An AI prompt optimizer for writing better prompts and getting better AI results.
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
LLM Reasoning and Generation Benchmark. Evaluate LLMs in complex scenarios systematically.
Prompture is an API-first library for requesting structured JSON output from LLMs (or any structure), validating it against a schema, and running comparative tests between models.
Test, compare, and optimize your AI prompts in minutes
The prompt engineering, prompt management, and prompt evaluation tool for TypeScript, JavaScript, and NodeJS.
Community Plugin for Genkit to use Promptfoo
prompt-evaluator is an open-source toolkit for evaluating, testing, and comparing LLM prompts. It provides a GUI-driven workflow for running prompt tests, tracking token usage, visualizing results, and ensuring reliability across models like OpenAI, Claude, and Gemini.
LLM Prompt Test helps you test Large Language Models (LLMs) prompts to ensure they consistently meet your expectations.
Test Claude Projects without copy-pasting. Local workbench for prompt engineering, agent testing, and workflow iteration. Direct Claude.ai access via cookie auth, 20+ prompt templates, web fetch/search tools, file uploads. Stop switching tabs to test your prompts.
curl for prompts. Run .prompt files against any LLM (Anthropic, OpenAI, Ollama) from the terminal. Treat prompts as code — version them, review them in PRs, and test them in CI.
An open-source testing framework for AI agents. Simulate LLM and tool calls to test edge cases, failure paths, and agent logic without live API calls.
Open-source prompt optimization tool — improve your LLM prompts with AI-powered suggestions and explanations.
An open-source AI prompt engineering playground with live code execution. Test OpenAI & Claude prompts, execute JavaScript, and iterate in real-time.
AI agent that helps you create, test, and iterate on LLM prompts. Saves versioned artifacts, generates test samples, runs evaluations, and provides detailed performance analysis.
OWASP LLM Top 10 vulnerability scanner CLI — test your AI endpoints for prompt injection, jailbreaks, data leakage & more. Fast red-teaming tool with pass/fail reports + fix recommendations. 🛡️
Sample project demonstrates how to use Promptfoo, a test framework for evaluating the output of generative AI models
Visual prompt engineering platform for creating, testing, and versioning LLM prompts across multiple providers (OpenAI, Anthropic, Mistral, Gemini).
DevTools for AI Coding — context engineering toolkit for Claude, Cursor, Copilot, and more
Add a description, image, and links to the prompt-testing topic page so that developers can more easily learn about it.
To associate your repository with the prompt-testing topic, visit your repo's landing page and select "manage topics."