5 open-source agents tracked · Ranked by trust score · Updated 2026-06-04 18:04 UTC
HVTracker independently evaluates 5 open-source security & guardrails using daily signals from GitHub, package registries, and security databases. Each agent is scored on activity, adoption, transparency, safety, and identity. The top-ranked security & guardrails is NeMo Guardrails with a trust score of 72.0/100 (Grade B). Other leading projects include Garak and Guardrails AI.
| # | Agent | Trust | Stars | Language |
|---|---|---|---|---|
| 1 | NeMo Guardrails B Listed NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. | 72.0 | 6.4k | Python |
| 2 | Garak B Listed the LLM vulnerability scanner | 68.7 | 8.0k | Python |
| 3 | Guardrails AI C Listed Adding guardrails to large language models. | 62.9 | 7.0k | Python |
| 4 | Llama Guard C Listed Set of tools to assess and improve LLM security. | 54.0 | 4.2k | Python |
| 5 | LLM Guard C Listed The Security Toolkit for LLM Interactions | 50.3 | 3.0k | Python |