diff --git a/README.md b/README.md index 7691ff5..2901af4 100644 --- a/README.md +++ b/README.md @@ -35,10 +35,14 @@ OpenGUI reads a real Android app UI, plans the next step, takes mobile actions, The fastest way to try OpenGUI is to let Claude Code or Codex bootstrap it for you. +Open Claude Code or Codex from the OpenGUI repository root and paste: + ```text Read ./skills/open-gui-bootstrap/SKILL.md and help me run OpenGUI. Only ask me for phone-side actions. ``` +Claude Code or Codex does not connect to the phone directly. It reads the bootstrap skill, starts the local backend, builds or installs the Android client, runs the required adb setup, and checks whether the phone is visible to OpenGUI. + You will need: - an Android phone or emulator @@ -46,7 +50,7 @@ You will need: - AccessibilityService enabled - model API keys for real task execution -OpenGUI will use the repository scripts to start the backend and install the Android client: +The bootstrap flow uses the repository scripts to start the backend and install the Android client: ```bash cd server @@ -150,11 +154,12 @@ The source code currently exposes these pieces: Start with [`skills/open-gui-bootstrap/SKILL.md`](./skills/open-gui-bootstrap/SKILL.md). -The intended flow is simple: +The intended flow is: -1. point Claude or Codex at the skill -2. describe the task in plain language -3. let the model handle backend bootstrap, APK build, install, and local debugging +1. clone OpenGUI locally +2. open Claude Code or Codex from the OpenGUI repo root +3. ask it to read the bootstrap skill +4. let it handle backend bootstrap, APK build, install, adb setup, and local debugging It should only stop for: @@ -164,6 +169,8 @@ It should only stop for: - granting overlay or battery permissions - providing API keys or bot credentials +Under the hood, OpenGUI still needs both the local backend and Android client running. The bootstrap skill is the guided path for getting those pieces running without manually following every setup step. + After the backend and Android client are running, use [`skills/open-gui-remote-control/SKILL.md`](./skills/open-gui-remote-control/SKILL.md) to let Codex or Claude Code control the phone through the local CLI: ```bash diff --git a/docs/get-started.md b/docs/get-started.md index 4260e49..57754b2 100644 --- a/docs/get-started.md +++ b/docs/get-started.md @@ -4,6 +4,9 @@ This repository already contains the runnable backend and Android client. ## Option 1: Bootstrap with Claude or Codex +Open Claude Code or Codex from the OpenGUI repository root, then ask it to read +the bootstrap skill. + Start with the bootstrap skill: - [`skills/open-gui-bootstrap/SKILL.md`](../skills/open-gui-bootstrap/SKILL.md) @@ -14,11 +17,31 @@ Recommended prompt: Read ./skills/open-gui-bootstrap/SKILL.md and help me run OpenGUI. Only ask me for phone-side actions. ``` +Claude Code or Codex does not connect to the phone directly. The skill guides +the local setup: it starts the backend, builds or installs the Android client, +runs adb setup, and checks whether the phone is visible to OpenGUI. + The skill should use the repository scripts directly: - `server/start.sh` - `client/start.sh` +It should only stop for phone-side actions or credentials: + +- connecting an Android device or starting an emulator +- approving USB debugging +- enabling Accessibility Service +- granting overlay or screen-related permissions +- providing model API credentials + +After setup, run a basic smoke test: + +```bash +cd server +pnpm opengui -- devices --json +pnpm opengui -- do "Observe the current Android screen and summarize what you see" --json +``` + ## Option 2: Manual setup ### 1. Start the backend