Weights & Biases' toolkit for tracing, evaluating and monitoring LLM applications. Un produit fermé de Weights & Biases.
| Outil | Remplacement | Étoiles | Licence | Conditions | Auto-hébergeable | Langage | Dernière release | Dernier push |
|---|---|---|---|---|---|---|---|---|
| Langfuse | Remplacement complet | 35k | Other | Open core | Oui | TypeScript | v4.53.0 | 2026-10-06 |
| Opik | Remplacement complet | 22k | Apache-2.0 | Open source | Oui | Python | 2.2.92 | 2026-10-06 |
| Arize Phoenix | Remplacement complet | 12k | Other | Source disponible | Oui | Python | arize-phoenix-v20.19.0 | 2026-10-06 |
3 alternatives
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
Tracing and evaluations of LLM calls, with SDKs for Python and JavaScript.
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Tracing and evaluations of LLM calls, with production monitoring dashboards.
AI Observability & Evaluation
Tracing and evaluations of LLM calls, built on OpenInference instrumentation.