prompty
Prompty is a new asset class and format for LLM prompts that aims to provide observability, understandability, and portability for developers. It includes spec, tooling, and a runtime. This Prompty runtime supports Python
Decision gist · record as of 2026-08-14
Yes, with conditions. Install if you need a structured, version-controlled way to manage and execute LLM prompts across multiple endpoints (Azure, OpenAI, serverless) with built-in tracing and CLI support. The low install friction and active maintenance are favorable. However, verify the status of the two known vulnerabilities (GHSA-wxhm-2mq7-7697, PYSEC-2026-3538) before deploying to production, and confirm whether optional invoker dependencies require explicit extras installation.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >= 3.9.
- To use Azure OpenAI invoker, install with: pip install "prompty[azure]".
- Prompty files must reference a valid LLM endpoint via environment variables or configuration.
License · maintenance · safety
MIT (permissive) — MIT license permits unrestricted use, modification, and distribution with minimal restrictions, making it suitable for commercial and open-source projects alike.
last release 2025-04-02 (499 days) · last repo commit 2026-08-12 · 1,248 stars
2 known vulnerabilities (OSV.dev, 2026-08-14) · 508,343 downloads/mo, #6,279 on PyPI
Alternatives
Verify before relying
pip install prompty
import prompty
import prompty.azure
response = prompty.execute("path/to/prompt.prompty")
print(response)- Whether the two known vulnerabilities (GHSA-wxhm-2mq7-7697, PYSEC-2026-3538) affect the current version or have been patched.
- Whether optional dependencies (e.g., for Azure or OpenAI invokers) are automatically installed or require explicit extras installation.
- Performance characteristics and latency overhead of the tracing mechanism in production workloads.
What it is and what it does
Prompty is a Python runtime that executes LLM prompts stored in a standardized `.prompty` file format. The format combines YAML metadata (model configuration, sample inputs, authors) with prompt templates written in Jinja2, allowing you to define and version control prompts separately from application code. The runtime loads these files, interpolates variables, and routes execution to the appropriate LLM API (Azure OpenAI, OpenAI, or serverless models via Azure AI Inference).
The package is designed to accelerate prompt engineering workflows by providing observability through a pluggable tracing system—built-in tracers write execution details to console or JSON files, and you can integrate OpenTelemetry or custom hooks. It includes a CLI tool for running prompts directly from the command line and a VS Code extension for interactive prompt development. Dependencies are minimal: pyyaml for config parsing, jinja2 for templating, python-dotenv for environment variables, click for CLI, and aiofiles for async file operations.
Use it for
- Run and iterate on LLM prompts defined in `.prompty` files without embedding them in Python code, enabling non-developers to edit prompts via VS Code.
- Trace and debug LLM API calls and prompt execution with built-in console or JSON output, or integrate with OpenTelemetry for centralized observability.
- Execute prompts from the command line with environment variable injection, useful for CI/CD pipelines or batch prompt testing.
- Switch between Azure OpenAI, OpenAI, and serverless model endpoints by changing configuration in the `.prompty` file without code changes.
- Build reusable prompt libraries with version control, sample inputs, and metadata for team collaboration on prompt engineering.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, with conditions.
Install if you need a structured, version-controlled way to manage and execute LLM prompts across multiple endpoints (Azure, OpenAI, serverless) with built-in tracing and CLI support. The low install friction and active maintenance are favorable. However, verify the status of the two known vulnerabilities (GHSA-wxhm-2mq7-7697, PYSEC-2026-3538) before deploying to production, and confirm whether optional invoker dependencies require explicit extras installation.
Install
prompty on PyPI
Before you install
Low install friction with a pure-Python wheel and five lightweight runtime dependencies. The package is actively maintained with recent commits and a steady release cadence since July 2024.
Requires Python >= 3.9. To use Azure OpenAI invoker, install with: pip install "prompty[azure]". Prompty files must reference a valid LLM endpoint via environment variables or configuration.
License in practice
MIT license permits unrestricted use, modification, and distribution with minimal restrictions, making it suitable for commercial and open-source projects alike.
Quickstart
pip install prompty
import prompty
import prompty.azure
response = prompty.execute("path/to/prompt.prompty")
print(response)Verify before relying
- Whether the two known vulnerabilities (GHSA-wxhm-2mq7-7697, PYSEC-2026-3538) affect the current version or have been patched.
- Whether optional dependencies (e.g., for Azure or OpenAI invokers) are automatically installed or require explicit extras installation.
- Performance characteristics and latency overhead of the tracing mechanism in production workloads.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packagespyyamljinja2python-dotenvclickaiofiles |
| Maintenance | Actively maintained 499 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 508,343 / month, #6,279 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | 2 GHSA-wxhm-2mq7-7697, PYSEC-2026-3538 |
Evidence: prompty-0.1.50-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “llm prompt execution framework”
- promptyPrompty is a Python runtime for executing LLM prompts defined in a…
- arize-phoenixPhoenix is an open-source AI observability platform that traces LLM…
- promptflowPrompt flow is a development suite for building, testing, and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also promptflow · prompthub-py · promptlayer · pdd-cli · ell-ai · banks · promptflow-tracing · llm · promptflow-devkit · opentelemetry-instrumentation-openai