We created the first open source implementation of Meta's TestGen–LLM

Codium AI developed Cover-Agent, the first open-source implementation of Meta's TestGen–LLM. It helps enhance code coverage by generating tests automatically, with features like additional instructions, test validation, and context-aware inputs for higher-quality tests. It aims to run as part of the CI/CD pipeline to suggest improvements post-pull requests.

• Cover-Agent is an open-source tool.
• TestGen-LLM improves code coverage.
• AI produces and validates tests.
• Meta's TestGen-LLM isn't released.
• Manual review improves test acceptance.