Implementation
Prompty has runtime implementations in multiple languages. Each follows the same pipeline architecture but uses language-native patterns and package managers.
| Language | Status | Package |
|---|---|---|
| Python | ✅ Stable (alpha) | prompty on PyPI |
| TypeScript | ✅ Stable (alpha) | @prompty/core on npm |
| C# | ✅ Alpha | Prompty.Core, Prompty.OpenAI, Prompty.Foundry, Prompty.Anthropic on NuGet |
| Rust | ✅ Alpha | prompty, prompty-openai, prompty-foundry, prompty-anthropic on crates.io |
Choosing a Runtime
Section titled “Choosing a Runtime”All runtimes share the same .prompty file format — a prompt written for one
runtime works with any other. The differences are in installation, API style,
and available providers.
Python
Section titled “Python”- Most mature runtime with all features implemented
- Async support via
_asyncvariants of every function - Entry-point-based plugin discovery
- Install:
uv pip install prompty[all]
TypeScript
Section titled “TypeScript”- Modular package architecture (
@prompty/core+ provider packages) - Native async/await throughout
- Provider registration via side-effect imports
- Install:
npm install @prompty/core @prompty/openai
- Alpha packages available on NuGet:
Prompty.Core,Prompty.OpenAI,Prompty.Foundry,Prompty.Anthropic - Static
PipelineAPI with async-first design - Same four-stage render → parse → execute → process architecture
- Install:
dotnet add package Prompty.Core --prerelease
- Async-only runtime (Tokio) with zero-cost abstractions
- Modular crate architecture (
promptycore + provider crates) - Trait-based plugin system (
Executor,Processor,Renderer,Parser) - Full agent loop with events, cancellation, guardrails, and steering
- Install:
cargo add prompty prompty-openai
Provider Packages
Section titled “Provider Packages”| Provider | Python | TypeScript | C# | Rust |
|---|---|---|---|---|
| OpenAI | prompty[openai] | @prompty/openai | Prompty.OpenAI | prompty-openai |
| Microsoft Foundry | prompty[foundry] | @prompty/foundry | Prompty.Foundry | prompty-foundry |
| Anthropic | prompty[anthropic] | @prompty/anthropic | Prompty.Anthropic | prompty-anthropic |
Provider feature coverage is not identical in every runtime. For model/deployment discovery support, see Discover Available Models. For endpoint-backed verification, see Run Live Provider Tests.
Schema Emitter
Section titled “Schema Emitter”Prompty’s runtime model types and schema reference are generated from the in-repository TypeSpec model. For details on how the generator works, see Schema Emitter.