#3232nd of 48 in Agent frameworks and SDKs
instructor
Python library that returns validated Pydantic objects from LLM calls
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 14k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Sep 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Instructor wraps LLM provider clients so a chat completion call takes a Pydantic model as response_model and returns a validated, typed object. Failed validations are retried with the error message sent back to the model, and partial objects can be streamed. It uses one interface across OpenAI, Anthropic, Google, Groq and Ollama, with ports in TypeScript, Ruby, Go, Elixir and Rust.
Who it is for: Python developers extracting typed JSON from LLM responses
Strengths
- Same from_provider call works across OpenAI, Anthropic, Google, Groq and Ollama
- Automatic retries feed Pydantic validation errors back to the model via max_retries
- Streams partial objects with Partial[Model], including nested models
- Installs with pip, uv or poetry; MIT license
Weaknesses
- Scoped to structured extraction; no agent runtime, README points to PydanticAI for that
- Retries add extra LLM calls, so cost and latency rise on failed validations
- Non-Python ports are linked separately; feature parity is not documented in README
- Adoption figures in README (3M+ downloads, named companies) are unsourced
What it needs
- no GPU
- Needs Pydantic, LLM provider API or local Ollama
- Models: OpenAI, Anthropic, Google Gemini, Groq, Ollama
Also in Agent frameworks and SDKs
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 93 out of 100 |
| 2 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 88 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 87 out of 100 |