Skip to content
SPECIFICTION
Get listed

MLflow Tracing

mlflow.org

Free plan Open source WebLinuxAPISelf-hosted
Visit mlflow.org
Spec score 8.4 #10 of 31 in AI Agent Observability Tools

Spec sheet

What it does
MLflow Tracing records inputs, outputs, and metadata for intermediate steps in LLM applications and AI agents so teams can inspect behavior and investigate issues.Read 21 Oct 2026 · mlflow.org
Purpose
MLflow Tracing captures inputs, outputs, and metadata from each step of LLM application and agent requests to help diagnose bugs and unexpected behavior.Read 30 Sep 2026 · mlflow.org
Integrations
The integrations directory organizes automatic tracing support across frameworks, coding agents, and model providers.Read 21 Oct 2026 · mlflow.org
Maker
The MLflow project is developed at Databricks, according to TrustRadius.Read 21 Oct 2026 · trustradius.com
Automatic instrumentation
MLflow offers one-line automatic tracing integrations for supported LLM and agent libraries, including OpenAI, LangChain, and DSPy.Read 21 Oct 2026 · mlflow.org
Automatic tracing
The integrations page lists automatic tracing for more than 40 LLM and AI agent libraries and frameworks.Read 30 Sep 2026 · mlflow.org
Browser limitation
The TypeScript SDK works in Node.js backend environments and is not compatible with frontend browser or Edge Runtime environments.Read 30 Sep 2026 · mlflow.org
Company founded
Databricks says it was founded in 2013 by the creators of Apache Spark, Delta Lake, MLflow, and Unity Catalog.Read 21 Oct 2026 · databricks.com
Company headquarters
Databricks says it is headquartered in San Francisco.Read 21 Oct 2026 · databricks.com
Dataset creation
Production traces can be used to build evaluation datasets that retain details about components such as retrievers and tools.Read 21 Oct 2026 · mlflow.org
Developer support
The repository directs users to documentation, GitHub issues, a mailing list, and Slack for help and project discussions.Read 21 Oct 2026 · github.com
Documentation
MLflow documentation has separate sections for LLM and agent development, tracing, and evaluation, and for traditional machine-learning workflows.Read 21 Oct 2026 · mlflow.org
Evaluation
MLflow connects trace inspection with evaluation results to help assess application quality.Read 21 Oct 2026 · mlflow.org
Human feedback
Users can attach feedback to traces with metadata such as the user and timestamp.Read 21 Oct 2026 · mlflow.org
Licence
The public MLflow repository identifies its licence as Apache-2.0.Read 21 Oct 2026 · github.com
Lightweight SDK
The production tracing package, `mlflow-tracing`, is documented as having a 95% smaller footprint than the full `mlflow` package.Read 30 Sep 2026 · mlflow.org
Maker and community
The MLflow site describes the project as backed by the Linux Foundation and committed to open source for more than five years.Read 30 Sep 2026 · mlflow.org
Manual instrumentation
Python developers can instrument custom functions with the `@mlflow.trace` decorator or create spans directly.Read 21 Oct 2026 · mlflow.org
OpenTelemetry
MLflow Tracing is compatible with OpenTelemetry and supports GenAI semantic conventions for trace export and ingestion.Read 21 Oct 2026 · mlflow.org
OTLP ingestion limit
OpenTelemetry trace ingestion requires MLflow 3.6.0 or later and a SQL-based backend store.Read 30 Sep 2026 · mlflow.org
Pricing
The MLflow Tracing page describes the open-source product as free and says trace data can be hosted on the user's infrastructure.Read 21 Oct 2026 · mlflow.org
Production monitoring
Tracing records latency, token usage, and quality metrics to help monitor deployed LLM applications and agents.Read 21 Oct 2026 · mlflow.org
Production package
The product documentation recommends the `mlflow-tracing` package for production deployments and says it has a 95% smaller footprint than the full MLflow package.Read 21 Oct 2026 · mlflow.org
Production use
The documentation describes tracing as production-ready and recommends asynchronous logging and sampling for production deployments.Read 30 Sep 2026 · mlflow.org
Rating on G2
No product rating or review count for MLflow Tracing is stated on the opened G2 MLflow marketplace page.Read 21 Oct 2026 · ai.g2.com
Rating on TrustRadius
8 out of 10 from 3 reviewsRead 21 Oct 2026 · trustradius.com
Review availability
TrustRadius lists three reviews for MLflow, but its page describes the broader MLflow platform rather than the Tracing feature alone.Read 21 Oct 2026 · trustradius.com
Review limitation
TrustRadius reviews cover MLflow as a broader machine-learning platform, so the page does not establish a Tracing-specific score.Read 21 Oct 2026 · trustradius.com
SDK languages
The MLflow repository describes support for Python, TypeScript or JavaScript, Java, and other languages, alongside OpenTelemetry integration.Read 21 Oct 2026 · github.com
Search and filtering
The trace table supports searching and filtering traces in the MLflow UI.Read 21 Oct 2026 · mlflow.org
Self-hosting
The repository's setup instructions show starting an MLflow server locally and connecting tracing to it.Read 21 Oct 2026 · github.com
Sensitive data
Custom span processors can mask sensitive data on the client before spans are sent to the backend.Read 30 Sep 2026 · mlflow.org
Server security
MLflow 3.5.0 and later include middleware for DNS rebinding, CORS, and clickjacking protections; the server documentation recommends a reverse proxy or VPN for TLS and authentication in production.Read 30 Sep 2026 · mlflow.org
Telemetry access
The same project review says raw telemetry is stored in a Databricks-managed environment and accessible to MLflow maintainers.Read 21 Oct 2026 · lfprojects.org
Telemetry privacy
In a Linux Foundation project review, the MLflow team said telemetry does not identify users' internal or proprietary AI tools and generalizes custom tool identifiers.Read 21 Oct 2026 · lfprojects.org
Trace controls
The product documentation lists PII redaction, sampling controls, global disablement, asynchronous tracing, and cross-service context propagation.Read 21 Oct 2026 · mlflow.org
Trace customization
The tracing API supports adding tags and metadata, associating users and sessions, and disabling tracing within a code scope.Read 21 Oct 2026 · mlflow.org
Trace inspection
The trace view presents execution spans, timing, inputs and outputs, tool calls, errors, token counts, costs, and attached feedback.Read 21 Oct 2026 · mlflow.org
Trace UI requirements
The notebook trace UI requires MLflow 2.20 or later and an MLflow Tracking Server to provide its UI assets.Read 21 Oct 2026 · mlflow.org
Trace views
Trace details include a span tree, per-span latency, inputs and outputs, tool calls, exception details, token counts, cost breakdown, feedback, and ground-truth annotations.Read 30 Sep 2026 · mlflow.org

Plans and prices

MLflow Tracing Free Open source · trace data hosted on your own infrastructure Read 30 Sep 2026 · mlflow.org

Every MLflow Tracing plan and price →

Where Specifiction places it

Alternatives to MLflow TracingAll alternatives →