# Eladlev/AutoPrompt

A framework for prompt tuning using Intent-based Prompt Calibration

Repository: https://github.com/Eladlev/AutoPrompt
Canonical: https://ross.abutalabs.com/products/autoprompt
Language: Python
License: Apache-2.0
License Family: permissive
Topics: prompt-engineering, prompt-tuning, synthetic-dataset-generation
Last push: 2025-12-02T17:23:20+00:00

## Health v2 (maintenance only)
Score: 42/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 55, release rhythm 8, longevity 71
- inputs: {"age_days": 1005, "days_push": 274, "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 3010, forks 265 (observed 2026-08-28T04:07:37.789840+00:00)

## What it is
AutoPrompt is a Python framework for optimizing LLM prompts using Intent-based Prompt Calibration. It iteratively generates challenging edge-case datasets, annotates them, and refines prompts to produce robust, production-grade prompts with measured accuracy.

## Use cases
- optimize and refine LLM prompts automatically
- generate synthetic datasets of challenging edge cases for prompt evaluation
- benchmark production-grade prompts with minimal annotation effort
- migrate prompts between LLM models
- build robust moderation or classification prompts
- create ranker prompts for content generation tasks

## When to choose
- you need reliable, robust prompts for real-world LLM applications
- manual prompt engineering is too time-consuming or error-prone
- you want to build evaluation benchmarks with minimal labeled data
- you need synthetic data generation combined with prompt optimization

## When to avoid
- you need a simple one-off prompt tweak without iterative optimization
- your project has no budget for LLM API calls during calibration
- you require fine-tuning of model weights rather than prompts

## Facets
- artifact type: framework
- maturity: active
- function: prompt-engineering, machine-learning, data-generation, llm-training
- domain: large-language-models, artificial-intelligence, machine-learning, developer-tools
- platform: python, cross-platform
- tags: prompt-optimization, prompt-tuning, synthetic-data, llm-evaluation, intent-based-prompt-calibration

## Member repositories
- Eladlev/AutoPrompt (main) score 42

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:37.789840+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 2026-08-30T07:30:12.028451+00:00, confidence not recorded.
  - readme: https://github.com/Eladlev/AutoPrompt (fetched 2026-08-28T04:07:37.789840+00:00, sha 0a4ce76c522f)
- Data as of 2026-08-30T08:39:29.467469+00:00.