diff --git a/README.md b/README.md index 5f968dc..9d489d7 100644 --- a/README.md +++ b/README.md @@ -3,16 +3,18 @@

- ARTEMIS: Autonomous AI Assistant for Mobile Automation + ARTEMIS: Next-Gen AI Mobile Test Automation & Autonomous Assistant Platform
+ Autonomous Real-time Testing, Exploration & Mobile Interaction System

- ⚡ Drive real phones from Cursor & Claude Code • Cross-App Automation • Zero-Maintenance UI Testing • Flash Mode as Fast as 3-5s + ⚡ Drive Real Devices from Antigravity & Claude Code • Cross-App Automation • Zero-Maintenance UI Testing • Bug Repro & Logcat Diagnostics

English • 中文文档 • + Workflow Showcase • Quick Start • MCP for IDEs • Benchmarks • @@ -36,12 +38,45 @@ ## ✨ Key Highlights -* ⚡ **Lightning Fast**: First-of-its-kind **Optimistic Asynchronous Pipeline** decouples the foreground execution stream from heavy LLM reasoning; -* 🔋 **Ultra-Long Autonomous Execution**: **Pro mode** runs stably for over 10 hours, while monitoring tasks support around-the-clock 24/7 execution; -* 🔌 **Native Model Context Protocol (MCP)**: Empowers **Cursor, Claude Code, OpenClaw, Windsurf** with direct mobile device manipulation from within your chat prompts; -* 💾 **Visual Console & Persistent Debugging**: Real-time Web UI screen projection, execution replay, and task management with natural language test generation and high-fidelity historical review; +* 🤖 **Cross-App Automation & Autonomous AI Assistant**: Operates not just as a robust testing framework, but as an autonomous agent capable of handling complex cross-app workflows and daily tasks via natural language; +* 🧪 **Zero-Maintenance UI Test Automation**: Built upon a "Dynamic-First, Coordinate-Fallback" multimodal locating engine, eliminating fragile XPath/ID selector maintenance and remaining resilient to UI redesigns, system updates, and resolution drift; +* 🐞 **One-Click Bug Repro & Logcat Diagnostics in IDE**: Native **Model Context Protocol (MCP)** integration allows **Antigravity, Claude Code, and Windsurf** to drive physical test devices via natural language, automatically capturing crash stacks from **Logcat** and keyframe screenshots; +* ⚡ **Ultra-Fast Execution (3–5s per Step)**: Pioneered an **Optimistic Asynchronous Pipeline** that completely decouples UI interaction from heavy LLM reasoning, achieving rapid regression throughput in Flash mode; +* 🛡️ **Popup Self-Healing & 10+ Hour Exploration**: Proprietary **Safety Net** double-checks targets before action execution to intercept and clear interfering system popups; Pro mode supports **10+ hours** of continuous exploratory & monkey-plus stability testing; * 🏆 **Industry-Leading SOTA**: Achieved **99%+ task completion** on Google Research's **AndroidWorld** benchmark (100+ complex multi-step tasks). + +## 🤝 Antigravity × ARTEMIS: Autonomous Testing Workflow + +Experience seamless collaboration between **Antigravity** and **ARTEMIS** via native MCP integration — taking you from a natural language requirement to a production-grade diagnostic report in four automated steps: + + + + + + + + + + +
+ 1️⃣ Prompt Input (Task Dispatch)
+ Describe your test scenario and target metrics in Antigravity

+ Step 1: Prompt Input in Antigravity + 		+ 2️⃣ Test Plan Generation
+ Antigravity formulates a step-by-step test plan & architecture for review

+ Step 2: Test Plan Generation +
+ 3️⃣ Autonomous Test Execution
+ ARTEMIS drives the real device, navigates UI, and profiles performance

+ Step 3: Autonomous Test Execution + 		+ 4️⃣ Comprehensive Final Report
+ Delivers structured audit findings, metric tables, and raw datasets

+ Step 4: Final Report +
+ ## ⚡ Quick Start @@ -64,7 +99,7 @@ start.bat

-🔌 MCP Setup for Cursor / Claude Code / Windsurf (Click to expand) +🔌 MCP Setup for Antigravity / Claude Code / Windsurf (Click to expand)
@@ -75,14 +110,14 @@ ARTEMIS includes a native **Model Context Protocol (MCP)** server. Connect your Run the built-in generator to produce ready-to-use JSON configuration: ```bash -artemis mcp --generate-config cursor +artemis mcp --generate-config antigravity # Or generate configs for all IDEs: artemis mcp --generate-config all ``` ### 2. Copy Config to Your IDE -* **Cursor** (`.cursor/mcp.json` or Settings ➔ MCP Servers): +* **Antigravity** (MCP config file or Settings ➔ MCP Servers): ```json { "mcpServers": { @@ -112,7 +147,7 @@ artemis mcp --generate-config all ``` ### 3. Prompt Your Phone in the IDE Chat -In Cursor or Claude Code, simply prompt: +In Antigravity or Claude Code, simply prompt: > 💬 *"Build the latest changes into an APK, install it on the connected device, open the login screen with a test account, verify if there are any unexpected popups after login, and return screenshots of the final page."*
@@ -131,15 +166,17 @@ from artemis.interfaces.sdk import ArtemisClient async def main(): - # Initialize client (choose "flash" for speed or "pro" for deep reasoning) + # Initialize client (choose "flash" for fast UI checks or "pro" for deep reasoning & self-healing) client = ArtemisClient(default_profile="flash") - # Run autonomous task - result = await client.run("Open calculator and compute (128 * 45) + 330") + # Execute natural language end-to-end test case + result = await client.run( + "Open System Settings, go to 'Battery', verify battery percentage is displayed, and check for any crash dialogs." + ) - print(f"Status: {result.status}") - print(f"Turns taken: {result.turns}") - print(f"Trace ID: {result.trace_id}") + # Structured assertions & execution tracing + assert result.status == "SUCCESS", f"Test failed: {result.failure_reason}" + print(f"✅ Test Passed! Turns: {result.turns} | Trace ID: {result.trace_id}") if __name__ == "__main__": @@ -156,20 +193,20 @@ if __name__ == "__main__": 💡 Console Overview: ① View Switcher (Home / Workspace) · ② Model & Replay (Flash/Pro status & video replay) · ③ Live Agent Stream (Action perception, target coordinates & structured results) · ④ Prompt Dock (Natural language dispatch) · ⑤ Task Queue & Dashboard (Lifecycle & history)

-* 🖥️ **Web Visual Console (`artemis ui`)**: Real-time screen projection and interactive panel, supporting natural language task dispatch, live reasoning telemetry, action trajectories, and execution replay; -* 🔌 **Native MCP Protocol (IDE Integration)**: Operates as a standard MCP server seamlessly integrating with **Cursor, Claude Code, OpenClaw**, etc., directly invoking mobile device manipulation inside the IDE; -* 💻 **Developer CLI (`artemis run`)**: Direct terminal execution for automated tasks, test cases, or AndroidWorld benchmarks with high-fidelity structured terminal output; -* 🐍 **Python SDK**: Integrates as a standard Python library into existing automated testing frameworks or pipelines with strongly typed Pydantic structured outputs. +* 🖥️ **Web Visual Test Console (`artemis ui`)**: Real-time screen projection and interactive panel, supporting natural language test dispatch, live reasoning telemetry, action trajectories, and execution replay; +* 🔌 **Native MCP Protocol (IDE Collaboration)**: Operates as a standard MCP server seamlessly integrating with **Antigravity, Claude Code, Windsurf**, etc., directly driving real devices inside the IDE to verify bugs and run test cases; +* 💻 **Developer CLI (`artemis run`)**: Direct terminal execution for automated test cases, exploratory stability inspection, or AndroidWorld benchmarks with high-fidelity structured terminal output; +* 🐍 **Python SDK**: Integrates as a standard Python library into existing automated testing frameworks (e.g., pytest) or CI/CD pipelines with strongly typed Pydantic structured outputs and assertion support. ## 📊 Head-to-Head Comparison -| Scenario / Dimension | Traditional Automation | Generic Screen AI Agents | **ARTEMIS ☕** | +| Evaluation Dimension | Traditional Test Automation (Appium / Maestro) | Generic Mobile VLM Agents | **ARTEMIS ☕ (Next-Gen AI Testing)** | | :--- | :--- | :--- | :--- | -| **Natural Language Execution** | ❌ Rigid hard-coded scripts only | ⚠️ Sluggish (waits 20-30s per tap) | ⚡ **High Throughput**: As fast as 3–5s per step in Flash mode with fluid responses | -| **UI Redesign Resilience** | ❌ Layout changes break XPath selectors | ⚠️ Coordinate guessing leads to drift | 🎯 **Semantic Grounding**: Blends text, icons & UI tree structure to adapt to UI changes | -| **Popup Interception** | ❌ Blocked and crashed immediately | ❌ Loops endlessly on unfamiliar screens | 🩹 **Pre-Execution Self-Healing**: Verifies target state before clicking; dismisses popups | -| **Dynamic & Video Tasks** | ❌ Blind static sleep only | ❌ Blind to dynamic video playback | ⏱️ **Real-Time Multimedia**: Live video stream analysis, countdown timers & speculative chaining | -| **IDE & Tooling Integration** | ❌ Standalone test runner | ❌ Web-only with high integration friction | 🔌 **Native MCP Server**: Directly callable inside Cursor, Claude Desktop, etc. | +| **Test Case Maintenance** | ❌ Fragile XPath/ID dependencies; UI changes cause test failures | ⚠️ Unreliable execution; cannot be reused as regression tests | 🧪 **Zero Maintenance**: Natural language test cases resilient to UI drift & redesigns | +| **Execution Latency & Throughput** | ⚡ Fast script execution, but extreme setup and locator debugging costs | ❌ Sluggish 20–30s per step; too slow for regression testing | ⚡ **High Throughput**: Optimistic Async Pipeline runs at 3–5s per step | +| **Popup Resilience & Self-Healing** | ❌ System popups or permissions immediately crash the script | ❌ Easily gets stuck or loops endlessly on unexpected dialogs | 🛡️ **Pre-Execution Safety Net**: Automatically intercepts and clears interfering popups | +| **Diagnostics & Multimedia** | ❌ Blind static waits (sleep); cannot assert dynamic video/animations | ❌ Static screenshots only; no system logs or underlying state | 🐞 **Deep Diagnostics**: Live video stream analysis & **Logcat crash stack capture** | +| **Dev Environment Integration** | ❌ Standalone runner; requires manual log collection upon failure | ❌ Isolated web demos; difficult to embed into dev pipelines | 🔌 **Native MCP & SDK**: Drive physical test devices and debug directly inside Antigravity / Claude Code | ## 🏆 Benchmarks: AndroidWorld (SOTA 99%+) @@ -230,7 +267,7 @@ Evaluated on [AndroidWorld](https://github.com/google-research/android_world) - [x] **Optimistic Asynchronous Pipeline**: Ultra-lean main loop + background context compression & milestone checks. - [x] **Pre-Execution Safety Net**: Millisecond pre-check gate & speculative chained actions. - [x] **Time-Sensitive Media Tasks**: Fullscreen video and audio stream analysis with `scrcpy` & `ffmpeg`. -- [x] **Native MCP Server**: Seamless integration with tools like Cursor and Claude Desktop. +- [x] **Native MCP Server**: Seamless integration with tools like Antigravity and Claude Desktop. - [x] **Web Visual Console**: Live screen projection, interactive playground, and trajectory review. - [x] **AndroidWorld SOTA**: Achieved 99%+ task completion rate. - [ ] **Cross-Platform Extensions**: Exploring iOS and desktop Web perception and execution. diff --git a/README_CN.md b/README_CN.md index cdc32c1..520a5ed 100644 --- a/README_CN.md +++ b/README_CN.md @@ -3,16 +3,18 @@

- ARTEMIS: 全自动操控手机的 AI 个人助理 + ARTEMIS: 下一代 AI 驱动的移动端自动化测试与个人助理平台
+ Autonomous Real-time Testing, Exploration & Mobile Interaction System

- ⚡ 让 Cursor / Claude Code 接管真机 • 跨 App 复杂自动化 • 零脚本维护 UI 测试 • Flash 模式单步最快 3-5 秒 + ⚡ 让 Antigravity / Claude Code 接管真机 • 跨 App 复杂自动化 • 零脚本维护 UI 测试 • 智能 Bug 复现与 Logcat 诊断

English • 中文文档 • + 全流程演示 • 快速上手 • MCP 接入 IDE • 基准评测 • @@ -36,11 +38,45 @@ ## ✨ 核心亮点 -* ⚡ **极致响应速度**：首创**全链路乐观异步流水线 (Optimistic Async Pipeline)**，主干执行流与后台重度推理完全解耦； -* 🔋 **超长程稳定运行**：**Pro 模式**可运行超 10 小时，监控任务甚至可以全天候运行； -* 🔌 **原生 MCP (Model Context Protocol) 赋能**：让 **Cursor、Claude Code、OpenClaw、Windsurf** 直接长出“操作真机的双手”，在聊天窗口一句话完成真机测试与 Bug 复现； -* 💾 **可视化控制台与持久化调试**：提供 Web UI 实时投屏、操作回放与任务持久化管理，支持通过自然语言生成测试用例，并对历史执行进行高保真可视化审查； -* 🏆 **业界顶尖 SOTA**：在 Google Research **AndroidWorld** 基准评测（100+ 复杂长程任务）中取得 **99%+ 任务完成率**。 +* 🤖 **跨 App 复杂自动化与 AI 个人助理**：不仅能执行严格的自动化测试用例，更具备接管真机的自主决策与长流程操作能力，一句话处理跨应用复杂业务与任务； +* 🧪 **零脚本维护 UI 自动化测试**：基于“动态优先、坐标兜底”的多模态语义定位，彻底告别传统 XPath / 控件 ID 频繁失效的痛点，无惧 App 改版、分辨率差异与系统升级； +* 🐞 **IDE 内一键 Bug 复现与 Logcat 诊断**：原生支持 **MCP 协议**，可在 **Antigravity、Claude Code、Windsurf** 中直接用自然语言驱动真机复现缺陷，自动抓取关键帧截图与 **Logcat 崩溃堆栈**，完成研发测试闭环； +* ⚡ **极速执行吞吐（单步 3–5 秒）**：首创**全链路乐观异步流水线 (Optimistic Async Pipeline)**，解耦重度推理与页面操作，在 Flash 模式下实现丝滑的高频交互与快速回归验证； +* 🛡️ **干扰弹窗自愈与超长程巡检**：独创 **Safety Net** 执行前校验机制，自动识别并清除系统权限弹窗、通知遮挡等异常；Pro 模式支持连续 **10+ 小时** 无人值守稳定性巡检与探索性测试 (Exploratory / Monkey-plus Testing)； +* 🏆 **业界顶尖 SOTA**：在 Google Research **AndroidWorld** 基准评测（100+ 复杂长程系统与应用交互任务）中取得 **99%+ 任务完成率**。 + + + +## 🤝 Antigravity × ARTEMIS：全流程自主测试演示 + +通过原生 MCP 协议，**Antigravity** 与 **ARTEMIS** 深度协同——只需一句自然语言指令，即可自动完成从需求理解、测试规划、真机执行到深度报告输出的完整闭环： + + + + + + + + + + +
+ 1️⃣ 输入测试提示词 (Task Dispatch)
+ 在 Antigravity 中用自然语言描述测试需求与目标指标

+ 步骤一：输入测试提示词 + 		+ 2️⃣ 生成测试方案 (Test Plan Generation)
+ Antigravity 自动拆解任务，生成详细测试步骤与架构图供确认

+ 步骤二：生成测试方案 +
+ 3️⃣ 自主执行测试 (Autonomous Test Execution)
+ ARTEMIS 接管真机自动化操作，跳过广告并实时采集性能指标

+ 步骤三：自主执行测试 + 		+ 4️⃣ 交付最终报告 (Comprehensive Final Report)
+ 生成结构化测试分析报告，包含性能数据表、结论与原始数据集

+ 步骤四：交付最终报告 +
@@ -65,7 +101,7 @@ start.bat

-🔌 接入 Cursor / Claude Code / Windsurf (MCP)（点击展开） +🔌 接入 Antigravity / Claude Code / Windsurf (MCP)（点击展开）
@@ -76,14 +112,14 @@ ARTEMIS 内置原生 **Model Context Protocol (MCP)** 服务。只需将以下 运行内置命令一键获取当前环境的完整配置 JSON： ```bash -artemis mcp --generate-config cursor +artemis mcp --generate-config antigravity # 或生成所有 IDE 配置： artemis mcp --generate-config all ``` ### 2. 复制配置到 IDE -* **Cursor** (`.cursor/mcp.json` 或 设置 ➔ MCP Servers)： +* **Antigravity** (MCP 配置文件或 设置 ➔ MCP Servers)： ```json { "mcpServers": { @@ -113,7 +149,7 @@ artemis mcp --generate-config all ``` ### 3. 在 IDE 中体验真机协同 -在 Cursor / Claude Code 对话框中直接输入： +在 Antigravity / Claude Code 对话框中直接输入： > 💬 *"请帮我把刚刚修改的代码编译成 APK 并安装到手机上，打开登录页面输入测试账号，验证登录后是否有异常弹窗，并把最终页面截图回传。"*
@@ -132,15 +168,17 @@ from artemis.interfaces.sdk import ArtemisClient async def main(): - # 初始化客户端（支持 "flash" 极速模式 或 "pro" 深度推理模式） + # 初始化测试客户端（支持 "flash" 极速校验模式 或 "pro" 深度推理与自愈模式） client = ArtemisClient(default_profile="flash") - # 执行自然语言任务 - result = await client.run("打开计算器，计算 (128 * 45) + 330 的结果") + # 执行自然语言端到端测试用例 + result = await client.run( + "打开系统设置，进入『电池』页面，验证是否正常显示电量百分比，确认页面无异常报错弹窗。" + ) - print(f"执行状态: {result.status}") - print(f"消耗步数: {result.turns}") - print(f"Trace ID: {result.trace_id}") + # 结构化断言与执行追溯 + assert result.status == "SUCCESS", f"测试执行失败: {result.failure_reason}" + print(f"✅ 测试通过！耗时步数: {result.turns} | Trace ID: {result.trace_id}") if __name__ == "__main__": @@ -157,20 +195,20 @@ if __name__ == "__main__": 💡 控制台功能布局：① 顶栏视图切换（主页与工作区） · ② 运行模式与录屏回放（Flash/Pro 状态与视频回放） · ③ 实时感知推理流（动作分解、点击坐标与结构化总结） · ④ 自然语言下发胶囊（自然语言驱动真机） · ⑤ 任务队列看板（状态流转与历史回溯）

-* 🖥️ **Web 可视化控制台 (`artemis ui`)**：集成设备实时投屏与交互面板，支持通过自然语言下发任务，实时观测推理过程、操作轨迹与状态回放； -* 🔌 **MCP 协议集成 (IDE 联动)**：作为标准 MCP 服务器无缝接入 **Cursor、Claude Code、OpenClaw** 等环境，直接在 IDE 中调用移动端真机操作能力； -* 💻 **命令行工具 (`artemis run`)**：支持通过 CLI 直接执行自动化任务、测试用例或 AndroidWorld 基准评测，提供高保真结构化终端输出； -* 🐍 **Python SDK**：作为标准 Python 库集成至现有自动化测试框架或流水线，提供基于 Pydantic 的强类型结构化输出。 +* 🖥️ **Web 可视化测试控制台 (`artemis ui`)**：集成设备实时投屏与交互面板，支持通过自然语言下发测试用例，实时观测推理步骤、操作轨迹、截图留存与异常状态回放； +* 🔌 **MCP 协议集成 (AI IDE 协同)**：作为标准 MCP 服务器无缝接入 **Antigravity、Claude Code、Windsurf** 等开发环境，在 IDE 中直接驱动真机完成自动化测试与 Bug 复现验证； +* 💻 **命令行工具 (`artemis run`)**：支持通过 CLI 直接执行自动化用例、稳定性巡检或 AndroidWorld 基准评测，提供高保真结构化终端输出； +* 🐍 **Python SDK**：作为标准 Python 库无缝集成至现有自动化测试框架（如 pytest）或 CI/CD 流水线，提供基于 Pydantic 的强类型结构化结果与断言支持。 ## 📊 方案横向对比 -| 场景 / 维度 | 传统自动化框架 | 常见屏幕 Agent | **ARTEMIS ☕** | +| 评估维度 | 传统自动化测试框架 (Appium / Maestro) | 常见移动端 VLM Agent | **ARTEMIS ☕ (下一代 AI 测试平台)** | | :--- | :--- | :--- | :--- | -| **自然语言指令支持** | ❌ 仅支持硬编码脚本，无语义理解 | ⚠️ 响应较慢，单步交互通常需 20-30 秒 | ⚡ **高效执行**：Flash 模式下单步最快约 3-5 秒，交互流畅 | -| **UI 改版适应能力** | ❌ 元素变更易导致脚本执行中断 | ⚠️ 依赖绝对坐标，存在位置偏移风险 | 🎯 **多模态语义定位**：结合文本、图标与层次结构，自适应 UI 变化 | -| **异常弹窗处理** | ❌ 弹窗遮挡易导致定位失败 | ❌ 面对未知弹窗易陷入无效循环 | 🩹 **执行前校验与自愈**：操作前确认目标状态，自动识别并处理干扰弹窗 | -| **动态与视频场景** | ❌ 仅支持静态等待 (sleep)，无动态感知 | ❌ 无法识别视频与动态流媒体内容 | ⏱️ **流媒体分析**：支持视频流分析、倒计时识别与预测性连点 | -| **开发环境集成** | ❌ 独立运行，难以直接与 AI IDE 联动 | ❌ 通常仅提供独立网页，集成成本高 | 🔌 **原生 MCP 支持**：可在 Cursor、Claude Desktop 等环境中直接调用 | +| **用例编写与维护** | ❌ 强依赖 XPath/ID，UI 微调即导致大面积报错 | ⚠️ 缺乏工程化封装，执行不可靠，无法作为用例复用 | 🧪 **零脚本维护**：自然语言直接定义用例，无惧 UI 漂移与改版 | +| **执行延迟与吞吐** | ⚡ 脚本执行快，但编写与定位调试耗时极长 | ❌ 单步推理动辄 20-30 秒，无法满足回归测试要求 | ⚡ **高吞吐低延迟**：首创乐观异步流水线，单步仅需 3-5 秒 | +| **异常遮挡与自愈** | ❌ 遇到系统权限弹窗或意外通知时直接中断报错 | ❌ 遇到非预期弹窗极易卡死或陷入无意义循环 | 🛡️ **执行前校验与自愈**：Safety Net 自动拦截并处理干扰弹窗 | +| **缺陷诊断与多媒体** | ❌ 仅支持静态等待，难以对视频流/动效做自动化验证 | ❌ 仅看静态截图，无法获取底层日志及系统状态 | 🐞 **深层诊断**：支持流媒体分析与 **Logcat 崩溃堆栈抓取** | +| **开发环境集成** | ❌ 独立运行，发现问题后需人工抓日志提单 | ❌ 多为独立网页 Demo，难以融入研发工具链 | 🔌 **原生 MCP & SDK**：在 Antigravity/Claude Code 中直接驱动真机测 Bug | @@ -232,7 +270,7 @@ if __name__ == "__main__": - [x] **全链路乐观异步流水线**：主流程轻量化，后台并发执行记忆压缩与断言校验。 - [x] **Safety Net 执行前校验**：动作下发前双层核验与预测性链式执行。 - [x] **时间敏感多媒体处理**：集成 `scrcpy` 与 `ffmpeg` 分析全屏视频与音频流。 -- [x] **原生 MCP 服务支持**：支持与 Cursor、Claude Desktop 等工具无缝集成。 +- [x] **原生 MCP 服务支持**：支持与 Antigravity、Claude Desktop 等工具无缝集成。 - [x] **Web 可视化控制台**：提供设备投屏、交互演练与轨迹回溯。 - [x] **AndroidWorld SOTA**：达到 99%+ 的任务完成率。 - [ ] **跨平台扩展**：探索 iOS 与 Web 端的定位与操作能力。 diff --git a/docs/assets/artemis-banner-en.png b/docs/assets/artemis-banner-en.png index be7b2bd..127b931 100644 Binary files a/docs/assets/artemis-banner-en.png and b/docs/assets/artemis-banner-en.png differ diff --git a/docs/assets/artemis-banner.png b/docs/assets/artemis-banner.png index be7b2bd..127b931 100644 Binary files a/docs/assets/artemis-banner.png and b/docs/assets/artemis-banner.png differ diff --git a/docs/assets/generate_banner.py b/docs/assets/generate_banner.py index d3f13ae..17fa28e 100644 --- a/docs/assets/generate_banner.py +++ b/docs/assets/generate_banner.py @@ -154,9 +154,23 @@ def create_banner_html(): filter: drop-shadow(0 0 35px rgba(66, 133, 244, 0.4)); } + .brand-acronym { + font-size: 13px; + font-weight: 600; + color: #94A3B8; + letter-spacing: 0.015em; + font-family: 'Google Sans Mono', 'Roboto Mono', monospace; + margin-top: -3px; + } + + .brand-acronym span { + color: #60A5FA; + font-weight: 800; + } + /* Clean Single Subtitle (Preserving Android) */ .brand-tagline { - font-size: 24px; + font-size: 23px; font-weight: 700; line-height: 1.35; color: #F8FAFC; @@ -216,7 +230,8 @@ def create_banner_html(): } .prompt-text { - font-size: 13.5px; + font-size: 12px; + line-height: 1.35; font-family: 'Google Sans Mono', 'Roboto Mono', monospace; color: #E2E8F0; font-weight: 500; @@ -379,6 +394,46 @@ def create_banner_html(): font-family: 'Google Sans Mono', 'Roboto Mono', monospace; } + /* Host Telemetry Metrics Panel in Console */ + .metrics-panel { + background: rgba(15, 23, 42, 0.85); + border: 1px solid rgba(255, 255, 255, 0.08); + border-radius: 8px; + padding: 7px 10px; + display: flex; + flex-direction: column; + gap: 4px; + margin-top: 1px; + } + + .metric-row { + display: flex; + align-items: center; + justify-content: space-between; + font-family: 'Google Sans Mono', 'Roboto Mono', monospace; + font-size: 9.5px; + } + + .metric-label { + color: #94A3B8; + } + + .metric-value { + color: #F1F5F9; + font-weight: 700; + } + + .metric-value.cpu-highlight { + color: #34D399; + background: rgba(52, 211, 153, 0.15); + padding: 1px 5px; + border-radius: 3px; + } + + .metric-value.status-ok { + color: #60A5FA; + } + /* Connected Mobile Phone Mockup */ .phone-frame { position: relative; @@ -657,9 +712,14 @@ def create_banner_html():

ARTEMIS

+ +
+ Autonomous Real-time Testing, Exploration & Mobile Interaction System +
+
- Control Any Android App with Autonomous AI + Test Any Pixel / Android App with Autonomous AI
@@ -672,7 +732,7 @@ def create_banner_html():
- > Order an iced caramel latte with oat milk + > Connect to Bluetooth earbuds, play a song, and capture CPU usage metrics
@@ -685,70 +745,86 @@ def create_banner_html():
- Agent Execution + Host Agent Console
- STEP 3 / 4 + MONITORING
✓ - 1. Open app & search catalog + 1. Connect to Bluetooth earbuds
✓ - 2. Select item & customize + 2. Launch music player & play song
- ▶ 3. Tap "Place Order" - 140ms + ▶ 3. Capture CPU usage metrics + Active
- Vision target grounded at (540, 1680) + ADB polling top -n 1 (pid: 14208) +
+
+ + +
+
+ Target App CPU + 4.2% +
+
+ Bluetooth Audio + ● Connected +
+
+ Sample Rate + 48kHz / A2DP
○ - 4. Verify receipt & return + 4. Assert CPU < 5.0% threshold
- +
- Food & Drink - ● ANDROID + Now Playing + ● PIXEL LAB
-
☕
+
🎵
- Iced Caramel Latte - Double Shot · Oat Milk + Coldplay - Yellow + Output: Pixel Buds Pro
- $5.40 + Playing ▶
- Delivery Address - Desk #42 + Active Audio Output Device + 🎧 Pixel Buds Pro (A2DP)
- +
🎯 GROUNDED (0.99)
- Place Order ($5.40) + Media Output Controls
diff --git a/docs/assets/workflow-1-prompt.png b/docs/assets/workflow-1-prompt.png new file mode 100644 index 0000000..f6526d2 Binary files /dev/null and b/docs/assets/workflow-1-prompt.png differ diff --git a/docs/assets/workflow-2-plan.png b/docs/assets/workflow-2-plan.png new file mode 100644 index 0000000..fc5c8ea Binary files /dev/null and b/docs/assets/workflow-2-plan.png differ diff --git a/docs/assets/workflow-3-exec.png b/docs/assets/workflow-3-exec.png new file mode 100644 index 0000000..55a6666 Binary files /dev/null and b/docs/assets/workflow-3-exec.png differ diff --git a/docs/assets/workflow-4-report.png b/docs/assets/workflow-4-report.png new file mode 100644 index 0000000..f48fe22 Binary files /dev/null and b/docs/assets/workflow-4-report.png differ