arthur-ai/arthur-engine
Make AI work for Everyone - Monitoring and governing for your AI/ML
Provides real-time evaluation and guardrailing for LLM/GenAI applications through pluggable metrics (hallucination detection, prompt injection, PII leakage, toxicity) built on open-source models like HuggingFace and Presidio. Deploys via Docker Compose with a REST API and extensible architecture supporting custom models and metrics. Integrates with LangChain and LlamaIndex frameworks while offering enterprise variants with proprietary models for improved latency and accuracy.
Stars
69
Forks
9
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/arthur-ai/arthur-engine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aimclub/OSA
Tool that just makes your open source project better using LLM agents
auraguardhq/aura-guard
Exactly-once + circuit breaker for agent tool calls (loops, retries, duplicate side effects)
anthalehq/anthale-node
Anthale's official TypeScript SDK
GoPlausible/.github
Plausible is a proof of anything protocol for Algorand
typper-io/ai-code-sandbox
Secure Python sandbox for AI/ML code execution using Docker. Run LLM outputs safely.