{
  "markdown": "# Promptfoo: LLM evals & red teaming\n\n<p align=\"center\">\n  <a href=\"https://npmjs.com/package/promptfoo\"><img src=\"https://img.shields.io/npm/v/promptfoo\" alt=\"npm\"></a>\n  <a href=\"https://npmjs.com/package/promptfoo\"><img src=\"https://img.shields.io/npm/dm/promptfoo\" alt=\"npm\"></a>\n  <a href=\"https://github.com/promptfoo/promptfoo/actions/workflows/main.yml\"><img src=\"https://img.shields.io/github/actions/workflow/status/promptfoo/promptfoo/main.yml\" alt=\"GitHub Workflow Status\"></a>\n  <a href=\"https://github.com/promptfoo/promptfoo/blob/main/LICENSE\"><img src=\"https://img.shields.io/github/license/promptfoo/promptfoo\" alt=\"MIT license\"></a>\n  <a href=\"https://discord.gg/promptfoo\"><img src=\"https://img.shields.io/discord/1146610656779440188?logo=discord&label=promptfoo\" alt=\"Discord\"></a>\n</p>\n\n<p align=\"center\">\n  <code>promptfoo</code> is a CLI and library for evaluating and red-teaming LLM apps. Stop the trial-and-error approach - start shipping secure, reliable AI apps.\n</p>\n\n<p align=\"center\">\n  <a href=\"https://www.promptfoo.dev\">Website</a> ·\n  <a href=\"https://www.promptfoo.dev/docs/getting-started/\">Getting Started</a> ·\n  <a href=\"https://www.promptfoo.dev/docs/red-team/\">Red Teaming</a> ·\n  <a href=\"https://www.promptfoo.dev/docs/\">Documentation</a> ·\n  <a href=\"https://discord.gg/promptfoo\">Discord</a>\n</p>\n\n> Promptfoo is now part of OpenAI. Promptfoo remains open source and MIT licensed. Read the [company update](https://www.promptfoo.dev/blog/promptfoo-joining-openai/).\n\n## Quick Start\n\nRequires [Node.js](https://nodejs.org/en/download) `>=22.22.0` for npm and npx usage. Node.js 24 LTS\nis recommended; see the [runtime support guide](https://www.promptfoo.dev/docs/installation/#nodejs-runtime-support).\n\n```sh\nnpm install -g promptfoo\npromptfoo init --example getting-started\n```\n\nAlso available via `brew install promptfoo` and `pip install promptfoo`. You can also use `npx promptfoo@latest` to run any command without installing.\n\nMost LLM providers require an API key. Set yours as an environment variable:\n\n```sh\nexport OPENAI_API_KEY=sk-abc123\n```\n\nOnce you're in the example directory, run an eval and view results:\n\n```sh\ncd getting-started\npromptfoo eval\npromptfoo view\n```\n\nSee [Getting Started](https://www.promptfoo.dev/docs/getting-started/) (evals) or [Red Teaming](https://www.promptfoo.dev/docs/red-team/) (vulnerability scanning) for more.\n\n## What can you do with Promptfoo?\n\n- **Test your prompts and models** with [automated evaluations](https://www.promptfoo.dev/docs/getting-started/)\n- **Secure your LLM apps** with [red teaming](https://www.promptfoo.dev/docs/red-team/) and vulnerability scanning\n- **Compare models** side-by-side (OpenAI, Anthropic, Azure, Bedrock, Ollama, and [more](https://www.promptfoo.dev/docs/providers/))\n- **Automate checks** in [CI/CD](https://www.promptfoo.dev/docs/integrations/ci-cd/)\n- **Review pull requests** for LLM-related security and compliance issues with [code scanning](https://www.promptfoo.dev/docs/code-scanning/)\n- **Share results** with your team\n\nHere's what it looks like in action:\n\n<img src=\"site/static/img/claude-vs-gpt-example@2x.png\" alt=\"prompt evaluation matrix - web viewer\" width=\"700\">\n\nIt works on the command line too:\n\n<img src=\"https://www.promptfoo.dev/img/docs/self-grading.gif\" alt=\"promptfoo command line\" width=\"700\">\n\nIt also can generate [security vulnerability reports](https://www.promptfoo.dev/docs/red-team/):\n\n<img src=\"https://www.promptfoo.dev/img/redteam-dashboard@2x.jpg\" alt=\"gen ai red team\" width=\"700\">\n\n## Why Promptfoo?\n\n- **Developer-first**: Fast, with features like live reload and caching\n- **Private**: LLM evals run 100% locally - your prompts never leave your machine\n- **Flexible**: Works with any LLM API or programming language\n- **Battle-tested**: Powers LLM apps serving 10M+ users in production\n- **Data-driven**: Make decisions based on metrics, not gut feel\n- **Open source**: MIT licensed, with an active community\n\n## Learn More\n\n- [Getting Started](https://www.promptfoo.dev/docs/getting-started/)\n- [Full Documentation](https://www.promptfoo.dev/docs/intro/)\n- [Red Teaming Guide](https://www.promptfoo.dev/docs/red-team/)\n- [CLI Usage](https://www.promptfoo.dev/docs/usage/command-line/)\n- [Node.js Package](https://www.promptfoo.dev/docs/usage/node-package/)\n- [Supported Models](https://www.promptfoo.dev/docs/providers/)\n- [Code Scanning Guide](https://www.promptfoo.dev/docs/code-scanning/)\n\n## Contributing\n\nWe welcome contributions! Check out our [contributing guide](https://www.promptfoo.dev/docs/contributing/) to get started.\n\nJoin our [Discord community](https://discord.gg/promptfoo) for help and discussion.\n\n<a href=\"https://github.com/promptfoo/promptfoo/graphs/contributors\">\n  <img src=\"https://contrib.rocks/image?repo=promptfoo/promptfoo\" />\n</a>\n",
  "bytes": 4840,
  "sha": "426270e1b7c45d0bf456b1284cdc1af055218db73869864b9590b1e0bdaab5cb",
  "repo_slug": "promptfoo/promptfoo",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_promptfoo_promptfoo_promptfoo_evals_7b7c0144/readme"
}