vigil-llm vs graphrag
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| vigil-llm | graphrag | |
|---|---|---|
| Tagline | ⚡ Vigil ⚡ Security scanner for detecting prompt injections, jailbreaks, and risky Large Language Model inputs | Graph-based Retrieval-Augmented Generation (RAG) system |
| Stars | 486 | 34k |
| Forks | 55 | 3.6k |
| Open issues | 16 | 158 |
| Language | Python | Python |
| License | Apache-2.0 | MIT |
| Last pushed | Jan 31, 2024 | Jun 22, 2026 |
| Categories | Evaluation & Observability, Model Training | Data & Retrieval, LLM Frameworks |
vigil-llm
Vigil is a Python library and REST API designed to evaluate prompts and responses from large language models (LLM) against various scanners to identify potential threats such as prompt injection and jailbreaking. The toolkit includes modular detection methods including vector similarity checks, YARA rules, transformer-based analyses, heuristic scanning, and more.
Python
graphrag
A modular graph-based RAG system designed to extract structured data from unstructured text using Large Language Models.
Python