promptfoo/promptfoo

A-Tier scored 2026-07-07 metrics 2026-07-07

Test harness for prompts, agents, and RAG pipelines: declarative test cases, assertions, matrix comparisons, and red-team scanning, runnable in CI. Agentiquette scores it 83/100 (A-tier), methodology v1.0, scored 2026-07-07.

83/100 A-Tier
scored 2026-07-07 · methodology v1.0 · how we score
Reliability7825%
Skill Leverage8220%
Documentation8415%
Maintenance9210%
Safety / Governance7610%
Evaluation Readiness9210%
Composability825%
Adoption (capped)845%

Key facts

CategoryEvaluation / observability
LicenseMIT
MaintainerPromptfoo Inc
Compatible agentsgeneric
File patterns
Triggeringmanual-reference
GitHub metrics22,994 stars · 2,054 forks · 401 open issues (fetched 2026-07-07)
Last commit2026-07-07
Created2023-04-28

Editorial analysis

The closest thing the ecosystem has to a standard test runner for the evaluation layer, and the tool this site's own benchmark protocols reference. Declarative YAML cases make evals diffable and reviewable, which is the property that separates evaluation from vibes. The red-team scanner doubles it as governance tooling.

Risks

LLM-graded assertions inherit grader bias; pin grader models and audit rubrics like code.

Evidence notes: Eval readiness: the product is eval readiness; assertions are checkable by construction. Docs: init-to-first-eval ran as written. Safety: red-team mode scans for injection and leakage classes.

Install and first run

install · verified by running it
npx promptfoo@latest init

Alternatives in this category

Compare with deepeval · Compare with langfuse

Embed this badge

Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.

Agentiquette: A tier, 83/100

README.md
[![Agentiquette](https://agentiquette.com/badge/promptfoo.svg)](https://agentiquette.com/index/repos/promptfoo)

Frequently asked questions

Is promptfoo/promptfoo good?

promptfoo/promptfoo scores 83/100 (A-tier) on Agentiquette's methodology v1.0, scored 2026-07-07. Strengths and weaknesses are in the editorial analysis; the score is explained dimension by dimension in the scorecard.

What is promptfoo/promptfoo for?

Test harness for prompts, agents, and RAG pipelines: declarative test cases, assertions, matrix comparisons, and red-team scanning, runnable in CI.

Is promptfoo/promptfoo maintained?

Last commit 2026-07-07, 401 open issues at fetch time (2026-07-07). Maintenance is scored at 92 of 100.

Maintainer of promptfoo/promptfoo? Claim this listing and suggest corrections.