PromptOps

Git-native prompt versioning for production LLM agents

Stable v0.1.0 Python 3.8+

Why PromptOps?

Your agent's behavior is defined by prompt text — but most teams ship prompts as raw strings baked into code, with no version history, no rollback, and no way to test a change before it hits production.

PromptOps turns prompts into first-class versioned artifacts. Every git commit auto-tags your prompts with a semantic version. Reference any version in code by name: :latest for production, :v1.2.0 for a specific release, or :unstaged to test uncommitted changes without touching anything live. No more "what prompt was running last Tuesday?"

Features

Automated Git Versioning

Zero-manual versioning with git hooks and semantic version detection. Every commit auto-tags your prompts.

Uncommitted Change Testing

Test prompts instantly with :unstaged, :working, :latest references before committing.

Cross-Version Comparison

Test and compare any two prompt versions side-by-side. Catch behavioral changes before they reach production.

Zero-Config Git Hooks

Pre-commit and post-commit hooks installed automatically. Versioning happens on every commit — nothing to remember.

Installation

terminal bash 
pip install llmhq-promptops

Quick Start

terminal bash 
# Create a new project with git hooks
promptops init repo

# Create a new prompt template
promptops create prompt welcome-message

# Test uncommitted changes
promptops test --prompt welcome-message:unstaged

# Check status of all prompts
promptops test status

Python SDK

app.py python 
from llmhq_promptops import get_prompt

# Smart default (unstaged if different, else working)
prompt = get_prompt("user-onboarding")

# Specific version references
prompt = get_prompt("user-onboarding:v1.2.1")
prompt = get_prompt("user-onboarding:unstaged")
prompt = get_prompt("user-onboarding:working")

# With variables
rendered = get_prompt("user-onboarding", {
    "user_name": "Alice",
    "plan": "Pro"
})

Framework Integration

Works with any LLM framework. Get a versioned prompt, pass it to your provider.

integrations.py python 
from llmhq_promptops import get_prompt

prompt_text = get_prompt("user-onboarding:working", {
    "user_name": "John",
    "plan": "Enterprise"
})

# Use with OpenAI
import openai
response = openai.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": prompt_text}]
)

# Use with Anthropic
import anthropic
client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-sonnet-4-5-20250929",
    messages=[{"role": "user", "content": prompt_text}]
)

Requirements

  • Python 3.8+
  • Git (required for versioning)
  • Dependencies: Typer, Jinja2, PyYAML, GitPython

Links

PyPI Package GitHub Report Issues Discussions

See it in action

Watch PromptOps version prompts and feed them into ReleaseOps bundles.

Interactive Demo ReleaseOps Docs