Rhesis AI
Open-source testing platform for LLM and agentic applications. Test generation, adversarial probing, and regression tracking.
Rhesis AI is an open-source (MIT) testing platform for LLM and AI agent applications. It goes beyond scoring to provide a full testing workflow: define requirements, generate test scenarios (including edge cases), execute them, review results, and track fixes. Engineers work in the SDK, non-technical team members work in the UI.
The platform generates test scenarios from requirements and can connect to knowledge sources via MCP (Notion, GitHub, Jira). Its red-teaming agent, Polyphemus, continuously probes for jailbreaks, prompt injection, and PII extraction. Every failed test links to its root cause across multi-step and multi-agent flows.
Covers conversational AI, RAG, NL-to-SQL, and agentic systems across any LLM provider.
Pricing: Free
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.
Rhesis AI Alternatives
Explore 58 products in the Observability & Analytics category. View all Rhesis AI 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
Future AGI
Open-source platform for testing, monitoring, and improving AI agents with tracing, evals, guardrails, and gateway
Vercel AI Gateway
Unified API for hundreds of AI models, with built-in rate limiting and key management
TruLens
Systematically evaluate and track LLM apps and agents with feedback functions and tracing
Guardrails AI
Open-source framework for adding input and output validators around LLM calls
Work on Rhesis AI? Feature it at the top of Observability & Analytics.
Is your product missing?