browse-code 0.1.1__tar.gz → 0.2.0__tar.gz

browse_code-0.2.0/PKG-INFO

@@ -0,0 +1,124 @@
+Metadata-Version: 2.4
+Name: browse_code
+Version: 0.2.0
+Summary: Turn any AI chatbot into an autonomous coding agent
+Description-Content-Type: text/markdown
+Requires-Dist: fastapi
+Requires-Dist: uvicorn
+Requires-Dist: pydantic
+Requires-Dist: rich
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: requires-dist
+Dynamic: summary
+
+<p align="center">
+  <img src="logo.png" alt="Browse Code" width="200">
+</p>
+
+# Browse Code
+
+![PyPI version](https://badge.fury.io/py/browse-code.svg)
+![Python Version](https://img.shields.io/badge/python-3.8%2B-blue)
+![License](https://img.shields.io/badge/license-MIT-green)
+
+**Browse Code** is a CLI tool that turns any AI chatbot (ChatGPT, Gemini, Claude, HuggingFace) into an autonomous coding agent. It bridges your browser and local terminal, letting AI read/write files, run commands, and manage processes on your machine.
+
+## How It Works
+
+Browse Code has two parts:
+
+1. **A local server** that exposes your file system and terminal to the AI via a secure API.
+2. **A Chrome extension** that injects agent capabilities into AI chat interfaces.
+
+When connected, you can ask ChatGPT/Gemini/Claude to edit files, run scripts, search code, and more — all executed locally on your machine.
+
+## Setup
+
+### Step 1: Install the package
+
+```bash
+pip install browse-code
+```
+
+### Step 2: Run the CLI
+
+```bash
+bc
+```
+
+> If `bc` is not found, add your Python Scripts folder to PATH:
+> ```bash
+> # Windows (PowerShell)
+> $env:Path += ";$env:APPDATA\Python\Python312\Scripts"
+>
+> # Or run directly
+> python -m browse_code.cli
+> ```
+
+### Step 3: First-run extension setup
+
+On the first run, `bc` will guide you through a one-time Chrome extension setup:
+
+1. It asks for your permission to extract the extension files.
+2. It copies the extension to `~/.browse_code/extension/` and copies the path to your clipboard.
+3. It opens `chrome://extensions/` in your browser automatically.
+4. You enable **Developer mode** (top-right toggle), click **Load unpacked**, and paste the path.
+5. Press Enter in the terminal and the server starts.
+
+**You only do this once.** The extension stays loaded in Chrome across sessions.
+
+### Step 4: Start an AI session
+
+1. Open any supported AI chat (ChatGPT, Gemini, Claude, or HuggingFace Chat).
+2. Click the Browse Code Bridge extension icon and set your workspace directory.
+3. Click "Initialize Agent in Chat".
+4. Start coding with AI — it now has full access to your local environment.
+
+## Subsequent Usage
+
+After the first-time setup, just run:
+
+```bash
+bc
+```
+
+The server starts immediately. Open your AI chat tab and you're ready to go. The server terminal will show:
+- A startup banner with your workspace and endpoint
+- `[+] Extension connected` when the browser extension connects
+- Real-time logs of every file read, write, command execution, and diff
+
+## Features
+
+- **File Operations:** Read, write, and patch files with inline terminal diffs
+- **Code Search:** Search across your entire codebase by keyword
+- **Terminal Commands:** Run shell commands with full stdout/stderr capture
+- **Background Processes:** Start, monitor, and kill long-running processes
+- **Multi-Platform AI:** Works with ChatGPT, Gemini, Claude, and HuggingFace Chat
+- **Extension Heartbeat:** Server detects when the browser extension connects/disconnects
+
+## For Developers
+
+1. Clone the repository:
+   ```bash
+   git clone https://github.com/Dedeep007/browse_code.git
+   cd browse_code
+   ```
+2. Install in editable mode:
+   ```bash
+   pip install -e .
+   ```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+1. Fork the repository.
+2. Create your feature branch (`git checkout -b feature/AmazingFeature`).
+3. Commit your changes (`git commit -m 'Add some AmazingFeature'`).
+4. Push to the branch (`git push origin feature/AmazingFeature`).
+5. Open a Pull Request.
+
+## License
+
+Distributed under the MIT License.

browse_code-0.2.0/README.md

@@ -0,0 +1,110 @@
+<p align="center">
+  <img src="logo.png" alt="Browse Code" width="200">
+</p>
+
+# Browse Code
+
+![PyPI version](https://badge.fury.io/py/browse-code.svg)
+![Python Version](https://img.shields.io/badge/python-3.8%2B-blue)
+![License](https://img.shields.io/badge/license-MIT-green)
+
+**Browse Code** is a CLI tool that turns any AI chatbot (ChatGPT, Gemini, Claude, HuggingFace) into an autonomous coding agent. It bridges your browser and local terminal, letting AI read/write files, run commands, and manage processes on your machine.
+
+## How It Works
+
+Browse Code has two parts:
+
+1. **A local server** that exposes your file system and terminal to the AI via a secure API.
+2. **A Chrome extension** that injects agent capabilities into AI chat interfaces.
+
+When connected, you can ask ChatGPT/Gemini/Claude to edit files, run scripts, search code, and more — all executed locally on your machine.
+
+## Setup
+
+### Step 1: Install the package
+
+```bash
+pip install browse-code
+```
+
+### Step 2: Run the CLI
+
+```bash
+bc
+```
+
+> If `bc` is not found, add your Python Scripts folder to PATH:
+> ```bash
+> # Windows (PowerShell)
+> $env:Path += ";$env:APPDATA\Python\Python312\Scripts"
+>
+> # Or run directly
+> python -m browse_code.cli
+> ```
+
+### Step 3: First-run extension setup
+
+On the first run, `bc` will guide you through a one-time Chrome extension setup:
+
+1. It asks for your permission to extract the extension files.
+2. It copies the extension to `~/.browse_code/extension/` and copies the path to your clipboard.
+3. It opens `chrome://extensions/` in your browser automatically.
+4. You enable **Developer mode** (top-right toggle), click **Load unpacked**, and paste the path.
+5. Press Enter in the terminal and the server starts.
+
+**You only do this once.** The extension stays loaded in Chrome across sessions.
+
+### Step 4: Start an AI session
+
+1. Open any supported AI chat (ChatGPT, Gemini, Claude, or HuggingFace Chat).
+2. Click the Browse Code Bridge extension icon and set your workspace directory.
+3. Click "Initialize Agent in Chat".
+4. Start coding with AI — it now has full access to your local environment.
+
+## Subsequent Usage
+
+After the first-time setup, just run:
+
+```bash
+bc
+```
+
+The server starts immediately. Open your AI chat tab and you're ready to go. The server terminal will show:
+- A startup banner with your workspace and endpoint
+- `[+] Extension connected` when the browser extension connects
+- Real-time logs of every file read, write, command execution, and diff
+
+## Features
+
+- **File Operations:** Read, write, and patch files with inline terminal diffs
+- **Code Search:** Search across your entire codebase by keyword
+- **Terminal Commands:** Run shell commands with full stdout/stderr capture
+- **Background Processes:** Start, monitor, and kill long-running processes
+- **Multi-Platform AI:** Works with ChatGPT, Gemini, Claude, and HuggingFace Chat
+- **Extension Heartbeat:** Server detects when the browser extension connects/disconnects
+
+## For Developers
+
+1. Clone the repository:
+   ```bash
+   git clone https://github.com/Dedeep007/browse_code.git
+   cd browse_code
+   ```
+2. Install in editable mode:
+   ```bash
+   pip install -e .
+   ```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+1. Fork the repository.
+2. Create your feature branch (`git checkout -b feature/AmazingFeature`).
+3. Commit your changes (`git commit -m 'Add some AmazingFeature'`).
+4. Push to the branch (`git push origin feature/AmazingFeature`).
+5. Open a Pull Request.
+
+## License
+
+Distributed under the MIT License.

browse_code-0.2.0/browse_code/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.2.0"

browse_code-0.2.0/browse_code/cli.py

@@ -0,0 +1,204 @@
+import os
+import sys
+import shutil
+import platform
+import subprocess
+import webbrowser
+from pathlib import Path
+
+# ── Rich TUI imports ──────────────────────────────────────
+from rich.console import Console
+from rich.panel import Panel
+from rich.text import Text
+from rich.table import Table
+from rich.prompt import Prompt, Confirm
+from rich import box
+
+console = Console()
+
+PORT = 5505
+HOST = "127.0.0.1"
+
+
+def get_data_dir():
+    """Return ~/.browse_code, creating it if needed."""
+    data_dir = Path.home() / ".browse_code"
+    data_dir.mkdir(exist_ok=True)
+    return data_dir
+
+
+def copy_to_clipboard(text):
+    """Copy text to the system clipboard (cross-platform)."""
+    try:
+        system = platform.system()
+        if system == "Windows":
+            subprocess.run("clip", input=text.encode("utf-8"), check=True)
+        elif system == "Darwin":
+            subprocess.run("pbcopy", input=text.encode("utf-8"), check=True)
+        else:
+            try:
+                subprocess.run(
+                    ["xclip", "-selection", "clipboard"],
+                    input=text.encode("utf-8"),
+                    check=True,
+                )
+            except FileNotFoundError:
+                subprocess.run(
+                    ["xsel", "--clipboard", "--input"],
+                    input=text.encode("utf-8"),
+                    check=True,
+                )
+        return True
+    except Exception:
+        return False
+
+
+def print_banner():
+    """Print the Browse Code ASCII art banner."""
+    banner_text = Text()
+    banner_text.append("  { ", style="bold cyan")
+    banner_text.append("Browse Code", style="bold white")
+    banner_text.append(" }", style="bold cyan")
+
+    console.print()
+    console.print(
+        Panel(
+            banner_text,
+            box=box.DOUBLE,
+            border_style="cyan",
+            padding=(1, 4),
+        )
+    )
+
+
+def setup_extension():
+    """First-time setup: extract extension, open Chrome, guide the user."""
+    data_dir = get_data_dir()
+    ext_dest = data_dir / "extension"
+    pkg_ext_dir = Path(__file__).parent / "extension"
+
+    print_banner()
+    console.print()
+    console.print(
+        Panel(
+            "[bold]First Time Setup[/bold]\n\n"
+            "Browse Code needs a Chrome extension to connect\n"
+            "your browser to the local server.",
+            border_style="yellow",
+            box=box.ROUNDED,
+            padding=(1, 2),
+        )
+    )
+
+    if not Confirm.ask("\n  Do you want to set up the extension now?", default=True):
+        console.print("  [dim]Skipped. Re-run 'bc' anytime to set it up.[/dim]")
+        return False
+
+    # Extract extension files
+    console.print()
+    with console.status("[cyan]Extracting extension files...[/cyan]"):
+        if ext_dest.exists():
+            shutil.rmtree(ext_dest)
+        shutil.copytree(pkg_ext_dir, ext_dest)
+
+    ext_path_str = str(ext_dest)
+    console.print(f"  [green]Extracted to:[/green] [bold]{ext_path_str}[/bold]")
+    console.print()
+
+    # Copy path to clipboard
+    copied = copy_to_clipboard(ext_path_str)
+
+    # Open chrome://extensions
+    console.print("  [cyan]Opening Chrome extensions page...[/cyan]")
+    webbrowser.open("chrome://extensions/")
+
+    # Setup instructions
+    steps = Table(
+        show_header=False,
+        box=box.SIMPLE,
+        padding=(0, 2),
+        show_edge=False,
+    )
+    steps.add_column("step", style="bold cyan", width=4)
+    steps.add_column("instruction")
+
+    steps.add_row("1.", 'Enable [bold]"Developer mode"[/bold] toggle (top-right corner)')
+    steps.add_row("2.", 'Click [bold]"Load unpacked"[/bold]')
+    if copied:
+        steps.add_row("3.", "Paste the path [green](already copied to your clipboard)[/green]")
+    else:
+        steps.add_row("3.", f"Select this folder: [bold]{ext_path_str}[/bold]")
+
+    console.print()
+    console.print(
+        Panel(
+            steps,
+            title="[bold]Quick Setup[/bold]",
+            title_align="left",
+            border_style="cyan",
+            box=box.ROUNDED,
+            padding=(1, 1),
+        )
+    )
+    console.print()
+
+    Prompt.ask("  Press [bold]Enter[/bold] after you've loaded the extension")
+
+    # Mark as installed
+    marker = data_dir / ".installed"
+    marker.touch()
+
+    console.print("  [bold green]Extension setup complete![/bold green]")
+    return True
+
+
+def print_server_header():
+    """Print the server status panel before starting."""
+    info = Table(show_header=False, box=None, padding=(0, 1), show_edge=False)
+    info.add_column("key", style="dim", width=12)
+    info.add_column("value")
+
+    info.add_row("Endpoint", f"[bold]http://{HOST}:{PORT}[/bold]")
+    info.add_row("Extension", "[yellow]Waiting for connection...[/yellow]")
+    info.add_row("Status", "[green]Running[/green]")
+
+    console.print(
+        Panel(
+            info,
+            title="[bold cyan]{ [/bold cyan][bold white]Browse Code[/bold white][bold cyan] }[/bold cyan]",
+            title_align="left",
+            subtitle="[dim]Press Ctrl+C to stop[/dim]",
+            subtitle_align="right",
+            border_style="cyan",
+            box=box.ROUNDED,
+            padding=(1, 2),
+        )
+    )
+    console.print()
+
+
+def main():
+    data_dir = get_data_dir()
+    marker = data_dir / ".installed"
+
+    if not marker.exists():
+        result = setup_extension()
+        if not result:
+            return
+    else:
+        print_banner()
+
+    console.print()
+    print_server_header()
+
+    try:
+        from .server import app
+    except ImportError:
+        from server import app
+
+    import uvicorn
+    uvicorn.run(app, host=HOST, port=PORT, access_log=False)
+
+
+if __name__ == "__main__":
+    main()