# hegelai/prompttools

Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).

Repository: https://github.com/hegelai/prompttools
Canonical: https://ross.abutalabs.com/products/prompttools
Homepage: http://prompttools.readthedocs.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, large-language-models, machine-learning, prompt-engineering, python, embeddings, llms, vector-search, developer-tools
Last push: 2026-02-11T03:24:04+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 8, longevity 83
- inputs: {"age_days": 1165, "days_push": 203, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3051, forks 256 (observed 2026-08-28T04:07:39.618989+00:00)

## What it is
PromptTools is an open-source Python library for testing, experimenting with, and evaluating prompts, LLMs (OpenAI, Anthropic, LLaMA, etc.), and vector databases (Chroma, Weaviate, LanceDB). It supports evaluation via code, Jupyter notebooks, and a local Streamlit playground.

## Use cases
- compare prompt outputs across multiple LLM models
- evaluate retrieval accuracy of a vector database
- A/B test prompt templates and model parameters like temperature
- run LLM experiments in a Jupyter notebook
- self-host a playground for prompt experimentation
- evaluate responses from OpenAI, Anthropic, or LLaMA models

## When to choose
- you need to systematically test and compare prompts or LLM parameters
- you want to benchmark vector database retrieval quality
- you prefer notebook-based or self-hosted evaluation workflows
- you want a free, open-source alternative to hosted prompt evaluation tools

## When to avoid
- you need production LLM observability and tracing in live applications
- you want a fully managed cloud evaluation service
- you need CI-integrated LLM testing pipelines with team dashboards

## Facets
- artifact type: library
- maturity: active
- function: prompt-engineering, testing, benchmarking, machine-learning, llm-inference, vector-database, data-visualization
- domain: large-language-models, machine-learning, deep-learning, developer-tools, databases
- platform: python, cross-platform, self-hosted
- tags: llm-evaluation, prompt-testing, vector-search, experimentation, notebooks, playground, search

## Member repositories
- hegelai/prompttools (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:39.618989+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:28:53.704972+00:00, confidence not recorded.
  - readme: https://github.com/hegelai/prompttools (fetched 2026-08-28T04:07:39.618989+00:00, sha 0bdc5fa375d0)
  - registry_pypi: https://pypi.org/pypi/prompttools/json (fetched 2026-08-29T09:44:27.576998+00:00, sha fd08d058302d)
- Data as of 2026-08-30T08:39:29.467469+00:00.