nextpy-agent 0.2.0

NextPy AI Agent - Intelligent coding assistant for NextPy framework

NextPy Agent

Version: 0.1.0
Status: Alpha (Phase B - Stage 1)

Overview

NextPy Agent is an AI-powered coding assistant specifically designed for the NextPy framework. It provides intelligent code generation, debugging, and refactoring capabilities with deep understanding of NextPy's architecture.

Quick Start

Installation

pip install nextpy-agent

Basic Usage

# Start a chat session
nextpy-agent chat

# Or with a specific provider
nextpy-agent chat --provider anthropic
nextpy-agent chat --provider ollama

Phase B - Stage 1 Features

Current Capabilities:

• Multi-provider support (Anthropic, Ollama)
• Interactive chat interface
• Framework-aware context via introspection
• Configuration management
• Quick start (<2 min setup)

Coming Soon (Stages 2-7):

• Tab completion
• Diff rendering
• Inline editing
• RAG with framework documentation
• Memory across sessions
• Composer mode with task planning

Provider Support

Anthropic (Cloud)

• Default provider for zero-install experience
• Requires API key: ANTHROPIC_API_KEY environment variable
• Best for: Production use, highest quality responses

Ollama (Local)

• Optional local provider for privacy and cost savings
• Requires Ollama installation and running service
• Best for: Development, offline use, cost-sensitive projects

Configuration

Create a .env file or set environment variables:

# Anthropic (cloud provider)
ANTHROPIC_API_KEY=your_api_key_here

# Ollama (local provider)
OLLAMA_BASE_URL=http://localhost:11434
OLLAMA_MODEL=gemma3:4b

# Default provider
NEXTPY_PROVIDER=anthropic

Development

Setup

# Clone repository
git clone https://github.com/IBRAHIMFONYUY/nextpy-agent.git
cd nextpy-agent

# Install with dev dependencies
pip install -e ".[dev,ollama]"

# Run tests
pytest

# Format code
black src/
ruff check src/

Architecture

nextpy-agent/
├── src/nextpy_agent/
│   ├── __init__.py
│   ├── cli.py              # Command-line interface
│   ├── config.py           # Configuration management
│   ├── providers/          # LLM provider implementations
│   │   ├── __init__.py
│   │   ├── base.py         # Abstract provider interface
│   │   ├── anthropic.py    # Anthropic provider
│   │   └── ollama.py       # Ollama provider
│   └── chat.py             # Chat functionality
├── tests/
├── pyproject.toml
└── README.md

Roadmap

Phase B - Stage 1 (Current)

• ✅ Provider interface
• ✅ Anthropic integration
• ✅ Ollama integration
• ✅ Basic chat functionality
• ✅ Configuration management

Phase C - Stages 2-3

• Tab completion
• Diff rendering
• Inline editing

Phase D - Stages 4-5

• RAG with framework docs
• Memory across sessions

Phase E - Stages 6-7

• Composer mode
• Task planning and execution
• AST-aware editing

License

MIT License - see LICENSE file for details.

Contributing

Contributions welcome! Please see CONTRIBUTING.md for guidelines.