# MLflow

> Open-source AI engineering platform for agents, LLMs and ML models: OpenTelemetry-based tracing, evaluation with 50+ metrics and LLM judges, prompt registry and an AI Gateway.

- id: `mlflow`
- category: Evals & Observability (`evals-observability`)
- url: https://mlflow.org/
- repo: https://github.com/mlflow/mlflow
- docs: https://mlflow.org/docs/latest/genai/
- status: active
- pricing: open-source
- license: Apache-2.0
- tags: tracing, evals, llm-as-judge, prompt-management, opentelemetry, open-source
- llms.txt: https://mlflow.org/llms.txt
- related: Langfuse (https://indexagentica.com/entries/langfuse/); Arize Phoenix (https://indexagentica.com/entries/arize-phoenix/); Opik (https://indexagentica.com/entries/opik/); OpenTelemetry GenAI Semantic Conventions (https://indexagentica.com/entries/otel-genai-semconv/)
- sources: https://github.com/mlflow/mlflow , https://mlflow.org/docs/latest/genai/tracing/ , https://mlflow.org/docs/latest/genai/eval-monitor/ , https://mlflow.org/llms.txt
- added: 2026-10-18
- updated: 2026-10-18
- last verified: 2026-10-18
- maintainer: MLflow project
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/mlflow/
- json: https://indexagentica.com/api/entries/mlflow.json

Tracing works with any LLM provider and agent framework and supports Python, TypeScript/JavaScript and Java. Evaluation and production monitoring track quality metrics over time; the prompt registry versions prompts with lineage and supports automatic prompt optimization; the AI Gateway is an OpenAI-compatible endpoint with credential management, rate limits, fallbacks and traffic splitting. A setup wizard can launch Claude Code, Codex or OpenCode to add tracing to an app. Run your own MLflow server or connect to a Databricks workspace.