Instructor
Python library to get structured outputs from language models with validation and parsing.
3. Used by agents' projects
Dependency in 4 public GitHub projects set up for AI coding agents that we scanned (0.1%).
4. Agent access
Agent skills for this library in the skills catalog; community skills are written by others, read them before you install.
From the package registry and GitHub, checked daily. Tap a verdict to see its source.How we checkedReport an error
What Instructor does
Python library to get structured outputs from language models with validation and parsing.
Instructor popularity
Gid Score measures public popularity and activity, not quality. How the Gid Score is calculated
How Instructor is used
- Instructor is a dependency in 4 of the 6,254 public GitHub projects set up for AI coding agents that we scanned, too few to describe it from them alone. Our scan also samples projects by dependency (Solana 3,063, Ethereum and EVM 1,777, 3D and games 3,120, agent frameworks and SDKs 13,629); counting those, it appears in 172 projects, and what it is used with below comes from all of them.
- The most used alternative in our scan is DSPy (6 projects).
- Projects that use it most often also use Pydantic (90.7%), OpenAI Python Library (90.1%), NumPy (87.8%).
Often used with
More about Instructor
Funding
- GitHub Sponsors: https://github.com/jxnl
- 3 GitHub sponsors
Agent Skills for it
- instructor: Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type sa
More in Prompts, structured output and evals
Alternatives
Instructor This page
Framework for optimizing LLM prompts and pipelines systematically.
Get started
Install it.
pip install instructorNo step-by-step start for Instructor yet: we have not written its hand-checked card.