Probe

Probe vs MLflow

MLflow is an open-source platform for the machine learning lifecycle: experiment tracking, a model registry and deployment tools, which you run yourself or use as a managed service. Probe is a hosted experiment tracker built for teams whose coding agents run the experiments.

Tell your coding agent:

Install Probe on this machine and its coding agents. Read https://research.prbe.ai/install.md and follow it.

How they differ

ProbeMLflow
What it isA hosted experiment record for ML teams and their coding agentsAn open-source ML lifecycle platform: tracking, model registry, deployment
SetupYour agent signs you up and installs Probe; you sign in once in the browserYou run a tracking server or use a managed MLflow service
Logging from codeprobe.init() and probe.log()MLflow's tracking API
Coding agentsWork is recorded as it happens, by the Probe daemon or the agent itself; agents read the team's record with probe ask or a hosted read-only MCP serverMLflow's Claude Code integration traces the agent's own sessions (prompts, tool calls, tokens and cost); its MCP server lets an agent search traces and read experiments and runs

MLflow facts above are from the MLflow documentation, its page on tracing Claude Code and its MCP server page, checked November 2026.

Pick MLflow if

Pick Probe if

Learn more