Our take
Quietno commits in the last 90 days and no release in a year- Activity
- 19
- Community
- 33
- Issues
- 21
- Pull requests
- 20
-8 stars in the last 30 days
POML offers a coherent markup-and-tooling approach to prompt development, but its quiet recent activity and concentrated contribution history make project continuity worth checking before adopting it as a dependency.
Good fit if
- You want prompts structured as reusable markup rather than maintained as large strings.
- Your workflow uses Node.js or Python, or benefits from the POML VS Code extension.
- You are comfortable with the MIT license and can evaluate the project’s maintenance status for your own needs.
Look elsewhere if
- You need evidence of active recent development or regular releases before depending on a tool.
- Your team wants a prompt workflow without introducing POML syntax and its Node.js or Python tooling.
- You need a project with broader recent contributor participation; most recorded contributions come from one person.
All health signals
| Last commit | 2026-01-14 (10 months ago) |
|---|---|
| Commits, last 90 days | 0 |
| Releases, last 12 months | 0 (latest v0.0.8, 2025-08-25, pre-release) |
| Contributors | 11 (top contributor: 87% of commits) |
| Issues closed, last 90 days | 0 |
| Pull requests merged, last 90 days | 0 |
| Project age | 23 months |
Checked on 2026-10-31 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
4,958Forks
253Change since Nov 17, 2026: 0 stars·0 forks
Overview
POML (Prompt Orchestration Markup Language) is Microsoft’s markup language for structuring prompts for large language models. It aims to make prompts easier to maintain and reuse, while helping developers integrate data and manage formatting without mixing presentation choices into prompt logic.
POML uses semantic elements for prompt content and data, plus templating and styling features. Its tooling includes a Visual Studio Code extension and SDKs for Node.js and Python, so it can fit both editor-based prompt development and application workflows.
Key Features
- Organizes prompts with semantic elements such as
<role>,<task>, and<example>. - Adds data components for sources such as documents, tables, and images.
- Separates presentation styling from prompt content through stylesheet definitions and inline attributes.
- Supports variables, loops, conditionals, and variable definitions for data-driven prompt generation.
- Provides a VS Code extension with syntax highlighting, completion, hover documentation, previews, diagnostics, and interactive testing.
- Offers SDKs for Node.js and Python to render POML in application workflows.
Use Cases
- Prompt engineers can use semantic structure and reusable templates to maintain prompts that have grown beyond a single text block.
- Application developers can generate prompts from changing input data with variables, loops, and conditionals.
- Teams working with documents, tables, or images can organize those inputs alongside prompt instructions.
- VS Code users can edit, preview, and diagnose POML prompts in their development environment.
- Teams experimenting with output formats can adjust styling separately from the underlying prompt content.
What you need
Detected in the repository
- Node.js (from package.json)
- Python >=3.9 (from pyproject.toml)
- Automated checks on GitHub Actions
License in plain words
MITpermissive
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the copyright and license notice
- Share your changes: no
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
Install the SDK for your runtime:
npm install pomljs
Or, for Python:
pip install poml
See the README and documentation for syntax, setup, and VS Code extension details.
Alternatives
- genaiscript: GenAIScript builds prompts in JavaScript or TypeScript and orchestrates models, tools, and data, while POML provides a markup language for structured prompts.
- py-priompt: PyPriompt composes reusable prompt components and prioritizes them to fit token limits, while POML organizes prompts with markup, templates, and styling.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| poml | TypeScript | MIT | 5k | Quiet |
| genaiscript | TypeScript | MIT | 2.9k | Archived |
| py-priompt | Python | Other | 65 | Inactive |
Considerations
- The project is marked quiet: it has had no commits in the last 90 days and no release in over a year. No issues were closed in that period, and no pull requests were merged, so confirm that the current packages and extension meet your needs before relying on ongoing fixes.
- Contribution activity is concentrated, with most of the code coming from one person. This may matter to teams assessing long-term maintenance.
- The README says prompt testing in the VS Code extension requires a configured model provider, API key, and endpoint. POML does not itself supply those services.
- The project is MIT-licensed. Contributions are subject to Microsoft’s CLA process, as described in the README.
Found this useful?
Share it with someone who would like poml.