Prompty

⚠️ v2 Alpha — This is the v2 branch of Prompty, currently in alpha. The API, file format, and tooling are under active development and may change. Feedback welcome via Issues.

Prompty is a markdown file format (.prompty) for LLM prompts. Write your prompt once — run it from VS Code, Python, or TypeScript.

Quick Start

1. Write a .prompty file

---
name: greeting
model:
  id: gpt-4o-mini
  provider: openai
  connection:
    kind: key
    apiKey: ${env:OPENAI_API_KEY}
template:
  format:
    kind: jinja2
  parser:
    kind: prompty
---
system:
You are a friendly assistant.

user:
Say hello to {{name}}.

2. Run it

Python

pip install "prompty[jinja2,openai]"

import prompty

result = prompty.invoke("greeting.prompty", inputs={"name": "Jane"})
print(result)

TypeScript

npm install @prompty/core @prompty/openai

import { invoke } from "@prompty/core";
import "@prompty/openai";

const result = await invoke("greeting.prompty", { name: "Jane" });
console.log(result);

VS Code — open the .prompty file and press F5.

Use an OpenAI-compatible endpoint

Prompty's openai provider can also target OpenAI-compatible control planes, gateways, or self-hosted model servers by setting model.connection.endpoint. The prompt asset stays portable: switch the endpoint and key at runtime without changing the prompt body.

---
name: governed-greeting
model:
  id: gpt-4o-mini
  provider: openai
  connection:
    kind: key
    endpoint: ${env:OPENAI_BASE_URL:https://api.openai.com/v1}
    apiKey: ${env:OPENAI_API_KEY}
template:
  format:
    kind: jinja2
  parser:
    kind: prompty
---
system:
You are a careful assistant.

user:
Say hello to {{name}}.

For example, to route through Tuning Engines:

export OPENAI_BASE_URL=https://api.tuningengines.com/v1
export OPENAI_API_KEY=sk-te-your-inference-key

This keeps the .prompty file unchanged while the endpoint provides routing, policy, usage tracking, or trace correlation around OpenAI-compatible calls.

Contributor hygiene

Prompty normalizes text files to LF line endings via .gitattributes. Enable the repo hook once per clone so staged files are normalized before each commit and whitespace errors are blocked locally:

git config core.hooksPath .githooks

Before opening a PR, you can run the same core hygiene checks directly:

git diff --check
git ls-files --eol | grep 'w/crlf'

VS Code Extension

The v2 extension includes a connections sidebar, live preview, chat mode, and a redesigned trace viewer.

Create

Right-click in the explorer → New Prompty to scaffold a new prompt file.

Preview

See the rendered prompt with live markdown rendering and template interpolation as you type.

Connections

Manage model connections from the sidebar — add OpenAI, Microsoft Foundry, or Anthropic endpoints, set a default, and browse available models.

Chat Mode

Thread-enabled prompts automatically open an interactive chat panel with tool calling support.

Tracing

Every execution generates a .tracy trace file. Click to inspect the full pipeline — render, parse, execute, process — with timing and payloads.

Runtimes

Python

pip install "prompty[all]"              # everything
pip install "prompty[jinja2,openai]"    # just OpenAI
pip install "prompty[jinja2,foundry]"   # Microsoft Foundry
pip install "prompty[jinja2,anthropic]" # Anthropic

import prompty

# Full pipeline: load → render → parse → execute → process
result = prompty.invoke("my-prompt.prompty", inputs={...})

# Step-by-step
agent = prompty.load("my-prompt.prompty")
messages = prompty.prepare(agent, inputs={...})
result = prom