# keirp/automatic_prompt_engineer

Repository: https://github.com/keirp/automatic_prompt_engineer
Canonical: https://ross.abutalabs.com/products/automatic_prompt_engineer
Language: Python
License: MIT
License Family: permissive
Last push: 2024-04-29T12:58:17+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1409, "days_push": 856, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1362, forks 172 (observed 2026-08-28T04:04:30.278149+00:00)

## What it is
Automatic Prompt Engineer (APE) is a Python library implementing the research method from 'Large Language Models Are Human-Level Prompt Engineers'. It automatically generates and selects natural language instructions by searching over LLM-proposed prompt candidates to maximize a scoring function.

## Use cases
- automatically generate prompts for an LLM task
- find the best instruction for zero-shot classification
- improve few-shot learning by prepending optimized prompts
- replace manual prompt engineering with automated search
- steer a model toward truthfulness with optimized instructions

## When to choose
- you want to automatically discover effective task instructions instead of handcrafting prompts
- you're reproducing or building on the APE research paper
- you have evaluation data and an OpenAI API key to score candidate prompts

## When to avoid
- you need a production-grade prompt management platform with UI and versioning
- you don't have an OpenAI API key or evaluation datasets
- you need actively maintained tooling - the repo appears research-oriented with limited upkeep

## Facets
- artifact type: library
- maturity: maintenance
- function: prompt-engineering, llm-inference, machine-learning
- domain: large-language-models, artificial-intelligence
- platform: python
- tags: automatic-prompt-engineering, instruction-induction, research-code, openai-api, zero-shot-learning, natural-language-processing

## Member repositories
- keirp/automatic_prompt_engineer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:30.278149+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 2026-08-30T04:41:30.809604+00:00, confidence not recorded.
  - readme: https://github.com/keirp/automatic_prompt_engineer (fetched 2026-08-28T04:04:30.278149+00:00, sha be8afac0cb56)
- Data as of 2026-08-30T08:39:29.467469+00:00.