Directory

SQL-first transformation framework that compiles templated models, tests and documentation into warehouse tables; open-source Core plus a commercial platform

Python web framework for building HTTP APIs from type-annotated functions, with automatic validation through Pydantic and generated OpenAPI documentation

Web data API that scrapes, crawls, maps and searches websites and returns clean Markdown or structured JSON for LLM pipelines, with an AGPL-licensed self-hostable core

Open-source LLM observability and evaluation platform: tracing, LLM-as-judge and human evals, prompt management, datasets and cost dashboards, self-hostable or as Langfuse Cloud

Low-level orchestration framework and runtime for stateful, long-running agents expressed as graphs, with durable execution, checkpointing, human-in-the-loop and streaming

Open-source Python SDK and self-hosted AI gateway that calls 100+ LLM providers in the OpenAI format, with routing, fallbacks, virtual keys, budgets, spend tracking and logging callbacks

Open JSON-RPC standard for connecting AI applications to tools, data and prompts through servers, now stewarded under the Linux Foundation with SDKs in many languages

Microsoft's browser automation and end-to-end testing framework driving Chromium, Firefox and WebKit from one API in TypeScript, Python, Java and .NET

Open-source computational notebook ecosystem: the .ipynb format, kernels for Python, R and Julia, JupyterLab and Notebook interfaces and JupyterHub

General-purpose, dynamically typed programming language with a large standard library and the dominant ecosystem for data science and machine learning

Open-source Python framework for distributing tasks, actors and ML workloads across a cluster, with libraries for data processing, training, tuning, serving and reinforcement learning

Mature open-source Python framework for writing crawlers (spiders) that fetch pages asynchronously, extract structured items and export them through pipelines

High-throughput LLM inference and serving engine with PagedAttention, continuous batching, quantization and an OpenAI-compatible server for GPU and accelerator clusters