Enoki
Automated red-teaming for AI agents: attacks your agent's endpoint, reports exploits and re-tests fixes on each release
Enoki tests AI agents for security and safety vulnerabilities by attacking them. You give it the agent's endpoint, with no SDK or code access; it learns what the agent can do, generates attacks specific to it, such as indirect prompt injection, multi-turn jailbreaks and data or system prompt leakage, and reports each break with the exact attack, response and severity mapped to OWASP and MITRE ATLAS. Fixed issues are re-tested automatically on each release. Assessments can also run through an API and an MCP server.
One agent can be assessed for free; paid plans are priced on request. Operated by EthicGate BV in Ghent, Belgium.
Choosing an LLM evaluation tool right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing an LLM evaluation tool right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Enoki Alternatives
Explore 64 products in the Observability & Analytics category. View all Enoki alternatives.
DeepEval
Open-source LLM evaluation framework with 50+ metrics for testing agents, RAG, and chatbots
Evidently AI
Open-source ML and LLM evaluation with 100+ built-in metrics and CI/CD integration
Lunary
The platform to monitor, manage and improve your LLM apps.
Langfuse
Traces, evals, prompt management and metrics to debug and improve your LLM application.
Work on Enoki? Feature it at the top of Observability & Analytics.
Is your product missing?