Promptfoo
AIOpen SourceFreeCLI and web tool for testing, evaluating, red‑teaming, and monitoring LLM prompts and outputs to catch regressions and vulnerabilities.
-(0 Reviews)
Free Available
Starting from Free
Promptfoo
AIOpen SourceFree
CLI and web tool for testing, evaluating, red‑teaming, and monitoring LLM prompts and outputs to catch regressions and vulnerabilities.
-(0 Reviews)
Free Available
Starting from Free
About Promptfoo
Promptfoo is an open-source toolset for testing, evaluating, and red‑teaming large language model (LLM) prompts and apps. It provides a declarative config system, CLI and web UI, and integrations for CI/CD so teams can run evals, compare outputs across models/providers, detect regressions, and find security or alignment vulnerabilities. Promptfoo supports templating and filters for prompt generation, multiple provider plugins, Docker distribution, and GitHub Actions to automate before/after evaluations on PRs, enabling test‑driven LLM development and safer deployments.
Screenshots
+
+
+
+
Key Features
Red-Teaming & Vulnerability Scanning: Declarative red‑team tests and automated scans to surface prompt injections, unsafe completions, and other model security risks across providers.
Evaluations & Regression Detection: Run reproducible eval suites and compare outputs before/after changes to detect regressions, with CI/CD and GitHub Action integration for automated checks on PRs.
Multi-Provider Model Comparison: Execute the same tests across multiple model providers and families (e.g., OpenAI, Claude, Gemini, Llama) to compare quality and safety consistently.
CLI and Web UI: Command‑line tools for running tests and a web 'view' UI to inspect prompts, final rendered prompts, outputs, and structured results in tabular form.
Declarative Configs & Templating: Use promptfooconfig.yaml with Nunjucks templating and custom filter plugins to generate complex prompts and test permutations programmatically.
Extensible Provider & Plugin System: Add or customize providers, local execution, or custom filters (JS/Python) to adapt tests to specific stacks or private model endpoints.
Docker Distribution & Local Execution: Official container images and local execution modes enable isolated, reproducible runs and CI friendliness.
GitHub & CI Integrations: Official GitHub Action and CI-friendly tooling to automatically post evaluations on PRs and enforce prompt quality gates.
Command‑line interface and library for running declarative evals and tests
Red‑teaming and vulnerability scanning for LLM outputs
Declarative configuration via promptfooconfig.yaml (prompts, providers, filters, tests)
Support for templated prompts using Nunjucks and custom filter modules
Providers for multiple model backends (OpenAI and others; compare GPT, Claude, Gemini, Llama, etc.)
Docker images published to GHCR (multi‑arch support: linux/amd64, linux/arm64, etc.)
Web UI (src/app) that integrates with `promptfoo view` for inspecting outputs and final prompts
CI/CD integrations including an official GitHub Action for evals on PRs
Developer productivity features: live reload, caching, npm scripts for local dev
Configurable Python executable (PROMPTFOO_PYTHON) and language‑agnostic test data (supports Python, JavaScript, others)
Use Cases
Red‑teaming LLM integrations to find prompt injections, unsafe outputs, and info‑leakage before release.
Regression testing in CI to automatically detect when a prompt or model update degrades output quality or safety on pull requests.
Comparing model performance across providers and model families to choose the best model for a given task or guardrail requirements.
Building test-driven prompt development workflows where prompts are versioned, evaluated, and iterated using reproducible eval suites.
Adding automated before/after eval diffs on GitHub PRs to give reviewers quantitative and qualitative signal about prompt edits.
Validating agents, RAG pipelines, and LLM apps end‑to‑end by running scenario-based tests and inspecting final rendered prompts and outputs.
Test‑driven prompt engineering and automated evaluation of model outputs
Red‑teaming and security testing of language model behavior
Regression testing of prompts and model changes via CI/CD and GitHub Actions
Comparing performance across multiple model providers
RAG (retrieval augmented generation) and agent testing in local/dev environments
Integrating automated evals into PR workflows to produce before/after views of prompt edits
