guidance

Python library for steering language models by constraining output with regex and grammars and mixing control flow with generation.

Harness by guidance-ai

IndexedMIT★ 21,808

Write a review

Install

From the package registry. Read the repository before you give any tool access to your data.

pip install guidance

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Guidance is a Python programming paradigm for controlling how language models produce output. Users interleave conditionals, loops and tool use with generation, and constrain output with regular expressions, select lists or context-free grammars. It supports backends such as Transformers, llama.cpp and OpenAI, and includes a Mock model for testing grammars offline. It installs with pip.

Use cases: prompt-engineering, model-inference

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Languages: PythonREADME
Packages: guidance (pypi)README
Model providers: openai, huggingface, llama.cppREADME
Maturity: Betagithub.com

Facts extracted by Claude Sonnet 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Alternatives

Frameworks for the same language with a similar way of orchestrating agents.

Signals

Stars: 21,808
Forks: 1,219
Open issues: 267
Weekly downloads: 3,166
Last commit: May 21, 2026 (5 months ago)
Last release: Mar 18, 2026 (7 months ago)
Last package publish: Feb 3, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Packages: pypi guidance
License: MIT
Repository: github.com/guidance-ai/guidance
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql