🤖 Dev Agent - Your Intelligent Development Assistant

An intelligent command-line agent that understands natural language and helps you manage files, analyze code, and automate development tasks.

A full-stack AI agent platform with:

• Python-based tool-driven agent
• FastAPI service layer
• Modern Next.js SaaS dashboard
• Session-based conversations
• Multi-chat support
• Glass-style UI
• Developer automation tools

✨ Features

🧠 Agent Core

• Natural language intent routing
• Tool registry + argument extraction
• Conversation memory
• File system automation
• Code analysis
• Git integration
• Web search & scraping

🌐 Web Dashboard (NEW)

• ChatGPT-style UI
• Sidebar conversation history
• Dark SaaS theme
• Session persistence
• FastAPI integration
• Health checks
• Multi-conversation support

⚙️ API Layer

• /agent/chat
• /agent/reset
• /agent/health
• CORS enabled
• Session management

📁 File System Operations

• Create, delete, rename files and folders
• Open files and folders with default applications
• Preview file contents
• Smart path resolution (Desktop, Downloads, Documents shortcuts)

🔍 Intelligent Search

• Search files by name, extension, or content
• Find recently modified files
• Multi-root search across common directories

💻 Code Analysis

• Dead code detection in Python files
• LLM-powered code explanations (via Groq API)
• Intent-based code search
• Function-level analysis

🔧 Development Tools

• Create virtual environments
• Install Python packages
• Git status and commit history
• Project-aware operations

🌐 Web Integration

• Web search (DuckDuckGo)
• Fetch URL contents
• Integration-ready architecture

🚀 Quick Start

Installation

# Clone the repository
git clone https://github.com/praharshithavishnubhatla/dev-agent.git
cd dev-agent

# Install dependencies
pip install -r requirements.txt

# (Optional) Set up Groq API for LLM features
export GROQ_API_KEY="your_api_key_here"

Usage

# Run the agent
python agent.py

Example Commands

🧠 You: create a file called notes.txt on desktop
🤖 Agent: ✅ File created at `/Users/you/Desktop/notes.txt`

🧠 You: find dead code in my project
🤖 Agent: 🧠 Dead code report:
         {'/path/to/file.py': ['unused_function', 'old_helper']}

🧠 You: explain main.py
🤖 Agent: 🧠 LLM Code Summary — main.py
         This script implements a command-line interface...

🧠 You: search files containing "TODO"
🤖 Agent: Found 5 files: [...list of files...]

🧠 You: install requests fastapi in myproject
🤖 Agent: 📦 Installing packages: requests, fastapi

📖 Documentation

Intent Classification

The agent understands natural language commands and classifies them into intents:

Command	Intent	What it does
"create test.py"	create_file	Creates a new file
"open main.py"	open_file	Opens file with default app
"find dead code"	dead_code_detector	Analyzes project for dead code
"explain app.py"	llm_summarize_code	AI explanation of code
"search for TODO"	search_files_by_content	Searches file contents
"git status"	git_status	Shows git status
"create venv in project"	create_virtualenv	Creates virtual environment

Supported Intents

File Operations:

• create_file, create_folder
• open_file, open_folder
• delete_path, rename_file
• preview_file

Code Analysis:

• dead_code_detector, dead_code_in_file
• llm_summarize_code
• code_intent_search

Search:

• search_files_by_name
• search_files_by_extension
• search_files_by_content
• list_recent_files

Development:

• create_virtualenv
• install_packages
• git_status, git_last_commits

Web:

• open_web_search, fetch_url

Architecture

dev-agent/
├── agent.py                 # Main entry point
├── tools/                   # Tool implementations
│   ├── fs.py               # File system operations
│   ├── search.py           # File search utilities
│   ├── code_analysis.py    # Code analysis tools
│   ├── git.py              # Git operations
│   ├── execution.py        # Virtual env & packages
│   └── web.py              # Web utilities
├── routing/                # Intent routing & extraction
│   ├── intent_classifier.py
│   ├── argument_extractor.py
│   └── tool_registry.py
├── core/                   # Core agent logic
│   ├── interactive_executor.py
│   ├── conversation_state.py
│   └── memory.py
└── tests/                  # Test suite

🧪 Testing

Run the comprehensive test suite:

python tests/test_agent.py

Current test coverage: 100% passing (39/39 tests)

🔧 Configuration

Groq API Setup (for LLM features)

1. Get a free API key from Groq
2. Set the environment variable:

   export GROQ_API_KEY="your_api_key_here"

3. The agent will automatically use it for code explanations

Search Roots Configuration

Edit SEARCH_ROOTS in core/interactive_executor.py to customize where the agent searches:

SEARCH_ROOTS = [
    "~/Downloads",
    "~/Documents",
    "~/your-projects-folder"
]

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

Development Setup

# Clone and install in development mode
git clone https://github.com/praharshithavishnubhatla/dev-agent.git
cd dev-agent
pip install -e .

# Run tests
python tests/test_agent.py

Adding New Tools

1. Create tool function in appropriate file under tools/
2. Register in routing/tool_registry.py
3. Add schema in routing/tool_schema.py
4. Add questions in routing/tool_questions.py
5. Update intent classifier if needed
6. Add tests

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Built with Python
• LLM integration via Groq
• Inspired by modern AI assistants and agentic workflows

📞 Contact

Have questions or suggestions? Open an issue or reach out!

---

Note: This is a personal development tool. Always review commands before execution, especially destructive operations like delete.

🎯 Roadmap

• Support for more LLM providers (OpenAI, Anthropic, local models)
• Interactive mode improvements (autocomplete, history)
• More code analysis features (complexity metrics, linting)
• Docker container support
• Web UI interface
• Plugin system for custom tools
• Multi-language support (beyond Python)
• Automated testing suggestions
• Code refactoring recommendations

🐛 Known Issues

None currently! If you find a bug, please open an issue.