MLflow Tracing

Open-source platform for tracing, evaluating and managing prompts for agents, LLMs and ML models

Observability tool by MLflow (Linux Foundation)

IndexedApache-2.0★ 28,516

Install

Pick your client. Read the repository before you give any tool access to your data.

pip install mlflow

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

MLflow tracing captures the inputs and outputs of each step in agent and LLM applications, built on OpenTelemetry. The platform also includes evaluation with built-in metrics and LLM judges, prompt versioning and optimization, and an AI Gateway that routes requests, handles fallbacks and enforces rate limits.

Use cases: monitoring-observability, llm-evaluation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category: Tracing · open source
Self-host: Yesraw.githubusercontent.com
Open source: Yesraw.githubusercontent.com
Protocols: opentelemetry, mcpraw.githubusercontent.com

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Signals

Stars: 28,516
Forks: 6,516
Open issues: 1,520
Last commit: Oct 24, 2026 (yesterday)
Last release: Oct 21, 2026 (5 days ago)

Details

Packages: pypi mlflow
License: Apache-2.0
Repository: github.com/mlflow/mlflow
Website: mlflow.org/genai
Docs: mlflow.org/docs/latest/genai/tracing/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README Website Docs

Cite this page

MLflow Tracing. Agent Mart. https://agentmart.dev/observability/mlflow-tracing (last updated 2026-10-24)