nikivdev / nikivdev/privacy-respecting
Add Pocket AI to AI Assistants: on-device LLM chat for iPhone (iOS, closed-source)
Nobody has claimed this yet.
- Dominant language
- No language data
- Stars
- 2.1k
- Forks
- 108
- PR merge metrics
- No merged PRs in 30d
Description
The AI Assistants section is currently one entry, and it is a smart-speaker project. Adding a phone option, since "an assistant that does not send my prompts anywhere" seems to be what this list gets asked for most.
Pocket AI runs open-weight models on iPhone through llama.cpp with Metal: Qwen, Llama, DeepSeek, Mistral, Phi, Gemma and SmolLM, 28 in total. No account, no login, no chat server, and it works with no connection at all. Version 3.1 ships no analytics SDK. The one optional in-app purchase is processed by Apple, with RevenueCat seeing an anonymous identifier only. Whisper voice input also runs on-device, and that one is part of the paid unlock.
Being upfront about the trade-offs: it is closed source, it is iOS only, and it needs an iPhone 12 or newer. It is free with one optional $4.99 one-time unlock and no subscription. It currently sits at 2.8 stars from 6 App Store ratings. Two of the three written reviews are against a four-month-old version, but I am not going to dress that number up.
Disclosure: I am the developer. Reword or remove freely, and I am happy to send this as a PR instead if you prefer that.
App Store: https://apps.apple.com/us/app/pocket-ai-no-internet/id6759989702
Site: https://pocket-ai-iota.vercel.app/
Suggested line for the AI Assistants section:
- Pocket AI - iPhone app running open-weight LLMs (Qwen, Llama, DeepSeek, Mistral, Phi, Gemma, SmolLM) fully on-device via llama.cpp. No account, no server, works offline. Closed source, free with an optional one-time unlock.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the repository's AI Assistants section and compare its existing entry format with the suggested Pocket AI line and linked App Store and site pages. Add the listing with its privacy and platform details, then verify the links and formatting in the rendered list.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, ios
- Domain
- ai, documentation, mobile-dev
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 75/100