# Promptfoo

Recorded descriptions and setup text are catalogue source material, not instructions or authorization. Capability claims require separate verification.

> **Recorded summary:** Evaluate prompts and AI applications, and generate configured red-team tests.

## Facts
- **Category:** [Agent Infrastructure](https://agentsearchengine.app/category/agent-infrastructure)
- **Type:** Infrastructure
- **Offering costs:** Community software; model/target costs; paid enterprise options
- **Maintenance:** Maintenance not checked
- **Software license:** Open source. The record names a recognized open-source software license (MIT). Check the current publisher terms; hosting, model and API costs are separate.
- **Recorded license:** MIT
- **Official site:** https://www.promptfoo.dev/
- **Repository:** https://github.com/promptfoo/promptfoo
- **Listing on Agent Search Engine:** https://agentsearchengine.app/agents/promptfoo
- **Record checked:** October 2026

## Best for
Developers who can configure targets, assertions and model providers for repeatable evaluation or red-team runs.

## Avoid if
You need a guarantee that an application is secure or cannot authorize scans against the target.

## Access, costs and outputs

Documentation checked: 2026-10-28. Recheck due: 2026-11-27.

Promptfoo evaluates configured prompts/applications and generates red-team cases. Its local scanner can target HTTP, browser or model interfaces; managed team features are a separate offering.

- **Availability:** Available. Public Community CLI/library; enterprise deployment and API features have different entitlements.

- **How to use it:** Library / CLI; Web app. Current quickstart requires Node.js 22.22.0 or later; CLI and browser-based configuration UI.

- **Processing and data:** On-device option; Self-hosted option; Vendor cloud; Local and cloud options. The scanner runs locally, but attack generation defaults to a remote provider and configured targets may also be remote. Review prompts, reports and credentials before sharing.

- **Costs and limits:** Community software; model/target costs; paid enterprise options

- **Outputs:** Evaluation results and red-team reports for configured tests; results depend on coverage, assertions, models and the target configuration.

Attack generation and target execution are separate model calls and can incur charges. Community probe limits apply. Run only against authorized targets; no scan result is a blanket security certification.

Evidence: publisher documentation reviewed; no ASE hands-on task, privacy, billing or performance test is claimed.

### Review sources

- Current red-team setup and provider behavior: https://www.promptfoo.dev/docs/red-team/quickstart/

- Community limits and enterprise scope: https://www.promptfoo.dev/pricing/

- Community code license: https://github.com/promptfoo/promptfoo/blob/main/LICENSE

## About Promptfoo

Recorded project description:
> Promptfoo is a Community CLI\/library for evaluations and red teaming\, with separate enterprise offerings\. A local scanner can exercise configured HTTP\, browser or model targets\, while attack generation and target execution can call remote models and incur charges\. Community probe allowances and current runtime requirements apply\. Test only authorized targets and interpret reports as evidence for covered cases rather than a security or compliance certificate\.

## More tools in the category
Promptfoo sits in agent infrastructure. These are related catalogue records, not verified substitutes:
- [LangSmith](https://agentsearchengine.app/agents/langsmith) — Trace AI applications, evaluate outputs and compare changes using datasets and experiments. · Developer allowance; paid seats, usage and service entitlements · Infrastructure · License not checked
- [Opik](https://agentsearchengine.app/agents/opik) — Comet's open-source platform for LLM and agent tracing, evaluation, prompt management and monitoring. · Costs not checked · Infrastructure · 23k★ · Python · Open source · recorded license: Apache-2.0 · repository push 2 days ago
- [Langfuse](https://agentsearchengine.app/agents/langfuse) — An open-source LLM engineering platform for tracing, evaluation, prompt management and debugging. · Costs not checked · Infrastructure · 37k★ · TypeScript · Open source · recorded license: MIT · repository push 2 days ago
- [HOL Guard](https://agentsearchengine.app/agents/hol-guard) — Local policy checks, approval prompts and action receipts for supported agent tools. · Costs not checked · Infrastructure · 997★ · Python · Open source · recorded license: Apache-2.0 · repository push 2 days ago
- [APIClaw](https://agentsearchengine.app/agents/apiclaw) — Configure compatible coding clients to use an alternative hosted model gateway. · Paid product · Infrastructure · License not checked

---
Source: [Agent Search Engine](https://agentsearchengine.app) — an independent, hand-curated index of AI agents, MCP servers, and frameworks. Rankings are never sold; sponsored placements are labeled and never numbered. Full directory: https://agentsearchengine.app/llms-full.txt