open-autoglm-phone-agent

User Natural Language → AutoGLM VLM → Screen Perception → ADB/HDC/WebDriverAgent → Device Actions

git clone https://github.com/zai-org/Open-AutoGLM.git
cd Open-AutoGLM
pip install -r requirements.txt
pip install -e .

# Android
adb devices
# Expected: emulator-5554   device
 
# HarmonyOS NEXT
hdc list targets
# Expected: 7001005458323933328a01bce01c2500

export BIGMODEL_API_KEY="your-bigmodel-api-key"
python main.py \
  --base-url https://open.bigmodel.cn/api/paas/v4 \
  --model "autoglm-phone" \
  --apikey $BIGMODEL_API_KEY \
  "打开美团搜索附近的火锅店"

export MODELSCOPE_API_KEY="your-modelscope-api-key"
python main.py \
  --base-url https://api-inference.modelscope.cn/v1 \
  --model "ZhipuAI/AutoGLM-Phone-9B" \
  --apikey $MODELSCOPE_API_KEY \
  "open Meituan and find nearby hotpot"

# Install vLLM (or use official Docker: docker pull vllm/vllm-openai:v0.12.0)
pip install vllm
 
# Start model server (strictly follow these parameters)
python3 -m vllm.entrypoints.openai.api_server \
  --served-model-name autoglm-phone-9b \
  --allowed-local-media-path / \
  --mm-encoder-tp-mode data \
  --mm_processor_cache_type shm \
  --mm_processor_kwargs '{"max_pixels":5000000}' \
  --max-model-len 25480 \
  --chat-template-content-format string \
  --limit-mm-per-prompt '{"image":10}' \
  --model zai-org/AutoGLM-Phone-9B \
  --port 8000

# Install SGLang or use: docker pull lmsysorg/sglang:v0.5.6.post1
# Inside container: pip install nvidia-cudnn-cu12==9.16.0.29
 
python3 -m sglang.launch_server \
  --model-path zai-org/AutoGLM-Phone-9B \
  --served-model-name autoglm-phone-9b \
  --context-length 25480 \
  --mm-enable-dp-encoder \
  --mm-process-config '{"image":{"max_pixels":5000000}}' \
  --port 8000

python scripts/check_deployment_cn.py \
  --base-url http://localhost:8000/v1 \
  --model autoglm-phone-9b

# Android device (default)
python main.py \
  --base-url http://localhost:8000/v1 \
  --model autoglm-phone-9b \
  "打开小红书搜索美食"
 
# HarmonyOS device
python main.py \
  --base-url http://localhost:8000/v1 \
  --model autoglm-phone-9b \
  --device-type hdc \
  "打开设置查看WiFi"
 
# Multilingual model for English apps
python main.py \
  --base-url http://localhost:8000/v1 \
  --model autoglm-phone-9b-multilingual \
  "Open Instagram and search for travel photos"

from phone_agent import PhoneAgent
from phone_agent.config import AgentConfig
 
config = AgentConfig(
    base_url="http://localhost:8000/v1",
    model="autoglm-phone-9b",
    device_type="adb",  # or "hdc" for HarmonyOS
)
 
agent = PhoneAgent(config)
 
# Run a task
result = agent.run("打开淘宝搜索蓝牙耳机")
print(result)

from phone_agent import PhoneAgent
from phone_agent.config import AgentConfig
import os
 
config = AgentConfig(
    base_url=os.environ["MODEL_BASE_URL"],
    model=os.environ["MODEL_NAME"],
    apikey=os.environ.get("MODEL_API_KEY"),
    device_type="adb",
    device_id="emulator-5554",  # specific device
)
 
agent = PhoneAgent(config)
 
# Task with sensitive operation confirmation
result = agent.run(
    "在京东购买最便宜的蓝牙耳机",
    confirm_sensitive=True  # prompt user before purchase actions
)

import openai
import base64
import os
from pathlib import Path
 
client = openai.OpenAI(
    base_url=os.environ["MODEL_BASE_URL"],
    api_key=os.environ.get("MODEL_API_KEY", "dummy"),
)
 
# Load screenshot
screenshot_path = "screenshot.png"
with open(screenshot_path, "rb") as f:
    image_b64 = base64.b64encode(f.read()).decode()
 
response = client.chat.completions.create(
    model="autoglm-phone-9b",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{image_b64}"},
                },
                {
                    "type": "text",
                    "text": "Task: 搜索附近的咖啡店\nCurrent step: Navigate to search",
                },
            ],
        }
    ],
)
 
print(response.choices[0].message.content)
# Output format: <think>...</think>\n<answer>do(action="...", ...)

import re
 
def parse_action(model_output: str) -> dict:
    """Parse AutoGLM model output into structured action."""
    # Extract answer block
    answer_match = re.search(r'<answer>(.*?)(?:</answer>|$)', model_output, re.DOTALL)
    if not answer_match:
        return {"action": "unknown"}
    
    answer = answer_match.group(1).strip()
    
    # Parse do() call
    # Format: do(action="ActionName", param1="value1", param2="value2")
    action_match = re.search(r'do\(action="([^"]+)"(.*?)\)', answer, re.DOTALL)
    if not action_match:
        return {"action": "unknown", "raw": answer}
    
    action_name = action_match.group(1)
    params_str = action_match.group(2)
    
    # Parse parameters
    params = {}
    for param_match in re.finditer(r'(\w+)="([^"]*)"', params_str):
        params[param_match.group(1)] = param_match.group(2)
    
    return {"action": action_name, **params}
 
# Example usage
output = '<think>需要启动京东</think>\n<answer>do(action="Launch", app="京东")'
action = parse_action(output)
# {"action": "Launch", "app": "京东"}

import subprocess
 
def take_screenshot(device_id: str = None) -> bytes:
    """Capture current device screen."""
    cmd = ["adb"]
    if device_id:
        cmd.extend(["-s", device_id])
    cmd.extend(["exec-out", "screencap", "-p"])
    result = subprocess.run(cmd, capture_output=True)
    return result.stdout
 
def send_tap(x: int, y: int, device_id: str = None):
    """Tap at screen coordinates."""
    cmd = ["adb"]
    if device_id:
        cmd.extend(["-s", device_id])
    cmd.extend(["shell", "input", "tap", str(x), str(y)])
    subprocess.run(cmd)
 
def send_text_adb_keyboard(text: str, device_id: str = None):
    """Send text via ADB Keyboard (must be installed and enabled)."""
    cmd = ["adb"]
    if device_id:
        cmd.extend(["-s", device_id])
    # Enable ADB keyboard first
    cmd_enable = cmd + ["shell", "ime", "set", "com.android.adbkeyboard/.AdbIME"]
    subprocess.run(cmd_enable)
    # Send text
    cmd_text = cmd + ["shell", "am", "broadcast", "-a", "ADB_INPUT_TEXT",
                      "--es", "msg", text]
    subprocess.run(cmd_text)
 
def swipe(x1: int, y1: int, x2: int, y2: int, duration_ms: int = 300, device_id: str = None):
    """Swipe gesture on screen."""
    cmd = ["adb"]
    if device_id:
        cmd.extend(["-s", device_id])
    cmd.extend(["shell", "input", "swipe",
                str(x1), str(y1), str(x2), str(y2), str(duration_ms)])
    subprocess.run(cmd)
 
def press_back(device_id: str = None):
    """Press Android back button."""
    cmd = ["adb"]
    if device_id:
        cmd.extend(["-s", device_id])
    cmd.extend(["shell", "input", "keyevent", "KEYCODE_BACK"])
    subprocess.run(cmd)
 
def launch_app(package_name: str, device_id: str = None):
    """Launch app by package name."""
    cmd = ["adb"]
    if device_id:
        cmd.extend(["-s", device_id])
    cmd.extend(["shell", "monkey", "-p", package_name, "-c",
                "android.intent.category.LAUNCHER", "1"])
    subprocess.run(cmd)

// .env configuration
// MIDSCENE_MODEL_NAME=autoglm-phone
// MIDSCENE_OPENAI_BASE_URL=https://open.bigmodel.cn/api/paas/v4
// MIDSCENE_OPENAI_API_KEY=your-api-key
 
import { AndroidAgent } from "@midscene/android";
 
const agent = new AndroidAgent();
await agent.aiAction("打开微信发送消息给张三");
await agent.aiQuery("当前页面显示的消息内容是什么？");

# Connect device via USB first, then enable TCP/IP mode
adb tcpip 5555
 
# Get device IP address
adb shell ip addr show wlan0
 
# Connect wirelessly (disconnect USB after this)
adb connect 192.168.1.100:5555
 
# Verify connection
adb devices
# 192.168.1.100:5555   device
 
# Use with agent
python main.py \
  --base-url http://model-server:8000/v1 \
  --model autoglm-phone-9b \
  --device-id "192.168.1.100:5555" \
  "打开支付宝查看余额"

# Model service
export MODEL_BASE_URL="http://localhost:8000/v1"
export MODEL_NAME="autoglm-phone-9b"
export MODEL_API_KEY=""  # Required for BigModel/ModelScope APIs
 
# BigModel API
export BIGMODEL_API_KEY=""
export BIGMODEL_BASE_URL="https://open.bigmodel.cn/api/paas/v4"
 
# ModelScope API
export MODELSCOPE_API_KEY=""
export MODELSCOPE_BASE_URL="https://api-inference.modelscope.cn/v1"
 
# Device configuration
export ADB_DEVICE_ID=""      # Leave empty for auto-detect
export HDC_DEVICE_ID=""      # HarmonyOS device ID

adb shell ime enable com.android.adbkeyboard/.AdbIME
adb shell ime set com.android.adbkeyboard/.AdbIME

# Test connectivity
curl http://YOUR_SERVER_IP:8000/v1/models
# Should return model list JSON

# After configuring WebDriverAgent per docs/ios_setup/ios_setup.md
python main.py \
  --base-url http://localhost:8000/v1 \
  --model autoglm-phone-9b-multilingual \
  --device-type ios \
  "Open Maps and navigate to Central Park"