I gave a language model hands inside Android — and it built me an app factory

Описание и применение

LLM получает доступ к терминалу Termux и может автономно создавать, собирать и устанавливать Android‑приложения, используя веб‑интерфейс DeepSeek.

Задача

LLM assistants cannot act in the real world; they only produce text that a human must copy and paste.

Результат

The system enables fully autonomous Android app development, from prompt to APK installation, using only a phone and an LLM.

Рабочий процесс

• 1. User runs vibe-run <project> "<task>"
• 2. Script collects project files and builds a prompt with file contents
• 3. Prompt sent to DeepSeek via VibeService /send
• 4. Wait for response stabilization (hash unchanged)
• 5. Parse response and apply file changes
• 6. Build APK using aapt2 → javac → d8 → apksigner
• 7. If build fails, send error log back to model and retry up to 5 times
• 8. On success, install APK via /install-apk

Доказательства

Termux Assistant AI is an Android app that bridges a WebView with DeepSeek Chat and simultaneously gives the assistant direct shell access inside Termux via local HTTP servers.

Источник

The key insight: if I have Termux, I have a shell. And if a language model has a shell, it can run arbitrary commands, work with files, compile code, publish releases.

Источник

If build fails — sends error log back to the model and retries (up to 5 iterations)

Источник