software-mansion · latekvo · Apr 17, 2026 · Apr 17, 2026 · Apr 17, 2026 · Apr 17, 2026
diff --git a/README.md b/README.md
@@ -6,15 +6,15 @@
 </p>
 <br/>
 
-**[Argent](https://argent.swmansion.com)** is an **agentic toolkit** that gives your AI assistant direct access to iOS Simulators. Ask it to tap a button, run a profiler or reproduce an issue manually - all from within your CLI, without switching context.
+**[Argent](https://argent.swmansion.com)** is an **agentic toolkit** that gives your AI assistant direct access to iOS Simulators and Android Emulators. Ask it to tap a button, run a profiler or reproduce an issue manually - all from within your CLI, without switching context.
 
 ```bash
 npx @swmansion/argent init
 ```
 
 ## Capabilities
 
-- **Autonomous iOS development** - Allow your agent to work with iOS apps on its own - let it build, open, interact with the app and debug it. Ask for reproducing issues, testing features manually, profiling your app and much more, without ever interrupting your work.
+- **Autonomous iOS and Android development** - Allow your agent to work with iOS and Android apps on its own - let it build, open, interact with the app and debug it. Ask for reproducing issues, testing features manually, profiling your app and much more, without ever interrupting your work.
 - **UI interaction** - Give your agent full control toolkit - tapping, swiping, pinching, typing, gestures, hardware buttons and all other gears included. Let it navigate your app exactly as a user would, without lifting a finger.
 - **Profiling with batteries included** - Argent can perform and analyze both React-Native and Xcode Instruments profiling sessions. Get comprehensive summaries and ask to optimise your app where you find fit.
 - **Debugging and diagnostics** - Let your agent inspect logs, capture crash reports, and reproduce failing states on the simulator, so you can jump straight to the fix.
@@ -33,8 +33,9 @@ npx @swmansion/argent init
 
 #### Prerequisites
 
-- macOS with **Xcode** installed
 - **Node.js 18** or later
+- For iOS: macOS with **Xcode** installed
+- For Android: **Android SDK Platform Tools** (`adb`) on `PATH`, and the **Android Emulator** package if you want to boot AVDs from Argent. Create AVDs via Android Studio or `avdmanager`.
 
 #### Run `init` in your project
 

diff --git a/packages/argent-cli/src/run.ts b/packages/argent-cli/src/run.ts
@@ -120,7 +120,7 @@ Invoke a tool exposed by the argent tool-server. Run \`argent tools\` to list
 available tools, or \`argent tools describe <name>\` to see one tool's flags.
 
 Examples:
-  argent run list-simulators
+  argent run list-devices
   argent run gesture-tap --udid <UDID> --x 0.5 --y 0.5
   argent run screenshot --udid <UDID> --out ./screen.png
   argent run run-sequence --udid <UDID> --steps-json '[{"tool":"button","args":{"button":"home"}}]'

diff --git a/packages/argent-installer/test/skills.test.ts b/packages/argent-installer/test/skills.test.ts
@@ -75,7 +75,7 @@ describe("refreshArgentSkills", () => {
   });
 
   it("resyncs a tracked project scope when the lock has an argent skill", () => {
-    listBundledSkillsMock.mockReturnValue(["argent-create-flow", "argent-simulator-setup"]);
+    listBundledSkillsMock.mockReturnValue(["argent-create-flow", "argent-ios-simulator-setup"]);
     writeLock(path.join(tmpDir, "skills-lock.json"), {
       "argent-create-flow": {},
     });

diff --git a/packages/argent-installer/test/update.test.ts b/packages/argent-installer/test/update.test.ts
@@ -8,7 +8,6 @@ import {
   detectPackageManager,
   globalInstallCommand,
   formatShellCommand,
-  isTempRunnerPath,
 } from "../src/utils.js";
 import { PACKAGE_NAME, NPM_REGISTRY } from "../src/constants.js";
 
@@ -68,33 +67,6 @@ describe("update — constants are correct", () => {
   });
 });
 
-describe("update — temp runner detection", () => {
-  // npx-cached argent shares the latest version, so without this filter the
-  // version compare would falsely match latest after the user uninstalled the
-  // global package via `npx @swmansion/argent uninstall`.
-  it("flags npx cache paths as transient", () => {
-    expect(isTempRunnerPath("/Users/me/.npm/_npx/abc123/node_modules/.bin/argent")).toBe(true);
-  });
-
-  it("flags pnpm dlx cache paths as transient", () => {
-    expect(isTempRunnerPath("/Users/me/.pnpm-store/dlx-1234/node_modules/.bin/argent")).toBe(true);
-  });
-
-  it("flags bun install cache paths as transient", () => {
-    expect(isTempRunnerPath("/Users/me/.bun/install/cache/argent")).toBe(true);
-  });
-
-  it("flags Windows dlx cache paths as transient", () => {
-    expect(isTempRunnerPath("C:\\Users\\me\\AppData\\Local\\dlx-abc\\argent.cmd")).toBe(true);
-  });
-
-  it("treats real global install paths as permanent", () => {
-    expect(isTempRunnerPath("/usr/local/bin/argent")).toBe(false);
-    expect(isTempRunnerPath("/opt/homebrew/bin/argent")).toBe(false);
-    expect(isTempRunnerPath("C:\\Users\\me\\AppData\\Roaming\\npm\\argent.cmd")).toBe(false);
-  });
-});
-
 describe("update — registry safety", () => {
   it("globalInstallCommand never includes --registry (relies on .npmrc scoped registry)", () => {
     for (const pm of ["npm", "yarn", "pnpm", "bun"] as const) {

diff --git a/packages/argent-mcp/src/mcp-server.ts b/packages/argent-mcp/src/mcp-server.ts
@@ -150,7 +150,7 @@ export async function startMcpServer(options: StartMcpServerOptions): Promise<vo
     {
       capabilities: { tools: {} },
       instructions:
-        "Argent — iOS Simulator Control for interacting, testing, profiling and debugging mobile applications. " +
+        "Argent — iOS Simulator and Android Emulator control for interacting, testing, profiling and debugging mobile applications. " +
         "Always use discovery tools (describe / debugger-component-tree / screenshot) before tapping — never guess coordinates. " +
         "On session end: call stop-all-simulator-servers and perform any necessary cleanup. " +
         "Full guidance is in the argent rule loaded from .claude/rules/argent.md.",

diff --git a/packages/argent-mcp/test/auto-screenshot.test.ts b/packages/argent-mcp/test/auto-screenshot.test.ts
@@ -83,8 +83,8 @@ describe("shouldAutoScreenshot", () => {
   });
 
   it("returns false for excluded tools", () => {
-    expect(shouldAutoScreenshot("list-simulators")).toBe(false);
-    expect(shouldAutoScreenshot("boot-simulator")).toBe(false);
+    expect(shouldAutoScreenshot("list-devices")).toBe(false);
+    expect(shouldAutoScreenshot("boot-device")).toBe(false);
     expect(shouldAutoScreenshot("simulator-server")).toBe(false);
     expect(shouldAutoScreenshot("activate-sso")).toBe(false);
   });

diff --git a/packages/argent/package.json b/packages/argent/package.json
@@ -1,7 +1,7 @@
 {
   "name": "@swmansion/argent",
   "version": "0.6.1",
-  "description": "MCP server for iOS Simulator control",
+  "description": "MCP server for iOS Simulator and Android Emulator control",
   "license": "Apache-2.0",
   "repository": {
     "type": "git",

diff --git a/packages/argent/scripts/bundle-tools.cjs b/packages/argent/scripts/bundle-tools.cjs
@@ -180,7 +180,7 @@ if (fs.existsSync(UI_SRC)) {
   console.warn(`⚠ Preview UI not found at ${UI_SRC} — skipping copy`);
 }
 
-// Copy Argent.tracetemplate so ios-profiler-start can find it at runtime.
+// Copy Argent.tracetemplate so native-profiler-start can find it at runtime.
 const TRACE_TEMPLATE_SRC = path.resolve(
   WORKSPACE_ROOT,
   "packages/tool-server/src/utils/ios-profiler/Argent.tracetemplate"

diff --git a/packages/registry/src/types.ts b/packages/registry/src/types.ts
@@ -119,7 +119,7 @@ export interface ToolCapability {
  * On a missing binary, the HTTP layer returns 424 Failed Dependency with an
  * install hint the agent can surface verbatim.
  */
-export type ToolDependency = "adb" | "xcrun";
+export type ToolDependency = "adb" | "xcrun" | "emulator";
 
 // ── Tool Types ──
 

diff --git a/packages/skills/agents/argent-environment-inspector.md b/packages/skills/agents/argent-environment-inspector.md
@@ -45,7 +45,7 @@ but required by the main agent, fill it in by manual inspection of the project.
    - `expo` in dependencies or `app.json` with `expo` key → Expo project
    - `pubspec.yaml` present → Flutter project
    - `ios/*.xcodeproj` or `ios/*.xcworkspace` without `react-native` → native iOS
-   - `android/build.gradle` without `react-native` → native Android
+   - `android/build.gradle` or `android/build.gradle.kts` without `react-native` → native Android
    - None of the above → classify based on what you find (web app, library, etc.)
 
 3. **Explore beyond the snapshot.** Use Read, Glob, Grep, and Bash to fill
@@ -64,7 +64,7 @@ but required by the main agent, fill it in by manual inspection of the project.
      flows (`.maestro/`).
    - For Flutter: `pubspec.yaml`, `analysis_options.yaml`, `lib/` structure.
    - For native iOS: Xcode project/workspace, schemes, `Podfile`, `Package.swift`.
-   - For native Android: `build.gradle`, `settings.gradle`, flavor configs.
+   - For native Android: `build.gradle` / `build.gradle.kts`, `settings.gradle` / `settings.gradle.kts`, flavor configs.
 
 4. **Populate every field** in the output schema below. Use `null` for
    genuinely unknown values or fields that do not apply to this project type.
@@ -89,6 +89,8 @@ Return a JSON object with these top-level fields:
 | `startup_commands`                    | array        | `[{ command, context }]` — concrete dev server start commands                                 |
 | `build_commands`                      | array        | `[{ command, platform, context }]` — build commands per platform                              |
 | `argent_workflow`                     | object       | `{ start_dev_server, build_ios, build_android, notes }` — exact commands for Argent           |
+| `ios_has_podfile`                     | bool         | True when `ios/Podfile` exists                                                                |
+| `android_has_gradle`                  | bool         | True when `android/gradlew` exists                                                            |
 | `configs`                             | object       | Paths to metro, babel, app, tsconfig, pubspec, xcode, gradle configs (`null` if absent)       |
 | `metro_port`                          | number\|null | From config or default 8081; `null` for non-RN                                                |
 | `env_resolution`                      | object       | `{ env_files, strategy, notes }`                                                              |

diff --git a/packages/skills/agents/references/quality-control-checklist.md b/packages/skills/agents/references/quality-control-checklist.md
@@ -41,5 +41,5 @@ Look for these beyond the obvious lint/test configs, regardless of project type:
 - `lint-staged` config — what runs on commit
 - CI config files — the CI steps are ground truth for what "passing" means
 - `Podfile` / `Package.swift` — iOS dependency management
-- `build.gradle` / `settings.gradle` — Android build config and flavor definitions
+- `build.gradle` / `build.gradle.kts` / `settings.gradle` / `settings.gradle.kts` — Android build config and flavor definitions (Groovy or Kotlin DSL)
 - `pubspec.yaml` / `analysis_options.yaml` — Flutter project config and lint rules
diff --git a/packages/skills/package.json b/packages/skills/package.json
@@ -3,7 +3,7 @@
   "name": "@argent/skills",
   "version": "0.6.1",
   "type": "module",
-  "description": "Claude Code skills for iOS simulator interaction via argent",
+  "description": "Claude Code skills for iOS simulator and Android emulator interaction via argent",
   "scripts": {
     "install-skills": "node scripts/install.js"
   },

diff --git a/packages/skills/rules/argent.md b/packages/skills/rules/argent.md
@@ -1,39 +1,39 @@
 ---
-description: Argent iOS Simulator Agent — always-on guidance for methodology and tools for working with, interacting, testing and profiling mobile app work
+description: Argent iOS Simulator and Android Emulator Agent — always-on guidance for methodology and tools for working with, interacting, testing and profiling mobile app work
 alwaysApply: true
 ---
 
 <description>
-Argent MCP tools are available in this project for iOS simulator control. Argent MCP tools are the preferred form of interaction with the application.
+Argent MCP tools are available in this project for iOS simulator and Android emulator control. Argent MCP tools are the preferred form of interaction with the application.
 Running MCP server and managing the Argent toolkit utilises `argent` command - if asked use `argent --help` for reference.
 To check current version of MCP server run `argent --version` command.
 
 Use cases:
 
-- User mentions iOS simulator, device, or app interaction
-- The app user is working with is a mobile application which can be run in the simulator
+- User mentions iOS simulator, Android emulator, device, or app interaction
+- The app user is working with is a mobile application which can be run in a simulator/emulator
 - Any tapping, swiping, typing, screenshotting, or inspecting a running app
-- Running, debugging, or testing a React Native app
-- Profiling performance or diagnosing re-renders in a React Native app
+- Running, debugging, or testing a React Native app (iOS or Android)
+- Profiling performance or diagnosing re-renders in a React Native app (iOS or Android)
   </description>
 
 <tapping_rule>
 <important>**Never** derive tap coordinates from a screenshot</important>
 Before **every** tap, you MUST call a discovery tool and extract coordinates from the result. This is not optional. Preferred tools are, in order:
 
-- `describe` - native app-level components and safely targetable foreground apps.
-- `native-describe-screen` - accessibility screen description via injected native devtools
+- `describe` - native app-level components and safely targetable foreground apps (iOS and Android).
+- `native-describe-screen` - accessibility screen description via injected native devtools (iOS only)
 - `debugger-component-tree` - react-native specific components
 
-`native-user-interactable-view-at-point` / `native-view-at-point` are follow-up diagnostics once you already have a candidate point.
+`native-user-interactable-view-at-point` / `native-view-at-point` are follow-up diagnostics once you already have a candidate point (iOS only).
 
 Whenever something changed YOU MUST first call `describe`, or another appropriate discovery tool so you do not hallucinate element positions. Do not guess coordinates if you can use discovery tool. Do not tap if you have not called a discovery tool in the current step. Screenshots alone are never sufficient for coordinates.
 
 If a **tap fails twice** at the same coordinates, **stop retrying**. Re-run the discovery tool.
 
-If `describe` fails, **read the exact error before reacting**, follow the recovery guidance in `argent-simulator-interact` to choose the correct next action.
+If `describe` fails, **read the exact error before reacting**, follow the recovery guidance in `argent-device-interact` to choose the correct next action.
 
-Before starting to interact with the app, read the `argent-simulator-interact` skill first.
+Before starting to interact with the app, read the `argent-device-interact` skill first.
 </tapping_rule>
 
 <skill_reading_rule>
@@ -42,13 +42,13 @@ Before starting to interact with the app, read the `argent-simulator-interact` s
 
 <general_rules>
 
-- All simulator interactions go through argent MCP tools — never use `xcrun simctl`,
+- All simulator/emulator interactions go through argent MCP tools — never use `xcrun simctl`,
   raw `curl` to simulator ports, or the simulator-server binary directly.
 - Before calling any gesture tool for the first time, use ToolSearch to load its schema.
 - Interaction tools (`gesture-tap`, `gesture-swipe`, `gesture-pinch`, `gesture-rotate`, `gesture-custom`, `launch-app`, etc.) return a screenshot automatically.
   Call `screenshot` separately only for a baseline before any action or after a delay.
 - Always open apps with `launch-app` or `open-url` — never tap home screen icons.
-- Always use `run-sequence` when performing multiple sequential simulator actions where you don't need to observe the screen between steps. More in `argent-simulator-interact` skill.
+- Always use `run-sequence` when performing multiple sequential simulator actions where you don't need to observe the screen between steps. More in `argent-device-interact` skill.
 - When the session ends or the user says they are done: call `stop-all-simulator-servers`.
   If the user started Metro separately, ask whether to call `stop-metro` (specify the port if not 8081).
 - If tools provided by mcp-server are not sufficient and action can be done using `xcrun` or other commands, use the command. Examples: changing simulator options, performing simulator action such as lock, shake, etc.
@@ -69,17 +69,21 @@ When `is_react_native` is true: load `argent-react-native-app-workflow` skill. U
 Load the matching skill before starting work and executing tools from argent-mcp — skills contain the full step-by-step
 procedure and edge-case handling for each workflow.
 
-SIMULATOR SETUP
-Skill: `argent-simulator-setup`
-When: Beginning a task that involves the simulator, no simulator booted yet, need UDID or simulator-server.
+iOS SIMULATOR SETUP
+Skill: `argent-ios-simulator-setup`
+When: Beginning a task that involves the iOS simulator, no simulator booted yet, need UDID or simulator-server.
+
+ANDROID EMULATOR SETUP
+Skill: `argent-android-emulator-setup`
+When: Beginning a task that involves the Android emulator, no emulator running yet, need an adb serial, or about to install an APK.
 
 TAPPING, SWIPING, TYPING, GESTURES, SCREENSHOTS, SCROLLING
-Skill: `argent-simulator-interact`
+Skill: `argent-device-interact`
 When: Performing touch interactions, typing, pressing hardware buttons, launching/restarting apps, opening URLs, rotating device, or taking standalone screenshots.
 
 RUNNING / BUILDING / DEBUGGING REACT NATIVE APP
 Skill: `argent-react-native-app-workflow`
-When: Project is react-native, starting Metro or running iOS app, build failures, pod issues, lost Metro connection, reading logs, reloading JS bundle, reinstalling app.
+When: Project is react-native, starting Metro or running the iOS or Android app, build failures, pod issues, lost Metro connection, reading logs, reloading JS bundle, reinstalling app.
 
 JS EVALUATION, METRO CONNECTION, REACT NATIVE
 Skill: `argent-metro-debugger`
@@ -89,9 +93,9 @@ REACT APP & COMPONENT PROFILING
 Use skill: `argent-react-native-profiler`
 When: To measure performance of specific components, to find app-wide bottlenecks. Investigating re-renders or CPU hotspots, producing ranked performance reports.
 
-NATIVE iOS PROFILING
-Use skill: `argent-ios-profiler`
-When: Profiling native iOS performance (CPU hotspots, UI hangs, memory leaks via Instruments). Useful as a reference for iOS-specific investigation when running dual profiling via `argent-react-native-profiler`.
+NATIVE PROFILING
+Use skill: `argent-native-profiler`
+When: Profiling native performance (CPU hotspots, UI hangs, memory leaks). iOS only today; Android on the roadmap. Useful as a reference for platform-specific investigation when running dual profiling via `argent-react-native-profiler`.
 
 PERFORMANCE OPTIMIZATION
 Use skill: `argent-react-native-optimization`