GraphCanon updated 3w · GitHub synced 3w
Decision brief
PromptSite is designed for managing and tracking prompt versions in LLM projects with Python, providing an easy-to-use decorator for streamlined integration.
Good fit when
- When your project requires detailed version control of prompts, as PromptSite manages versions effectively through its decorator.
- If you are working within a Python environment, since PromptSite specifically supports Python and integrates well with it.
Avoid when
- If your development team or project does not use Python, because PromptSite is strictly for Python-based projects only.
- When a minimal package size is critical, as although PromptSite is lightweight, competitors might offer even more compact solutions without sacrificing necessary features.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (544d since push)
- As of 3w
- Provenance
- Not a fork · Personal account
- As of 3w
- Security (OSV)
- 35 low (35 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install promptsite PyPISimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
PromptSite manages versions, tracks experiments, and aids in debugging LLM prompts. It supports Python and offers an easy-to-use decorator for tracking prompt versions and runs.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 2, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 2, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
Installation
pip install promptsite
Quick Start with the Decorator
The following example shows how to use the @tracker decorator to auto track your prompt versions andruns in your LLM calls.
For agents
This page has a .md twin and JSON over the API.