---
title: Our Commitment to Open Source
description: 'Discover our open-source ecosystem: data validation for Python, JSON parsing and our agent framework for LLMs. Get involved and contribute'
canonical: https://pydantic.dev/opensource
last-reviewed: '2026-07-15'
---

> Markdown version of [Open Source](https://pydantic.dev/opensource) — the canonical HTML page.
>
> Site index: [/llms.txt](https://pydantic.dev/llms.txt)

---

# /opensource

## Powering the Python community

Our open source packages are built for the Python and Rust community and MIT licensed — and will remain so, forever.

Find us on [Slack](https://pydantic.dev/docs/logfire/join-slack/), [GitHub](https://github.com/pydantic), [Twitter/X](https://twitter.com/pydantic), [Mastodon](https://fosstodon.org/@pydantic), [LinkedIn](https://linkedin.com/company/pydantic), [YouTube](https://www.youtube.com/@pydantic), and the [Open Source Pledge](https://opensourcepledge.com/members/pydantic/).

## pydantic

**The default data validation library for Python.**

Pydantic is the most widely used data validation library, downloaded millions of times a day by thousands of developers all over the world.

Pydantic's success stems from its great developer experience. It's simple to use, even when doing complex things.

```python
from datetime import datetime
from typing import Tuple

from pydantic import BaseModel

class Delivery(BaseModel):
    timestamp: datetime
    dimensions: Tuple[int, int]

m = Delivery(timestamp='2020-01-02T03:04:05Z', dimensions=['10', '20'])
print(repr(m.timestamp))
#> datetime.datetime(2020, 1, 2, 3, 4, 5, tzinfo=TzInfo(UTC))
print(m.dimensions)
#> (10, 20)
```

Docs: https://pydantic.dev/docs/validation/latest/get-started/

## Pydantic AI

**Agent Framework / shim to use Pydantic with LLMs.** https://github.com/pydantic/pydantic-ai

- Pydantic AI is a Python agent framework designed to make it less painful to build production grade applications with Generative AI.
- Model-agnostic: Pydantic AI supports OpenAI, Anthropic, Gemini, Deepseek, Ollama, Groq, Cohere, and Mistral.

```python
from pydantic_ai import Agent

agent = Agent(
    'openai:gpt-4o',
    system_prompt='Be concise, reply with one sentence.',
)

result = agent.run_sync('Where does `hello world` come from?')
print(result.data)
#> The first known use of "hello, world" was
#> in a 1974 textbook about the C language.
```

## speedate

**Fast and simple datetime, date, time and duration parsing for Rust.** https://github.com/pydantic/speedate

- Build with total flexibility. Speedate supports multiple formats.
- Enjoy peace of mind — all relaxations from RFC 3339 are compliant with ISO 8601.

## jiter

**The fast, iterable JSON parser with multiple interfaces.** https://github.com/pydantic/jiter

- Stable and battle tested, jiter is the most downloaded third party JSON parser for Python.
- Significantly faster than serde-json in most scenarios.
- Supports partial/incomplete JSON parsing, especially useful for LLM output.

## From the blog

- [A research agent, three ways](https://pydantic.dev/articles/harness-exa) — Bill Easton, 2026-07-21 ([markdown](https://pydantic.dev/articles/harness-exa.md))
- [You've built this agent before](https://pydantic.dev/articles/harness-week) — Douwe Maan, 2026-07-20 ([markdown](https://pydantic.dev/articles/harness-week.md))
- [Your traces already know how to fix your prompt](https://pydantic.dev/articles/logfire-prompt-optimization) — Bill Easton, 2026-07-17 ([markdown](https://pydantic.dev/articles/logfire-prompt-optimization.md))

## The Pydantic Open Source Fund

For too long the open source ecosystem has been taken for granted. We're proud to be part of the movement to change that. More about the [Pydantic Open Source Fund initiative](https://pydantic.dev/articles/pydantic-oss-fund-2025).

Pydantic is proud to be a member of the [Open Source Pledge](https://opensourcepledge.com/).

---

Explore all our open source packages: https://github.com/pydantic