Metadata-Version: 2.1
Name: prisl-code
Version: 1.0.0
Summary: Autonomous CLI powered by local LLMs with self-healing tools
Author: rx76d
License: MIT
Project-URL: Homepage, https://github.com/rx76d/prisl-code
Project-URL: Repository, https://github.com/rx76d/prisl-code.git
Project-URL: Issues, https://github.com/rx76d/prisl-code/issues
Project-URL: Documentation, https://github.com/rx76d/prisl-code/blob/main/README.md
Project-URL: Changelog, https://github.com/rx76d/prisl-code/releases
Keywords: llm,cli,agentic,autonomous,local-llm
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: openai>=1.0.0
Requires-Dist: rich>=13.0.0
Requires-Dist: prompt-toolkit>=3.0.0
Requires-Dist: psutil>=5.9.0

# Prisl Code
![Version](https://img.shields.io/badge/version-v1.0.0-blue)
![License](https://img.shields.io/badge/license-MIT-green)
![Platform](https://img.shields.io/badge/platform-windows%20%7C%20macos%20%7C%20linux-default)
![Downloads](https://img.shields.io/pypi/dm/prisl-code)


A local AI coding assistant for your terminal that runs GGUF models using llama.cpp locally.
It can read, write, and execute code in your projects while running offline in an isolated environment.
>You can run your own server too it will detect it and will connect.

## Installation
Prisl Code is designed to be a one-command setup.
```bash
pip install prisl-code
```

## Usage

Once installed, navigate to any folder on your computer and start the assistant by typing:

```bash
prisl-code
```

On its first run, Prisl Code checks for an active LLM server (ports 8080/11434). If none is found, it offers to automatically download `llama-server` and opens a native file picker for you to select your GGUF model.

## Basics
**Add context:**
- Type @filename.py anywhere in your message to instantly inject that file's contents into the AI's memory.

**Commands:**

 - **@\<filepath\>:** Inject a file's content directly into context.
- **/compact:** Clear conversation history to save tokens (keeps system prompt).
- **/history:** Print a summary of the current conversation history.
- **/save:** Export the current chat history to a Markdown file.
- **/clear:** Clear the terminal screen.
- **/help:** Show this help menu.
- **/exit:** Exit the application.

## Requirements
- Python 3.8+
- Pip 23.0+

## Uninstall

```bash
pip uninstall prisl-code
```

## License

This project is open source and available under the MIT License.

<br>

<div align="center">
<sub>Developed by rx76d</sub>
</div>
