Registry / llm-agents / poml
library0.0.8pypypi✓ verified 84d ago

POML (Prompt Orchestration Markup Language) is a Python library for defining, composing, and managing prompts in a structured markup language. It allows you to define reusable prompt components, variables, and orchestration logic. As of version 0.0.8, the library is in early alpha with basic functionality for parsing and rendering POML templates. Release cadence is irregular.

pip install poml
INSTALL
IMPORT
SIG · POML
P
poml
llm-agentspythonv0.0.8
harness data pending
Install & Compatibility
Where this runs

No compatibility data collected yet for this library.

Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

Prompt
✓ from poml import Prompt
✗ from poml import POML
Backend
✓ from poml import Backend
OutputFormat
✓ from poml import OutputFormat

Instantiate a POML object, define a template, and render with variables.

from poml import POML poml = POML() template = ''' [context] user_name = "{{user_name}}" [instructions] Greet the user warmly. ''' rendered = poml.render(template, {"user_name": "Alice"}) print(rendered)
Debug
Known issues
breakingPOML 0.0.8 changed the API: render() now returns a string instead of a dict. Previous 0.0.7 returned {'content': ...}.
fix
Update code from `result['content']` to `result` directly.
affects: 0.0.7 and earlier
deprecatedThe `poml.parse()` function is deprecated and will be removed in 0.1.0. Use `poml.load()` instead.
fix
Replace `poml.parse(template)` with `poml.load(template)`.
affects: 0.0.8
gotchaTemplates must be indented consistently. Mixing tabs and spaces causes parsing errors. Use spaces only.
fix
Configure your editor to replace tabs with spaces when editing .poml files.
affects: all
Upgrade
Version history
0.0.8latest on PyPI · released Aug 25, 2025
Audit
Dependencies

No dependency data recorded yet.

Agent activity
22 hits · last 30 days
node
18
OpenAI (training)
1
Resources
poml — pip install poml · libregistry