Benchlight
Code
Open-source test runner for prompts that compares models on your own examples
Review, testing, SQL, legacy code, infrastructure and prompt evaluation tools that fit an existing workflow.
Code
Open-source test runner for prompts that compares models on your own examples
Code
Generates Terraform from an architecture diagram and checks it against your policies
Code
Groups production errors and points to the commit that most likely caused them
Code
Writes unit tests for the code paths your coverage report says nobody tests
Code
Ask questions in plain English and get readable SQL against your own warehouse
Code
Reviews pull requests for risky changes and explains why, in a single comment
Know a tool that belongs in Code?
Submit a tool