

The latest version of OpenIntelligence is 4.4, last updated on June 29, 2026. This indicates a recent update, suggesting active development and maintenance.

### What devices is OpenIntelligence compatible with?

OpenIntelligence is compatible with Mac, iPhone, and iPad devices that have Apple Intelligence capabilities. It utilizes native FoundationModels APIs and hardware-accelerated embeddings on Apple silicon.

## Version history (last 5 releases)

### 5.1 — 2026-09-03

Two releases went out on the Mac that iPhone and iPad never received. This one brings them across, along with the changes made since.


OPENING AND MOVING AROUND

• The Documents tab made you wait while it counted your cached documents. That count fed a single row which stays hidden unless the number is above zero, and on the device this was traced on it was always zero, so the row was never drawn. You waited for a number that was then thrown away. It now loads in the background and the tab opens straight away.

• Switching libraries was the slow thing people actually noticed, and nothing on that path was being measured, so four separate attempts to find the cause had missed it. It is measured now, and faster.

• "Analyzing corpus…" was an empty state wearing a progress spinner. It could never finish, because nothing was running behind it.


THINGS THAT WERE TELLING YOU THE WRONG THING

• The Semantic Atlas labelled a neuroscience paper "API Reference" and "Glossary". The fault was in three separate places, not one.

• Turning the execution profile up removed hardware instead of adding it, and the control itself was a dropdown showing one option while hiding three, on a setting whose only purpose is choosing between them.

• The Deep Think card described a minimum number of reasoning steps that does not exist.

• Temperature stayed adjustable under a sampling mode that ignores it entirely.

• The hardware panel reported a limit of 1,073,741,824 threads, which is 1024 cubed and not a real ceiling. It also now reports free memory rather than a number that looked like it but was not.


DOCUMENTS

• Refreshing one of the built-in samples left the old copy behind, so the library grew a duplicate every time you did it.

• A tag that appears exactly once in a document no longer gets treated as a description of the whole thing.


TEXT RECOGNITION

• The app was asking the system to guess what language each page was written in, on every page, while also handing it a list of thirteen languages. Those two instructions contradict each other, and a wrong guess means your text is corrected against the wrong dictionary, which damages it rather than just slowing things down. The language is now worked out once, from the document itself.

• Page images went to text recognition at the highest possible resolution with no downscaling, which is the slowest setting available. Recognition now scales to what is needed to read the smallest print a real document contains.


IF YOU QUIT MID-IMPORT

• A large PDF interrupted by quitting the app came back showing zero progress, as though the work was gone. It never was: the app resumes from the last page it finished. But the screen said otherwise, and removing the item is the one action that does discard that progress. A resumed import now tells you how far it got.


Everything still runs on your device.

### 5.0 — 2026-08-27

Documents were quietly losing parts of themselves, answers were built from a fraction of what was found, and the app rewrote your library on every launch. This is the fix for all three.


SEARCH

• The part of the app that reads what a passage means was looking at one position instead of the whole thing. It reads all of it now.
• A broken length check returned the same number for every input, so long passages were cut short before they were ever indexed.


ANSWERS

• Deep Think was writing from a fraction of what it found, discarding its own best passages before the first word. It keeps them now, and says what it left out.
• Citations are checked against the real source list. An answer could cite a source number past the end of its own list.
• Deep Think is about three times faster, and stops when it runs out of new material instead of re-reading.


YOUR DOCUMENTS

• Tables in Word documents were read and then thrown away. A file could import looking complete with all of its numbers missing.
• A tag that appears once no longer describes a document. Running headers were being turned into tags.


YOUR LIBRARIES

• A document you import no longer loses its searchability to the app's own housekeeping, which deleted a just-built index and said nothing. It now says so and rebuilds.
• "Remove Local Copies" is now "Remove All Documents", because that is what it did. It deleted from iCloud and your other devices while saying Sync Now could bring them back.
• Changing the embedding model no longer wipes your vectors before you agree to rebuild them.


SPEED

• The app starts faster. A 43 MB model loaded on every launch before anything appeared.
• iCloud stopped re-uploading libraries that had not changed. One launch could rewrite hundreds of megabytes identical to what was there.
• Leaving the chat no longer cancels the answer you were waiting for, and coming back keeps your place.
• The Documents tab stopped waiting on a number it never showed you. It cost up to 393 milliseconds on every open.


YOUR HARDWARE

• Macs were being given iPhone-sized limits. Every Mac below the very top landed in a tier tuned for phones, and base M4 and M5 were demoted again on top of that, costing a 32 GB M5 six times its vector batch.
• Turning performance up was making the app slower at the thing it does most. The four profiles were inverted, so the fastest setting gave the slowest import.
• The performance selector is four cards, each saying which parts of the chip it engages. It was a dropdown hiding three.
• The app understands Apple chips that do not exist yet. An iPhone 17 or M5 no longer reports itself as "A12 or Older", and anything newer scales forward instead of falling back.
• Rotating no longer leaves black rectangles around the floating hardware readout, which now also shows free memory.


SETTINGS

• Settings is a searchable list instead of one long scroll.
• Choose Top-K, Top-P or Greedy. The app used to decide, and always picked the same one.
• Temperature is disabled, with a reason, on the one sampling mode that ignores it.
• Five switches that never controlled anything are no longer switches.


THINGS WE WERE CLAIMING THAT WEREN'T TRUE

• Settings listed eight agentic tools and all eight were wrong. Four are wired up. Those four are what it names now.
• We removed the claim that answers can run on Apple's Private Cloud Compute today. Shipped builds do not contain it yet.
• Pages, Numbers and Keynote were advertised and never worked. They are no longer advertised, and importing one now fails clearly.
• The hardware panel claimed a ceiling of 1,073,741,824 threads. That is 1024 cubed. It was multiplying three limits instead of reading one.
• Deep Think said "6 to 8 reasoning sessions". There is no minimum; it stops when it has what it needs.
• The Atlas was labelling a medical paper "API Reference", matching fragments instead of whole words.
• "Analyzing corpus..." was never analyzing anything. It was a spinner that could not finish.

### 4.9 — 2026-08-05

Deep Think and Maximum were not wired up correctly in previous releases. This release fixes that, and everything it uncovered.


DEEP THINK AND MAXIMUM

• Both modes now reason across your documents. Previously they returned Standard quality answers after a much longer wait.
• Answers cite their sources in every mode. Maximum produced none at all.
• Both stop once they stop finding new material, typically halving Maximum's run time.
• A single failed pass no longer ends a query.
• Resolved "The selected model isn't available right now."


PRIVACY AND ROUTING

• On-Device now covers the entire query, including the final answer.
• The model picker governs every mode. It previously reached Standard only, so Deep Think and Maximum fell back to a default.


WHAT YOU SEE

• The live pipeline names each stage correctly, including verification and query rewriting.
• Reasoning detail wraps instead of cutting off mid-sentence.
• Follow-up suggestions come from the answer rather than stray words.
• Raw model output no longer appears in answers.
• Passes skipped for having no relevant text are shown instead of leaving gaps.
• An answer reporting that your documents do not cover something is kept, not replaced with generic help text.


YOUR LIBRARIES

• Fixed documents disappearing shortly after import. A document that finished importing while the app was saving your library could be dropped from the list, even though it had imported correctly.
• Documents processed on one device no longer need re-importing on another.
• Libraries no longer appear to lose documents while iCloud is still catching up.


ALSO

• Document import works on Mac. The file picker there was a placeholder.
• Opening the app after an update now shows what changed.

### 4.7 — 2026-07-29

This update makes OpenIntelligence more precise about what it tells you.

- Labels now say exactly where each answer ran: on your device, or Apple Private Cloud Compute with your permission. Nothing claims more than the system can verify.
- The key ideas pulled from your documents now come out the same every time, for steadier search and more reliable connections across files.
- New internal checks make sure every answer's recorded route matches what actually ran.

Same goal as always: ask hard questions of your own files, see exactly where every answer came from, and trust what you can verify, not what you're told.

### 4.6 — 2026-07-16

v4.6 is a major Apple Intelligence routing, transparency, reliability, and jargon-reducing update.

EVIDENCE-FIRST MODEL ROUTING:
- OpenIntelligence now searches your library before deciding where an answer should run. The decision uses the evidence actually found, the amount of context required, and whether the question needs synthesis across multiple documents.
- Normal work remains on-device. On supported iOS, iPadOS, and macOS 27 systems, longer evidence-backed requests can use Apple's native Private Cloud Compute when entitlement, availability, network, quota, and consent requirements are satisfied.
- Missing or weak evidence never triggers cloud escalation. The app can stay local or abstain when the library does not contain enough information.

CLEARER CONSENT AND EXECUTION HISTORY:
- Private Cloud Compute consent now happens after the final evidence package is prepared. The confirmation view explains why PCC was selected and shows the number of source passages, context size, and estimated payload size.
- Saved response details now distinguish the intended route, attempted route, route that actually ran, any fallback, and the route that completed the answer.
- Automatic mode can fall back on-device before meaningful response text has streamed. Cloud and local partial answers are never stitched together, and Cloud Only requests report why they could not run instead of silently changing routes.
- Model labels and diagnostics now reflect the Apple model route the public SDK actually executed instead of claiming a selectable model tier that the operating system does not expose.

PRIVATE CLOUD COMPUTE SUPPORT:
- Enabled OpenIntelligence's approved native PCC capability for supported builds and added platform-specific entitlement checks for iPhone, iPad, and Mac.
- Availability and quota are checked again immediately before a PCC session begins. Unknown or unavailable quota states fail safely and do not authorize cloud execution.
- Retrieval, evidence selection, citation checking, and final verification remain on-device even when PCC performs the final synthesis step.

INGESTION THAT RESPECTS STOP:
- Closing or discarding an ingestion queue now records that decision during iCloud reconciliation, preventing those exact jobs from reappearing after a workspace reload or stale sync snapshot.
- Automatic repair of an empty document index now runs one library at a time and stays disabled for a dismissed library on that device until you explicitly import or rebuild again.
- Cancellation waits for a safe document boundary so stopping a repair does not leave half-removed catalog metadata behind.

INDEXING AND EXTRACTION RELIABILITY:
- Knowledge-index migrations now use a fixed, code-owned migration catalog with stricter identifier validation, reducing the risk of malformed database upgrades.
- Document chunk metadata has a deterministic fallback when system language tagging cannot return named entities, keeping retrieval useful in asset-constrained environments.
- Expanded regression coverage now protects model routing, fallback behavior, embeddings, citation parsing, structured answers, ingestion recovery, and launch configuration.

OpenIntelligence is still focused on the same goal since its inception: help users question complex source material, understand how each answer was produced, and return to the evidence when verification is imperative.

## Apps similar to OpenIntelligence

| App | Rating | Price | Category |
| --- | --- | --- | --- |
| [EasyMD - MD reader & editor](https://appshunter.io/ios/app/easymd-md-reader-and-editor/id6761411978) | — | Free | Productivity |
| [Mimi AI](https://appshunter.io/ios/app/mimi-ai/id6760657528) | — | Free | Productivity |
| [ReplyKit : Text Expander](https://appshunter.io/ios/app/replykit-text-expander/id6761647620) | 5.0 (10) | Free | Productivity |
| [Habit Tracker - HabitGate](https://appshunter.io/ios/app/habit-tracker-habitgate/id6758404919) | 4.6 (5) | Free | Productivity |
| [ShortcutStudio - AI Shortcuts](https://appshunter.io/ios/app/shortcutstudio-ai-shortcuts/id6760745118) | 4.1 (17) | Free | Productivity |
| [Open Minis](https://appshunter.io/ios/app/open-minis/id6759188481) | 4.9 (68) | Free | Productivity |

## More apps by Gunnar Hostetler

- [OpenAssistant](https://appshunter.io/ios/app/openassistant/id6692613772)
- [OpenCone](https://appshunter.io/ios/app/opencone/id6744467668)
- [OpenResponses](https://appshunter.io/ios/app/openresponses/id6757338355)

All apps by Gunnar Hostetler: https://appshunter.io/developer/1768599987

## Related topics

[intext](https://appshunter.io/ios/topics/intext)

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-09-03.*