# anysphere/priompt

Prompt design using JSX.

Repository: https://github.com/anysphere/priompt
Canonical: https://ross.abutalabs.com/products/priompt
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2025-10-15T01:17:29+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 47, release rhythm 35, longevity 83
- inputs: {"age_days": 1167, "days_push": 323, "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 2850, forks 159 (observed 2026-08-28T04:07:25.619733+00:00)

## What it is
Priompt is a JSX-based prompt design library for building LLM prompts with React-like components. It uses priority levels to decide which prompt components fit within the context window's token limit.

## Use cases
- build llm prompts with jsx components
- prioritize which context to include when token limit is exceeded
- compose chat prompts from message history with fallbacks
- reserve token space in prompts for model responses
- design prompts declaratively like react components

## When to choose
- you build LLM applications in TypeScript and want declarative prompt composition
- you need fine-grained control over what gets dropped when context overflows
- you want React-style component reuse for prompt engineering

## When to avoid
- you work in Python or another non-JS language
- you need a full LLM orchestration framework with agents and tooling
- you prefer simple string-template prompts without priority logic

## Facets
- artifact type: library
- maturity: active
- function: prompt-engineering, llm-inference, templating
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: -
- tags: jsx, prompt-design, context-window, token-prioritization, llm, nodejs, typescript

## Member repositories
- anysphere/priompt (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:25.619733+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 2026-08-30T07:36:54.646696+00:00, confidence not recorded.
  - readme: https://github.com/anysphere/priompt (fetched 2026-08-28T04:07:25.619733+00:00, sha 32c6c67b96b5)
- Data as of 2026-08-30T08:39:29.467469+00:00.