Bypassing ADB: 0.32ms Android UI trees and A* routing for AI agents (Rust/Kotlin A benchmark suite published by the DroidPath project measured its Shadow DOM plus A* spatial-graph router at 0.32 ms steady-state latency for retrieving a 54-node Android UI tree on an unlocked Google Pixel 10a, versus 2,423.9 ms and 29,357 bytes (~7,340 tokens) for an `adb exec-out uiautomator dump` XML loop and 658.1 ms for a raw PNG screencap. DroidPath streams incremental NDJSON accessibility diffs over a persistent loopback TCP socket and executes learned multi-hop paths locally in Rust via A*, reaching 100% success (3/3) on live Settings navigation tasks at an average 603 ms cold-start and 561 ms warm. The project claims the approach is 7,575× faster than uiautomator in steady state and cuts text tokens 2.7× versus the XML hierarchy, with opt-in hybrid vision returning a 38,581-byte JPEG (q45) in 452.33 ms. You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert This benchmark suite compares DroidPath Shadow DOM + Layer 3 A Spatial Graph Router against the two dominant Android automation paradigms used by autonomous AI agents: Pure Vision Screenshot + VLM loop — captures a full-resolution PNG screenshot on every step and sends it to a Vision-Language Model to predict x, y coordinates. Appium / uiautomator dump XML loop — runs uiautomator dump over ADB on every step and feeds the raw XML hierarchy ~25–35 KB to an LLM. DroidPath Shadow DOM + Layer 3 A — streams incremental NDJSON accessibility diffs over a persistent loopback TCP socket android-daemon and executes learned multi-hop paths locally in Rust via A without intermediate LLM turns. Transparency Note: Hardware primitive latencies and End-to-End E2E Settings navigation timings below were measured live over USB ADB on an unlocked Google Pixel 10a 61061JEA307110, Android com.android.settings root screen, 54 live UI nodes using node scripts/benchmark agentic.mjs --mode live --json against compiled target/release/droidpath-mcp. Multi-step Pure Vision and Appium/XML comparisons in the replay table run real droidpath-mcp stdio JSON-RPC calls against a 60-node loopback Shadow DOM daemon paired with explicit token and cost formulas documented under Methodology & Token Model. 1. Live Hardware Probe Unlocked Google Pixel 10a · com.android.settings, 54 Nodes Primitive / Method Status Measured Latency Payload Size Notes DroidPath android get ui tree steady-state ok 0.32 ms 10,742 bytes ~2,686 tok 54 live UI nodes from local Shadow DOM stream 7,575× faster than uiautomator DroidPath android get ui tree cold connect ok 41.89 ms 10,742 bytes ~2,686 tok First TCP connect + live snapshot 58× faster than uiautomator DroidPath Hybrid Vision include vision: true ok 452.33 ms 38,581 bytes JPEG 540×1212 54 live UI nodes + compressed JPEG q45, 6.1× smaller than raw PNG adb exec-out screencap -p raw PNG ok 658.1 ms 235,258 bytes PNG Visual capture only — no structured UI tree adb exec-out uiautomator dump /dev/tty XML ok 2,423.9 ms 29,357 bytes ~7,340 tok Requires stopping UiAutomation daemon; 2.7× more text tokens than Shadow DOM 2. Live End-to-End Hardware Navigation Google Pixel 10a · Real Seed Hydration → Warm A Task Settings → Target Cold-Start Seed Hydration Cold Status Warm A Graph Warm Status Live Success Rate Settings → Display 378.6 ms arrived 296.2 ms 1 step arrived 100% Settings → Battery 655.9 ms arrived 642.8 ms 1 step arrived 100% Settings → About phone scroll required 775.7 ms arrived 744.1 ms 1 step arrived 100% Average across live suite 603 ms 100% 3/3 561 ms 100% 3/3 100% 3. Local MCP Runtime Micro-Benchmarks Measured Metric Measured Value tools/list JSON-RPC latency 9 tools 0.25 ms android graph stats JSON-RPC latency 0.42 ms Pre-hydrated Seed Graph loaded at boot 20 vertices / 19 edges Compact Shadow DOM tree 60-node mock Settings screen Text tokens:ceil utf8 bytes / 4 standard BPE approximation for JSON/XML . Cost / 1,000 tasks: Computed transparently at $3.00 / 1M input tokens standard Claude Sonnet-class API pricing : avg tokens per task 1,000 / 1,000,000 $3.00. Vision image tokens: Anthropic's published W × H / 750 formula for a 1080×2400 Android screenshot scaled to 1568px long edge 706 × 1568 / 750 = 1,477 image tokens + ~350 prompt/tool tokens = 1,827 tokens/step . Opt-in Hybrid Vision include vision: true : Downscaled 540px-wide JPEG quality: 45, measured 38.6 KB on unlocked Pixel 10a Settings vs 235.3 KB raw PNG is strictly opt-in and only used when an agent explicitly needs visual disambiguation e.g., canvas/icons , remaining strictly blocked on FLAG SECURE screens.