Sanju Sivalingam 610fd04818 10x improvement: vision, multi-turn memory, planning, streaming, smart filtering, logging ...

- Auto-detect screen resolution and compute dynamic swipe coordinates
- Detect foreground app each step via dumpsys activity
- Smart element filtering: deduplicate by position, score by relevance, compact to essentials
- Session logging with crash-safe .partial.json writes and final summary
- Real multimodal vision: send base64 screenshots to LLMs (off/fallback/always modes)
- Multi-turn conversation memory: maintain full chat history across steps with trimming
- Multi-step planning: think/plan/planProgress fields on every LLM decision
- Streaming responses for all 4 providers (OpenAI, Groq, OpenRouter, Bedrock)
- Comprehensive README with examples, architecture docs, and troubleshooting

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-06 10:32:58 +05:30

android-action-kernel

10x improvement: vision, multi-turn memory, planning, streaming, smart filtering, logging

2026-02-06 10:32:58 +05:30

.gitignore

Remove root .DS_Store and add root .gitignore

2026-02-06 09:06:56 +05:30

CLAUDE.md

Add CLAUDE.md and README.md documentation

2026-02-06 09:04:06 +05:30

Description

turn old phones into ai agents - give it a goal in plain english. it reads the screen, thinks about what to do, taps and types via adb, and repeats until the job is done.

2 MiB

Languages

TypeScript 48.1%

Kotlin 32.8%

HTML 9.1%

Svelte 8.6%

Shell 1%

Other 0.3%