Evidently
Evaluate, test, and monitor LLMs, RAG applications, AI agents, and ML models in a single framework. Fully open-source under Apache 2.0.
Provider: Evidently AI
- built_in_metrics: 100+
- community_members: 3000+
- companies_using: 1000s
- downloads: 40m+
- github_stars: 7500+
- license: Apache 2.0
Buying
- Public pricing
- Unknown
- Enterprise offering
- Unknown
- Founded
- Unknown
Capabilities
- Automated evaluation of AI output quality, safety, and reliability
- Run evals as part of a pipeline with shareable visual reports
- Synthetic data generation for realistic, edge-case, and adversarial inputs
- Continuous monitoring with a live dashboard for drift, regressions, and emerging risks
- 100+ built-in metrics plus custom rules, classifiers, and LLM-based evaluations
- LLM evaluation for adherence, hallucinations/factuality, PII detection, retrieval quality, sentiment, toxicity, tone, and trigger words
- Evaluate LLM-powered systems including chatbots, RAG applications, AI agents, and copilots
- Evaluate predictive ML systems with metrics for predictive performance, data drift, and data quality
- Fully open-source under Apache 2.0
Categories
- LLM evaluation tools
- LLM observability