# SessionsAI — What do you want to do today?

> On-device private AI chat and image generation with local language models. (iPhone/iPad app by Erich Champion.)

- Source: https://appshunter.io/ios/app/sessionsai/id6758984669 (this page in markdown: same URL + `.md`)
- Developer: [Erich Champion](https://appshunter.io/developer/1849298255)
- Category: Productivity, Utilities
- Price: $0.99 (on sale, was $4.99)
- Rating: 5.00/5 from 2 App Store ratings
- Age rating: 4+
- Requires: iOS 26.0 · 87 MB
- Languages: American English
- Released: 2026-02-27
- Data updated: 2026-09-05
- Monetization: paid
- User reviews in markdown: https://appshunter.io/ios/app/sessionsai/id6758984669/reviews.md

## What is SessionsAI?

Sessions AI is a private AI workspace that runs entirely on your iPhone, iPad, or Mac. Not just a chat
box: it uses real tools, works from your own documents, and creates images—all on device, with no
account and no cloud.

More than a chat box

Most on-device AI apps just run a model. Sessions AI gives the assistant real tools and lets it do the
work: calculate, convert units, look things up on Wikipedia, check your calendar, add reminders, search
the web, fetch a page, generate an image. Ask for something involved and it writes a plan first—which
you can read, edit, and approve before it spends a moment of compute. You see every step it takes.

Ask by voice, or from a Shortcut

Say "Start a chat in Sessions AI" to Siri and speak your question—it opens the app and lands the answer
in a real conversation you can carry on. The Ask Sessions AI action appears in Spotlight and the
Shortcuts app too, so you can build it into your own workflows.

Ground answers in your own knowledge

Give a persona its own private knowledge base—add documents from a file or a URL, including Word, RTF,
and PDF. When you ask a question, Sessions AI searches that content on device and bases its answer on
it, and shows you which passages it used. Nothing is uploaded; indexing and search happen locally.

Personas that keep work separate

Set up a persona for each kind of work, each with its own system prompt, knowledge base, and connected
tools. Switch per chat. Research stays separate from writing, and work stays separate from home.

Bring your own tools (MCP)

Connect Model Context Protocol servers and their tools appear right in your chat, alongside the built-in
ones. Add custom HTTP headers for authentication, stored securely in the Keychain. It's your
workspace—extend it however you like.

Create images on device

Ask the assistant to draw, sketch, or visualize—and it generates images right on your device, no cloud
APIs. Choose from fast models like Stable Diffusion XL Lightning and Z-Image Turbo through to
higher-quality ones like FLUX.2 Klein, with larger models such as Qwen Image on high-memory Macs. Watch
a live preview as it draws, start from one of your own photos with image-to-image, and reuse the seed
shown with each result to reproduce or vary it. Browse everything you've made in a built-in Gallery.

Your chats are yours

Every conversation is saved on your device as a plain Markdown file you can open in the Files app—no
proprietary format, no lock-in, no export button needed. Pin, rename, group, and search across every
chat by name or content.

Your model, your choice

Sessions AI runs open language models in a range of sizes—Gemma, Qwen, Ministral, Mistral, and Ternary
Bonsai families among them. Pick a small, fast model for quick answers or a larger one for harder work,
and set a different model per conversation. Download only what you need; remove any model to free space.

Made for every screen

Designed for iPhone, iPad, and Mac, with full Dark Mode support. On iPad and Mac, a roomy sidebar lets
you group and pin chats and jump
between your models and Gallery; on iPhone, a simple tab bar keeps everything a tap away.

Built for privacy

Chat transcripts, the knowledge base, and all model data stay on your device. Language models and image
generation both run locally—nothing you type is sent to the cloud for AI processing. Calendar and
reminder access are used only on device to answer your questions. Web search is optional; when enabled,
only the search query is sent to the provider (e.g. DuckDuckGo), not your full conversation. No
telemetry, no analytics, no account—just you and your device.

Who it's for

Sessions AI is for anyone who wants a capable AI workspace without handing their work to the cloud.
Whether you care about privacy, work offline, or simply prefer to own your data, it gives you a full
assistant that runs where you do: on your own device.

## Key features

- On-device AI processing
- No cloud servers or accounts
- Local language model execution
- On-device image generation
- Private knowledge base integration
- Offline functionality


## Frequently asked questions about SessionsAI

### What is SessionsAI?

SessionsAI is a private AI chat application that runs entirely on your iPhone, iPad, or Mac. It processes all conversations and data locally on your device, ensuring maximum privacy and control.

### Does SessionsAI require an internet connection?

No, SessionsAI is designed to work offline. All AI processing, including language model execution and image generation, happens on your device without needing to send data to the cloud.

### How does SessionsAI ensure privacy?

SessionsAI guarantees privacy by running all operations on your device. Your conversations, data, and any generated content never leave your device, meaning no third-party access or cloud-based training on your chats.

### Can I use my own documents with SessionsAI?

Yes, you can add your own documents to a private knowledge base within SessionsAI. The app can then use this content to ground its answers, all processed locally on your device.

### What devices does SessionsAI support?

SessionsAI is available for Mac, iPhone, and iPad, allowing you to use its private AI capabilities across your Apple ecosystem.

### How much does SessionsAI cost?

SessionsAI is a paid application, available for a one-time purchase of $4.99. This price grants you full access to its features without ongoing subscriptions or data-sharing requirements.

### How often is SessionsAI updated?

SessionsAI was last updated on April 17, 2026, with version 1.0.2. This indicates a commitment to ongoing development and improvements for the application.

### What is the age rating for SessionsAI?

SessionsAI has an age rating of 4+, making it suitable for a wide range of users. This rating suggests it contains content generally considered appropriate for young children.

## Version history (last 5 releases)

### 1.2.0 — 2026-08-27

Cancel Actually Cancels
- Stop a model while it loads: Cancel now interrupts loading a multi-gigabyte model, not just the
  reply that follows it.
- Stop a long prompt: Cancelling during the "reading your prompt" stage takes effect immediately
  instead of waiting for it to finish.
- Stop an image mid-draw: Image generation now aborts partway through and gives the memory straight
  back. Cancelling is treated as something you meant to do — no error alert, no Retry button.

You Can See What It's Doing
- Loading progress for big models: A large model now shows "Loading model… 42%" instead of "Thinking…"
  for minutes on end.

More Room to Think
- 1.5× more context on 8 GB iPhones and iPads: 8192 → 12288 tokens, from two memory corrections rather
  than optimism — enough for noticeably longer documents and conversations.

Better Answers from the Same Models
- Models now follow their own recipe: A model can carry the sampler settings its author recommends
  inside the model file, instead of every model sharing one profile.
- Correct prompt formatting: The special tokens that structure a conversation are handled as tokens
  rather than as ordinary text, which is how the models were trained to see them.

Image Generation, Corrected
- Your photos keep their shape: Image-to-image preserves the subject's proportions instead of
  stretching everything to a square, and respects the orientation your phone recorded — portraits no
  longer come back rotated and cropped.
- Reproducible images: The seed appears with the result, so you can recreate an image or vary it
  deliberately.
- Smoother previews: Live previews no longer run a full decode on every single step.

A Smaller, Newer Model Catalog
- Gemma 4 E4B joins, alongside Gemma 4 E2B — and Gemma 4 is now Apache-2.0 licensed.
- Older models retired: Gemma 3, Phi-4 mini, Ministral 3 8B and Mistral Nemo Prism are no longer
  offered to new installs. Anything you have already downloaded keeps working; retired models stay in
  your list until you delete them.
- 12 text models offered, down from 16 — chosen so each one covers a device class the others do not.

More Reliable Tools
- Tool parameters from MCP servers now carry their descriptions and numeric limits through to the model,
  union-typed and combined-schema parameters are no longer dropped, and a tool that takes no arguments no
  longer has one invented for it.

Privacy & Stability
- Prompt-injection defences now derive their markers from the model's own vocabulary rather than a fixed
  list.
- A build-time guard fails the release if the shipped image engine is not the exact version the build
  pins, and a data race in image-model downloads is fixed.

### 1.1.1 — 2026-08-10

A big update: new image engine, a fresh design, and more models

• Faster on-device images — A new Stable Diffusion engine runs fast image models like SDXL Lightning and Z-Image Turbo right on iPhone. Watch a live preview as it draws, and guide results with image-to-image, seeds, and negative prompts.  
• Browse your creations — A new Gallery collects every image you've made; open any one full-screen and jump back to its chat.  
• Redesigned everywhere — A fresh look across iPhone, iPad, and Mac with Dark Mode, first-run onboarding, and a roomy sidebar for grouping and pinning chats.  
• More models — Added Gemma, Qwen, Llama, Ministral, and Phi families. Set a different model or persona for each chat.  
• Smarter, snappier chat — More reliable tools on small models, richer Markdown, and faster first replies.  
• More document types — Add documents from a file or a URL, now including Word, RTF, and PDF.  
• Connect your tools — Add custom HTTP headers for MCP servers, stored securely in the Keychain.

Thank you for trying Sessions AI. We hope it helps you get more done without giving up your privacy.

### 1.1.0 — 2026-06-23

On-Device Image Generation
- Fast image models on iPhone: A new in-process Stable Diffusion engine runs GGUF image models directly on iOS — no cloud, no APIs. SDXL Lightning generates in just a few steps for quick results.
- A bigger model lineup: Choose from Stable Diffusion, SDXL Lightning, Z-Image Turbo, and FLUX.2 Klein, plus Qwen Image on high-memory Macs. A lightweight Stable Diffusion 1.5 option fits 4 GB-RAM devices.
- Watch it draw: See live previews and phase-aware progress as an image is generated, with the generation time and model name shown right in the chat.
- More creative control: Guide results with image-to-image, a seed for reproducibility, and negative prompts.
- A real Gallery: Browse everything you've created in a cross-platform Gallery, open any image full-screen, and jump back to the chat that made it.
- Respects your device: Image generation is offered only when it can fit in memory alongside your language model, and pauses when the app is backgrounded.

Redesigned Across iPhone, iPad & Mac
- A fresh look: A new design system with full system dark-mode support.
- Built for each device: A floating tab bar on iPhone, and a grouped, pinnable sidebar with quick access to Models, Gallery, and Settings on iPad and Mac.
- Easy first run: New onboarding welcomes you and helps you pick and download your first model.
- Per-chat models and personas: Set the model and persona for each conversation, shown as chips while you compose. Settings are now organized as "Personas."
- Better reading: Richer Markdown rendering for headings, lists, quotes, code, and inline formatting.
- More control over chats: Edit a chat or delete an individual prompt and its reply.

More Models & Faster Replies
- New model families: Added Gemma, Qwen3 and Qwen3.5, Llama 3.2 and 3.3, Ministral, and Phi-4-mini, with clear labels for deprecated models.
- Reliable tools on small models: Smaller models now call tools far more reliably, so features like calculator, search, calendar, and image generation work even on compact models.
- Snappier responses: Models pre-warm when you open a chat, and conversation context is reused between turns for faster replies.

Documents & Knowledge
- Add documents from a URL: Pull in a web page or document by URL — for a single chat or for your persona's knowledge base — and review the extracted text before adding it.
- Rich-text support: Attach and ground answers in Word (.docx), RTF/RTFD, and ODT documents, all parsed on device.

Tools & Connections (MCP)
- Custom headers for MCP servers: Add custom HTTP headers (such as API keys) when connecting to MCP servers; header values are stored securely in the Keychain.
- Built-in tools always available: Connecting an MCP server no longer hides the app's built-in tools.
- Better-grounded answers: Web search and page fetching pull in more content and stick to it, reducing made-up details, with more reliable handling of long results.

### 1.0.2 — 2026-04-17

Performance Improvements
- Faster Image Generation: Core ML models now use optimization hints that prioritize inference speed for Stable Diffusion models
- macOS GPU Optimizations: Enabled FP16 accumulation on GPU for faster image generation on Mac devices

Code Quality
- Cleaner Code: Refactored trace reading and model configuration into reusable, well-documented methods

### 1.0.1 — 2026-03-12

New Features:
- Help Menu: Access documentation directly from the app via the new Help menu item

Bug Fixes:
- Fixed a crash that could occur on older iPad Pro models (3rd generation) during Metal operations
- Fixed chat list search functionality

Performance:
- Improved memory management for image models and image generation based on your device's available RAM

## Apps similar to SessionsAI

| App | Rating | Price | Category |
| --- | --- | --- | --- |
| [Voice Record Pro 7](https://appshunter.io/ios/app/voice-record-pro-7/id810588885) | 4.7 (1,142) | Free | Productivity |
| [Granola - AI Meeting Notes](https://appshunter.io/ios/app/granola-ai-meeting-notes/id6739429409) | 5.0 (11,765) | Free | Productivity |
| [HyNote: AI Note Taker, Summary](https://appshunter.io/ios/app/hynote-ai-note-taker-summary/id6478655348) | 4.8 (7,301) | Free | Productivity |
| [Google AI Edge Eloquent](https://appshunter.io/ios/app/google-ai-edge-eloquent/id6756505519) | 3.3 (9) | Free | Productivity |
| [Obsidian Web Clipper](https://appshunter.io/ios/app/obsidian-web-clipper/id6720708363) | 4.4 (98) | Free | Productivity |
| [Magnit VMS Mobile](https://appshunter.io/ios/app/magnit-vms-mobile/id421031585) | 3.7 (594) | Free | Productivity |

## More apps by Erich Champion

- [ElectroSpotmatic](https://appshunter.io/ios/app/electrospotmatic/id6754665552)
- [2G](https://appshunter.io/ios/app/2g/id6754823221)
- [Spotmatic Magic](https://appshunter.io/ios/app/spotmatic-magic/id6756294043)
- [Sell in May](https://appshunter.io/ios/app/sell-in-may/id6757163635)
- [Aperio Ephemeris](https://appshunter.io/ios/app/aperio-ephemeris/id6757413246)

All apps by Erich Champion: https://appshunter.io/developer/1849298255

---

*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 2026-09-05.*