Declare LLM prompts with TSX

Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts

A TypeScript library for validating and securing LLM prompts

Meld: A template language for LLM prompts

Token-efficiency linter for LLM prompts and payloads

Pipedream LLM prompts

Use MDX to render high quality LLM prompts

Source code generation with LLM prompts

Strongly-typed template engine for LLM prompts, designed for markdown

A test framework for LLM prompts. Write evals in Markdown, run them like tests.

One-shot LLM prompts

Token-Oriented Object Notation (TOON) – A compact, deterministic JSON format for LLM prompts

Optimize LLM prompts to reduce tokens, save costs, and improve performance

MCP Server for managing LLM prompts

Static security scanner for LLM prompts — CLI tool

Tiny utilities for crafting LLM prompts, parsing partial JSON streams, and helpful text/JSON helpers.

Analyze LLM prompts before you send them.

Static analysis for LLM prompts — catch cost waste, quality issues, and injection risks

> Command-line tools for analyzing, linting, and benchmarking LLM prompts. Find token waste, duplicate instructions, and quality issues before they reach your model.

Define, train, and use optimized LLM prompts