Bayesian optimization
Each trial result informs the next. The optimizer focuses on promising regions of your parameter space, finding better configurations in fewer runs than grid or random search.
Hyperparameter optimization,managed for you
Define your search space and objective. We run trials, track metrics, and surface the best configuration in a clean dashboard. No infra needed.
Benefits
Focus on strategy. We handle the search.
Stop manually tuning hyperparameters. Let Bayesian optimization find the best configuration while you focus on what matters: your model, strategy, or simulation.
Zero infrastructure
No clusters to provision, no job queues, no teardown scripts. Push a Docker image, configure parameter ranges in the dashboard, and we handle everything else.
Full privacy & isolation
Containers run in complete isolation. We only see the metric lines you explicitly print to stdout. Zero access to your source code, trading logic, or data.
Visual results dashboard
Leaderboard ranked by any metric, convergence plots showing optimizer progress, and Pareto frontiers for multi-objective experiments. Visual clarity, not a CSV dump.
Parallel trial execution
Multiple trials run simultaneously across our infrastructure (5 by default). Experiments finish faster while the optimizer uses completed results to guide the search.
Flexible parameter spaces
Integer, float, categorical: define any combination of hyperparameters and their ranges. The optimizer handles the sampling and search strategy automatically.
How it works
Three steps. No SDK.
Docker in, metrics out, ranked results on a dashboard. That's the whole contract.
1
Build a Docker image
Package your code in a Docker container. Any language, any framework: if it runs in Docker, it works with us.
2
Parse args & print metrics
Read --hpo-* flags at runtime and emit metrics with the hpo.metrics. prefix.
3
View results in the dashboard
We run parallel trials, the optimizer suggests the next parameter set, and you see the live leaderboard as your experiment runs.
Strengths
Built for real workloads
No vendor lock-in, no proprietary SDK. Just Docker, stdout, and CLI args.
Docker-native
Any language, any framework. If it runs in Docker, it works with HyperOptimizer. No SDK, no client library, no lock-in.
No code changes needed
Parse CLI args with argparse (or any library) and print metrics to stdout. Two changes to your code. That's it.
Multi-objective optimization
Optimize for multiple metrics simultaneously. Pareto frontiers help you balance competing objectives like return vs. drawdown.
Fault-tolerant trials
Each trial runs independently. If one fails or times out, the others continue. Results from completed trials are always preserved.
Integrations
Works with your stack
HyperOptimizer is Docker-native. These guides show how specific frameworks integrate.
Docker
Run any program, any language, any framework. Build a Docker image and optimize.
NautilusTrader
High-performance algorithmic trading optimization with Nautilus backtests.
Freqtrade
Optimize your crypto trading bot hyperparameters with managed infrastructure.
Soon
Bring your own cloud
Run trials in your cloud. Coming soon.
Ready to optimize?
Join the private beta. Free during beta, no credit card, no commitment. Want us to support your framework? Let us know.