Skip to main content

ArtiNator: Your Agentic Systems and Network Coding Assistant

Welcome to ArtiNator, an automated coding assistant designed for systems and networks programmers. ArtiNator leverages the power of Large Language Models (LLMs) to help you navigate, understand, and manipulate your project's environment efficiently.

🌟 Why Dynamic Prompts?

Traditional prompts become outdated as your code evolves. Our dynamic prompt system ensures your AI interactions remain relevant, accurate, and valuable throughout your development lifecycle.

Stop maintaining prompts manually - let them maintain themselves!

Features

  • Dynamic Prompt Creation: ArtiNator dynamically builds prompts based on your input, enhancing the relevance and accuracy of responses.
  • Contextual Awareness: Automatically attaches file contents and command outputs to the prompt context, ensuring comprehensive answers.
  • Command Execution: Runs shell commands to gather necessary information or execute tasks, making it an active participant in your workflow.

Key Commands

shoot Command

The shoot command is designed for one-shot LLM queries without looping. It parses the prompt to:

  • Automatically attach the content of any file path mentioned in the prompt.
  • Run any command enclosed in ^ symbols and attach its output to the context.
  • If the command output contains relative paths, ArtiNator will attach those file contents as well.

Usage Examples:

# To explain foo.py and attach the file content to the context
artinator shoot explain my/foo.py

# To run "your command", parse its output, and attach it to the context
# Useful for debugging tracebacks that include relative paths
artinator shoot what breaks ^my command^ is it a bug in foo.py

loop Command

The loop command allows the LLM to run bash commands iteratively until it can answer your query comprehensively. It's perfect for tasks that require ongoing interaction or more complex problem-solving.

Usage Example:

# To fix a test, ArtiNator will suggest and run commands until the issue is resolved
artinator loop fix some test

How it Works:

  • ArtiNator suggests one complete, executable shell command at a time within suggestedcommand blocks.
  • It uses verbose flags where applicable to gather detailed context.
  • The assistant avoids interactive commands and placeholders, ensuring all commands are ready to execute.
  • It navigates the project directory structure using commands like ls, cat, or grep to inspect files and gather necessary context.
  • ArtiNator stops suggesting commands once it has enough context to provide a complete, relevant answer.

How to Use

  1. Install ArtiNator: Use pip install artinator
  2. Run Commands: Use artinator shoot for one-shot queries or artinator loop for iterative problem-solving.
  3. Interact: Respond to ArtiNator's command suggestions with 'y' (yes), 'n' (no), or 'a' (accept all) to control command execution.

ArtiNator is designed to enhance your productivity by automating the gathering of context and providing intelligent, context-aware responses to your queries. Dive into your projects with confidence, knowing ArtiNator is there to assist every step of the way!

Release files for artinator 1.1.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for artinator 1.1.5
File Size Uploaded
artinator-1.1.5.tar.gz 18.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for artinator 1.1.5
File Interpreter ABI Platform
artinator-1.1.5-py3-none-any.whl Python 3 none any Details

Total release size: 37.7 kB

Release files / artinator-1.1.5.tar.gz

Download URL artinator-1.1.5.tar.gz
Size 18.4 kB
Tags Source
SHA-256 checksum
How to use checksums
879fa585936a5c80eacbd86bf049f7ba57044456d5efb216624d7a6386baa840
BLAKE2b-256 checksum
How to use checksums
05c8404a855fd9d19a8b0591c9076b4a2162c4ecdfe4e3a2a4d8ccde32748401
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.13.7

Release files / artinator-1.1.5-py3-none-any.whl

Download URL artinator-1.1.5-py3-none-any.whl
Size 19.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3ad225ef625530bd09ba1323c19286bea093965d4ebcfddcdc86c1b4cdb01b73
BLAKE2b-256 checksum
How to use checksums
aa3d9f42ebc134ac9b3dfb10aef783aecd38175d4e0fadb66bd488e9b0a6a305
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.13.7

Release history Release notifications | RSS feed

This release

1.1.5 This release

2 release files

1.1.4

2 release files

1.1.3

2 release files

1.1.2

2 release files

1.1.1

2 release files

1.1.0

2 release files

1.0.1

1 release file

1.0.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page