# character-ai/prompt-poet

Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

Repository: https://github.com/character-ai/prompt-poet
Canonical: https://ross.abutalabs.com/products/prompt-poet
Homepage: https://pypi.org/project/prompt-poet/
Language: Python
License: MIT
License Family: permissive
Topics: prompt-engineering, llm, llm-inference, prompt, prompt-design, prompt-tuning, prompting
Last push: 2026-02-12T02:12:29+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 35, longevity 55
- inputs: {"age_days": 778, "days_push": 203, "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 1155, forks 95 (observed 2026-08-28T04:03:47.865687+00:00)

## What it is
Prompt Poet is a Python library for designing LLM prompts using YAML and Jinja2 templates in a low-code approach. It renders dynamic, structured prompt messages with roles and truncation priorities for use with AI models.

## Use cases
- build dynamic llm prompts from templates
- design chat prompts without string manipulation
- manage prompt parts with roles and truncation priority
- let non-technical users edit prompt templates in yaml
- render jinja2 prompt templates for langchain models

## When to choose
- you want declarative, versioned prompt templates instead of f-string concatenation
- your team includes non-developers who need to edit prompts
- you need fine-grained control over prompt part truncation and roles

## When to avoid
- you need a full prompt management platform with evaluation and A/B testing
- your prompts are simple enough that plain f-strings suffice
- you are not working in a Python LLM stack

## Facets
- artifact type: library
- maturity: active
- function: prompt-engineering, templating, llm-inference
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python
- tags: prompt-templates, jinja2, yaml, low-code, llm-prompting

## Member repositories
- character-ai/prompt-poet (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:47.865687+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 2026-08-30T06:32:12.018680+00:00, confidence not recorded.
  - readme: https://github.com/character-ai/prompt-poet (fetched 2026-08-28T04:03:47.865687+00:00, sha a99d43c897a2)
  - homepage: https://pypi.org/project/prompt-poet/ (fetched 2026-08-29T12:37:32.104047+00:00, sha 4b4e8fead74a)
  - registry_pypi: https://pypi.org/pypi/prompt-poet/json (fetched 2026-08-29T12:37:32.113122+00:00, sha fc13d2351877)
- Data as of 2026-08-30T08:39:29.467469+00:00.