Mirascope/lilypad
Open-source versioning, tracing, and annotation tooling.
When working with AI models (like ChatGPT), their responses can vary, making it hard to track what worked best. This tool helps you keep a record of every input you send to an AI model and every response it gives back, along with details about the specific AI code that generated it. This allows AI developers and data scientists to systematically improve their AI applications.
214 stars.
Use this if you are building applications with large language models and need to track, version, and evaluate their non-deterministic outputs.
Not ideal if you are looking for a maintained solution, as this project is deprecated in favor of Mirascope v2 and Mirascope Cloud.
Stars
214
Forks
16
Language
Python
License
—
Category
Last pushed
Jan 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/Mirascope/lilypad"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
Supervertaler/Supervertaler-Workbench
Open-source, AI-enhanced CAT tool with multi-LLM support, translation memory, glossary...
crjaensch/PromptoLab
A multi-platform app to serve as a prompts catalog, a LLM playground for running and optimizing...
parea-ai/parea-sdk-py
Python SDK for experimenting, testing, evaluating & monitoring LLM-powered applications - Parea...
geeknees/sentinel_rb
SentinelRb is an LLM-driven prompt inspector designed to automatically detect common...
NeuroTinkerLab/synt-e-project
A Python tool to translate natural language requests into efficient, single-line commands for AI...