Bayesian optimization as a service and an open-source engine: ask for the next point, evaluate it yourself, report the result.
TauOpt picks the next configuration to try when each evaluation is expensive: hyperparameter tuning, simulator calibration, experimental design. The engine fits a model to everything reported so far and picks the next point, and every suggestion carries a receipt naming the strategy that produced it.
One client runs the engine in-process on your own machine or talks to the hosted service, with the same create, suggest, observe, and best calls either way.
Expensive evaluations
Built for loops where each evaluation costs real time: a training run, a simulation, an experiment. Report a crashed evaluation as a failure and a noisy one with its measurement noise.
Hosted parallel workers
Share one experiment across many workers on the hosted service. Each open suggestion holds a slot until its result is reported, so a batch of jobs or a whole cluster can draw from the same experiment without repeating a point.
MCP access for agents
The hosted service exposes the experiment surface as tools over the Model Context Protocol, so an agent in Claude Code or any other MCP client can create an experiment, ask for suggestions, and report results in conversation.
The engine is open source under the Apache 2.0 license. The hosted service adds accounts, persistence, and parallel workers on top of it.
Request access
Hosted access is by request. Tell us what you want to optimize and how you evaluate it.
Open the request form →