All commands
Every hillclimb command, generated from the CLI itself.
One page per command, with its arguments, options and defaults as the CLI itself declares them. The CLI reference is the shorter, hand-written view: which command you want, and why.
Getting a problem and running it
| command | what it does |
|---|---|
hillclimb init | Make a folder a hillclimb dir. |
hillclimb problem … | Problems: copy a bundled one, or start your own. |
hillclimb verify | Run a problem's verifier once, outside a search. |
hillclimb run | Start a run on a problem or a run-spec YAML. |
hillclimb resume | Resume a parked or interrupted search. |
hillclimb smoke | One real DRAFT call through the selected coding agent, end to end. |
Watching a climb
| command | what it does |
|---|---|
hillclimb status | Show the candidate tree of a search. |
hillclimb watch … | Live TUI: runs, searches, candidates, and candidate details. |
hillclimb chart | Live hillclimb chart: best score so far vs tested candidates. |
hillclimb tree | Live tree of one search, drawn like the Darwin Gödel Machine's archive. |
hillclimb treeclimb | The tree and the climb chart of one search, side by side, live. |
hillclimb surface | Live 3D fitness surface of one search: candidates on the problem's terrain. |
hillclimb similarity … | Live 3D similarity views of a search's candidates: reference (named axes, default) and map (pairwise). |
hillclimb graph | Live knowledge graph (same screen as hillclimb knowledge graph). |
hillclimb show | Everything known about one candidate. |
Controlling a climb
| command | what it does |
|---|---|
hillclimb ps | Every process hillclimb is responsible for on this machine — compute only. |
hillclimb stop | Stop a running search now; it can be resumed. |
hillclimb kill | Last resort for a search that does not respond to hillclimb stop. |
hillclimb prune | Prune a candidate and its whole subtree. |
hillclimb summit | Copy the best solution found so far into your hillclimb dir. |
hillclimb reset | Kill every search of THIS hillclimb dir and delete what hillclimb made in it. |
Memory
| command | what it does |
|---|---|
hillclimb knowledge … | Cross-search learning: cards distilled from finished searches |
hillclimb paper … | Distill PDF papers into knowledge claims that seed future searches |
Experiments and policies
| command | what it does |
|---|---|
hillclimb experiment … | Compare setups: a study of named experiments (config overrides) × repeats on a problem |
hillclimb store … | The record store behind the cross-run views (store.backend in hillclimb.yaml: files | sqlite) |
Everything else
| command | what it does |
|---|---|
hillclimb disconnect | Undo hillclimb connect <agent>: unpin it and forget its credentials. |
hillclimb top | The control pane for every hillclimb process on this machine. |
hillclimb plot | Draw a solution the way its problem says: the problem's plot.py (matplotlib). |
hillclimb climber … | Climbers, the swappable search methods: list, copy, check. |
hillclimb connect … | Connect the coding agents (claude, codex, pi) and the OpenRouter route that pays for them. |
hillclimb sandbox … | The sandbox coding agents and solutions run in: what it stops, shown on this machine |
hillclimb skills … | The skills operators are given: the global layer and this folder's own |