Automates decompiling APK/AAR/JAR and extracting HTTP APIs — Retrofit endpoints, OkHttp calls, hardcoded URLs, and auth patterns — so you can document and reproduce an app's network surface without source code. Integrates jadx/Vineflower/Fernflower and scripts for call-flow tracing.
Generates production-ready App Store and Google Play screenshots from app metadata and style preferences using AI. Scaffolds a Next.js project, composes ad-style slides with localized/RTL support, and exports PNGs at all required Apple and Google resolutions.
Provides modular, AI-optimized SKILL.md instructions that ground LLMs in Android development workflows and can be installed into agent environments via the Android CLI; focuses on tasks where LLMs underperform.
Orchestrates parallel CLI-based AI agents in isolated git worktrees so you can run multiple coding agents side-by-side, review AI-generated diffs, and link PRs/CI to each worktree. Desktop client with a mobile companion and BYO model subscriptions.
Delivers an ultra-efficient, edge-friendly multimodal image-and-video-to-text model optimized for on-device deployment. Uses mixed 4x/16x visual token compression, a low-FLOPs visual encoder, and multiple quantized variants for mobile and embedded inference.
Cross-platform native video editor with hardware-accelerated processing and frame-accurate multi-track timeline; core editor is open-source and free while optional Pro AI features (natural-language editing, auto-captions, smart reframing) are paid.
Multilingual on-device translation model compressed to 1.25-bit via the Sherry quantization, supporting 33 languages and 1,056 directions in a 440MB package for offline mobile translation and demos.
Routes code-based AI agents through repeatable reverse-engineering and pentesting workflows and orchestrates local and remote tools (jadx, Frida, IDA, BurpSuite) so agents can triage APKs, binaries, JS, firmware, and CTFs without guessing the toolchain. Includes master routing rules, tool-index detection, MCP integration, and a field-journal for reusable lessons.
Provides 2,170 reference-grounded evaluation samples across seven agent domains (MCP, Search, Terminal, SWE, Android, Web, OS) to score language world models on Format, Factuality, Consistency, Realism and Quality. Includes per-domain JSONL files, judge prompts and an evaluation script for reproducible scoring.
Provides structured egocentric manipulation signals from smartphone videos: MANO 3D hand reconstructions, metric camera trajectories, and fine-grained atomic action segments (full release ≈2,000 hours planned). Supplies aligned hands.npz, camera_traj.npz, undistorted intrinsics and segment annotations for embodied-learning pipelines.
Designs and evaluates a foundation GUI agent that performs cross-platform GUI and CLI actions on real devices to complete long-horizon workflows. Emphasizes a unified action space, a large-scale real-device mobile runtime, an AutoResearch-style data flywheel, and online RL training across 10,000+ concurrent environments.