hillclimb run
Start a run on a problem or a run-spec YAML.
Start a run on a problem or a run-spec YAML.
The search runs in the background and the terminal comes straight back: hillclimb watch follows it, hillclimb stop --all ends it. --no-detach keeps it in this terminal instead (Ctrl-C stops it).
hillclimb run [OPTIONS] TARGETArguments
| argument | what it is |
|---|---|
TARGET | — required |
Options
| option | what it does |
|---|---|
--budget TEXT | Wall-clock budget, e.g. 2h / 30m. |
--agent, --backend TEXT | The coding agent that runs the operators: claude-code | codex | pi | dummy | toy (the last two need no LLM; --backend is the old spelling). |
--model TEXT | Model the coding agent runs, e.g. sonnet / opus. |
--climber TEXT | The climber: a .py file, a climber folder, or package.module:Class (hillclimb climber list shows the catalog's). It replaces the climber: block of runs/config.yaml (or of the run spec); --set climber.params.k=v edits it. Repeat it (--climber climbers/greedy --climber climbers/gepa) for a mixed fleet: one search per climber on the problem, under one run, each tagged as an experiment. |
--holdout / --no-holdout | Hidden selection holdout. Default: on. |
--learning / --no-learning | Cross-search memory (cards/claims injection + distillation); off = memory-blind experiment. Default: on. |
--name TEXT | Run name shown in the TUI. |
--parallel-agents, --parallel-operators INTEGER | Concurrent coding agents per search, one candidate each (--parallel-operators is the old spelling). |
--parallel-searches INTEGER RANGE | Independent searches on the problem at once, each in the background. Default: 1. |
--solution-cpus INTEGER RANGE | CPU cores each run of a solution may use, given to it as $HILLCLIMB_CPUS (default 1; --set concurrency.solution_cpus=N is the same). |
--detach / --no-detach | Run in the background (the default; hillclimb watch follows it) or in this terminal (Ctrl-C stops it). Default: on. |
--parallel-replicates INTEGER RANGE | How many of a trial's replicates run at once: 0 = all (default), 1 = one after another, required when the metric measures the machine (time, throughput, memory). |
--seed-from PATH | Incumbent solution.py scored as the floor candidate. |
--set TEXT | Any config setting, dotted: --set climber.params.num_drafts=5 --set learning.enabled=false. |
--experiment-set, --arm-set TEXT | A setting for one experiment of a mixed fleet, EXPERIMENT:KEY=VALUE: --experiment-set gepa:concurrency.parallel_agents=1 (applied after --set; --arm-set is the old spelling). |
--study TEXT | Tag the search as one experiment of a study (with --experiment); names a mixed fleet's study. |
--experiment TEXT | The experiment name (with --study). |