Metadata-Version: 2.4
Name: tarang
Version: 4.7.0
Summary: Tarang - AI Coding Agent (Hybrid WebSocket Architecture)
Author-email: Tarang Team <hello@devtarang.ai>
License: MIT
Project-URL: Homepage, https://devtarang.ai
Project-URL: Documentation, https://docs.devtarang.ai
Project-URL: Repository, https://github.com/tarang-ai/tarang-cli
Keywords: ai,coding,assistant,llm,developer-tools
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Code Generators
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: click>=8.0.0
Requires-Dist: httpx>=0.25.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: rich>=13.0.0
Requires-Dist: websockets>=12.0
Requires-Dist: prompt_toolkit>=3.0.0
Requires-Dist: rank-bm25>=0.2.2
Requires-Dist: tree-sitter>=0.23.0
Requires-Dist: tree-sitter-python>=0.23.0
Requires-Dist: tree-sitter-javascript>=0.23.0
Requires-Dist: tree-sitter-sql>=0.3.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"
Requires-Dist: mypy>=1.0.0; extra == "dev"

# Tarang CLI

AI-powered coding assistant with ManagerAgent architecture.

## Installation

```bash
pip install tarang
```

## Quick Start

```bash
# Start interactive session
tarang run

# Run a single instruction
tarang run "create a hello world app"

# Run and exit
tarang run "fix linter errors" --once
```

## Commands

- `tarang run [instruction]` - Start coding session (interactive or single)
- `tarang init <project>` - Initialize a new project
- `tarang chat` - Interactive chat mode
- `tarang status` - Show project status
- `tarang resume` - Resume interrupted execution
- `tarang reset` - Reset execution state
- `tarang clean` - Remove all Tarang state
- `tarang check` - Verify configuration

## Options

- `--project-dir, -p` - Project directory (default: current)
- `--config, -c` - Agent config (coder, explorer, orchestrator)
- `--verbose, -v` - Enable verbose output
- `--once` - Run single instruction and exit

## Configuration

Tarang requires an OpenRouter API key:

```bash
export OPENROUTER_API_KEY=your_key
```

## Project State

Tarang stores execution state in `.tarang/` directory:
- `state.json` - Current execution state
- Supports resume after interruption

## Links

- Website: [devtarang.ai](https://devtarang.ai)
- Documentation: [docs.devtarang.ai](https://docs.devtarang.ai)

## License

MIT
