v0.6.22
SaschaHeyer/gen-ai-livestreamv0.6.22Oct 5, 2026by RasulOs
Upgrading?
AI Summary
This release introduces a folder restructuring for app cards and updates Portal installation logic to pin specific versions.
Key Highlights
- App cards moved to platform-specific folders (`android/app_cards.json` and `ios/app_cards.json`)
- Portal auto-setup now pins version 0.7.25 for the specific mobilerun version
- Logs warnings for ignored flat app cards
Breaking Changes
- App card folder structure changed: a single `app_cards.json` directly in `app_cards_dir` is no longer read.
New Features
- Portal version pinning during auto-setup
Full Release Notes
## Breaking change: app card folders App cards are now read from one folder per platform: `<app_cards_dir>/android/app_cards.json` and `<app_cards_dir>/ios/app_cards.json`. A single `app_cards.json` directly in `app_cards_dir` is no longer read; Mobilerun logs `Ignoring <path>` for it. Move the file and its cards into `android/` (and add an `ios/` folder for iOS bundle ids). ## Portal `mobilerun setup` and Portal auto-setup now install the Portal version pinned for your mobilerun version (0.7.25). Auto-setup upgrades an older Portal in place, keeping its settings, and leaves a newer one alone. ## What's Changed * fix: SDK debug logging, per-platform app cards and the Portal version pin by @RasulOs in https://github.com/droidrun/mobilerun/pull/474 * fix: warn on ignored flat app cards and keep a newer Portal in doctor by @RasulOs in https://github.com/droidrun/mobilerun/pull/476 * chore: require mobilerun-core-local 0.6.1 by @RasulOs in https://github.com/droidrun/mobilerun/pull/475 * chore(release): 0.6.22 by @RasulOs in https://github.com/droidrun/mobilerun/pull/477 * chore: merge develop into main for 0.6.22 by @RasulOs in https://github.com/droidrun/mobilerun/pull/478 **Full Changelog**: https://github.com/droidrun/mobilerun/compare/v0.6.21...v0.6.22
Related Repositories
rasbt/LLMs-from-scratch★ 107,095
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
lyogavin/airllm★ 40,274
AirLLM 2.8T LLM inference with single 4GB GPU
NirDiamant/RAG_Techniques★ 29,967
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
microsoft/OmniParser★ 25,540
A simple screen parsing tool towards pure vision based GUI agent
karpathy/nn-zero-to-hero★ 24,911
Neural Networks: Zero to Hero