promptfoo and recursive-prompt-improver

These are complementary tools: promptfoo provides systematic evaluation and comparison across multiple LLM providers, while recursive-prompt-improver focuses on iterative optimization and management of individual prompts, making them useful together in a prompt engineering workflow.

promptfoo

Verified

recursive-prompt-improver

Experimental

Maintenance 22/25

Adoption 14/25

Maturity 25/25

Community 20/25

Maintenance 10/25

Adoption 4/25

Maturity 13/25

Community 0/25

Stars: 14,219

Forks: 1,297

Downloads: —

Commits (30d): 380

Language: TypeScript

License: MIT

Stars: 5

Forks: —

Downloads: —

Commits (30d): 0

Language: JavaScript

License: MIT

No risk flags

No Package No Dependents

About promptfoo

promptfoo/promptfoo

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.

This tool helps AI developers and engineers evaluate and secure their large language model (LLM) applications. You provide your prompts, models (like GPT, Claude, or Llama), and test cases, and it generates performance comparisons and vulnerability reports. This is ideal for anyone building or deploying AI systems and needing to ensure their reliability and safety.

LLM development AI security Prompt engineering Model evaluation AI red teaming

About recursive-prompt-improver

d-barletta/recursive-prompt-improver

RPI is a desktop/web application for testing, improving, and managing LLM prompts with multi-provider support

Related comparisons

promptfoo and promptfoo-action

Scores updated daily from GitHub, PyPI, and npm data. How scores work