Probe

An agent-native Weights & Biases alternative

When coding agents run most of your experiments, the tracker has to work for them too: set itself up, take their writes, and answer their questions before they start the next run. Probe does that, and it keeps your W&B history.

Tell your coding agent:

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

Switch without losing anything

probe wandb import-local /srv/work --project folding
probe wandb import-hosted my-team my-wandb-project --project folding

See Weights & Biases in the docs.

What you can do that a dashboard can't

You want toWith Probe
Compare runs without building a dashboardAsk the dashboard agent "what changed from the baseline?" and get a chart linked to its source runs
Let your coding agent read past resultsprobe ask from the session, or a hosted MCP server with six read-only tools for any MCP client
Stop agents repeating failed experimentsAgents read the team's projects, experiments and notes before they start
Track RL, not only scalarsRewards per step, plus rollouts, turns and tool calls as spans, and Harbor trials
Keep the record after a crashData already saved stays available after the run or the machine stops
Get set up without a setup guideYour agent signs you up and installs Probe; you sign in once in the browser

Built for teams running agents

Learn more