Skip to content

refactor: add .env sample and fix import bug #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
sjanaX01 wants to merge 4 commits into
base: main
Choose a base branch
from
+13 −7
Open

refactor: add .env sample and fix import bug #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
986e188
revise README for clarity and consistency in examples
iArsalanshah Dec 12, 2025
3992689
Merge pull request #1 from iArsalanshah/update-readme-docs
ethanjlimgit Dec 12, 2025
dc41825
refactor: add sample.env file and fix small bug
sjanaX01 Dec 12, 2025
7838c8d
refactor: update resolve merge conflict
sjanaX01 Dec 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@

**[Watch it automate a logistics workflow in 60 seconds](https://x.com/ethanjlim/status/1999152070428148108?s=20)**

<sub>Driver texts a photo → Agent handles WhatsApp → Scanner app → Banking app → Invoice submitted</sub>
<sub>Driver texts a photo → Agent opens WhatsApp → uses scanner app → opens banking app → submits invoice</sub>

<br>

Expand Down Expand Up @@ -53,7 +53,7 @@ But the real economy runs on mobile devices, in places where laptops don't fit:

**Priority partnership area.** Android Use automating an entire logistics workflow:

### Before (Manual - 10+ minutes)
### Before — Manual (10+ minutes)
```
1. Driver takes photo of Bill of Lading
2. Opens WhatsApp, sends to back office
Expand All @@ -63,7 +63,7 @@ But the real economy runs on mobile devices, in places where laptops don't fit:
6. Submits for payment
```

### After (Automated - 30 seconds)
### After — Automated (30 seconds)
```python
# Driver just texts the photo. Agent does the rest.
run_agent("""
Expand Down Expand Up @@ -176,7 +176,7 @@ brew install android-platform-tools # macOS
# 4. Connect device & verify
adb devices

# 5. Set API key
# 5. Set your OpenAI API key:
export OPENAI_API_KEY="sk-..."

# 6. Run your first agent
Expand Down
9 changes: 6 additions & 3 deletions kernel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,17 +2,20 @@
import time
import subprocess
import json
from typing import Dict, Any
from typing import Dict, Any, List
from openai import OpenAI
import sanitizer
from dotenv import load_dotenv

load_dotenv()

# --- CONFIGURATION ---
ADB_PATH = "adb" # Ensure adb is in your PATH
MODEL = "gpt-4o" # Or "gpt-4-turbo" for faster/cheaper execution
MODEL = os.environ.get("MODEL") # Or "gpt-4-turbo" for faster/cheaper execution
SCREEN_DUMP_PATH = "/sdcard/window_dump.xml"
LOCAL_DUMP_PATH = "window_dump.xml"

client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))
client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"), base_url=os.environ.get("BASE_URL"))

def run_adb_command(command: List[str]):
"""Executes a shell command via ADB."""
Expand Down
3 changes: 3 additions & 0 deletions sample.env
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
OPENAI_API_KEY=""
BASE_URL="https://api.openai.com/v1"
MODEL="gpt-4o"