vigil-llm vs promptfoo
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| vigil-llm | promptfoo | |
|---|---|---|
| Tagline | ⚡ Security scanner for LLM prompts ⚡ | Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. |
| Stars | 486 | 23k |
| Forks | 55 | 2.1k |
| Open issues | 16 | 402 |
| Language | Python | TypeScript |
| License | Apache-2.0 | MIT |
| Last pushed | Jan 31, 2024 | Jul 7, 2026 |
| Categories | Evaluation & Observability | Developer Tools, Evaluation & Observability |
vigil-llm
Vigil is a Python library and REST API designed to assess Large Language Model (LLM) inputs, detecting injections, jailbreaks, and other security threats. It includes modular scanners with the ability to extend via custom signatures and supports various detection methods including vector databases, heuristics, transformer models, canary tokens, and sentiment analysis.
Python
promptfoo
A CLI and library to evaluate and red-team LLM applications with simple declarative configurations, supporting GPT, Claude, Gemini, etc., with CI/CD integration. Used by OpenAI and Anthropic.
TypeScript