A simple package to validate functions from your project
TypeScript CLI + SDK for planned Claude Code harness runs, LLM bundle judging, and summary.md + results.jsonl reports with Braintrust + Promptfoo telemetry.
TypeScript SDK for capturing failed LLM interactions with PromptCrash.
Safeguard your AI agents - keep them grounded and on the rails
A StatsD backend for Instrumental
A utility to wrap async functions with try-catch
Generates test case outlines from function signatures with edge cases and recommendations
Evaluation harness for testing and benchmarking Verydia agent flows