Testing

Braintrust

LLM evaluation and prompt management for production

DeepEval

Open-source pytest-style evaluation framework for LLMs and agents

Promptfoo

Open-source evaluation and red-teaming for LLM apps, agents and RAG.

Qodo

Agentic AI for code review, testing and coverage across the dev lifecycle

Thunders

AI agents that write, run and maintain test suites in plain language