Hillclimb: Open-source AlphaEvolve-style search with Claude Code and Codex

Hillclimb launched as an open-source CLI and modular Python framework for building, testing and benchmarking hillclimbing algorithms driven by coding agents such as Claude Code and Codex. The framework separates a problem, defined by a verifier script (verifier.sh) and optional starting solution (solution.py), from a climber, a search algorithm composed of five modules — selector_policy, operator_policy, operators, tuner and memory — with catalog climbers greedy, openevolve and gepa. Installed via `uv tool install hillclimb` or `pip install hillclimb` on Python 3.12+, it runs searches in the background under a user-set compute budget and keeps the best result in runs/<run-id>/searches/<search-id>/best/.

Hillclimbing on verifiable rewards. Use Claude Code and Codex to autonomously search for python programs that optimize a score you define. Website https://hillclimb.sh?utm medium=readme · Docs https://docs.hillclimb.sh?utm medium=readme · Quickstart https://docs.hillclimb.sh/quickstart?utm medium=readme · Python SDK https://docs.hillclimb.sh/python?utm medium=readme · CLI reference https://docs.hillclimb.sh/cli?utm medium=readme · Blog https://docs.hillclimb.sh/blogposts?utm medium=readme · Discord https://hillclimb.sh/discord?utm medium=readme hillclimb is a CLI and modular Python framework for building, testing and benchmarking hillclimbing algorithms powered by coding agents. It provides reusable components and a common way to evaluate different search strategies across different problems — from speeding up code and solving optimisation problems to improving prediction accuracy. The goal of hillclimb to create a framework to enable discovery of better autoresearch methods, rather than build a single best autoresearcher. There are two main parts: the problem https://docs.hillclimb.sh/problems?utm medium=readme and the climber https://docs.hillclimb.sh/climbers?utm medium=readme . A problem defines what counts as better through a verifier script, verifier.sh , and optionally includes a starting solution, solution.py . A climber is a search algorithm that drafts initial solutions and then decides which solutions to build on and what to try next. Start with built-in problems and climbers, or write your own ones. hillclimb run https://docs.hillclimb.sh/cli/commands/run?utm medium=readme starts the search in the background and returns control of your terminal. Within the compute budget you set, the climber dispatches headless coding agents to write, debug and improve solutions. Your verifier scores each attempt, and hillclimb keeps the best result. A hillclimb search running visualised through hillclimb watch : uv tool install hillclimb or: pip install hillclimb Python 3.12+ hillclimb connect claude or codex, pi, openrouter; add --agent dummy to any run for no LLM at all hillclimb init hillclimb.yaml, problems/, runs/, climbers/ in this folder hillclimb problem get heilbronn-convex-13 the verifier is the problem; description.md is the brief hillclimb climber get greedy the climber, as Python you can read and edit climbers/greedy/policy.py hillclimb verify heilbronn-convex-13 score the floor solution hillclimb run heilbronn-convex-13 --budget 10m hillclimb watch live coding agents and scores also: chart, tree hillclimb stop --all hillclimb summit copy the best solution.py into this folder Every search also keeps its best in runs/<run-id /searches/<search-id /best/ . The walkthrough https://docs.hillclimb.sh/walkthrough?utm medium=readme goes through each step. A climber is five modules, run in this order at every step of a search. The engine ships none of the first two: the catalog's climbers greedy , openevolve , gepa are Python files hillclimb climber get copies into your folder, to read and edit; the other three are built in or a file of your own. | Module | Decides | Built in / in the catalog | |---|---|---| | selector policy | which candidate the next attempt builds on | Best , MapElites catalog | | operator policy | which operator to apply to it | Greedy catalog | | operators | how one attempt is made: the prompt the coding agent gets | draft , debug , improve , ensemble | | tuner | which parameter values to try on a candidate | random , optuna | | memory | what carries over from one search to the next | files , none | Together they are one block of config, in a run spec or as the folder's run default in runs/config.yaml hillclimb climber get pins one there : climber: selector policy: climbers/openevolve/policy.py:MapElites which candidate to build on next operator policy: climbers/greedy/policy.py:Greedy which operator to use on it operators: draft, debug, improve, crossover.py:Crossover tuner: optuna memory: files params: {num drafts: 5} Every slot takes a .py file file.py:Class , package.module:Class , or a built-in's name. A fetched climber is one file that builds the whole block climber: climbers/greedy/policy.py . Or compose in Python: python from hillclimb import Budget, Climber, Problem, catalog greedy, openevolve = catalog.module "greedy" , catalog.module "openevolve" problem = Problem "heilbronn-convex-13" budget = Budget wall clock="10m", evaluations=40 climber = Climber selector policy=openevolve.MapElites num drafts=5 , operator policy=greedy.Greedy climber.search problem, budget=budget climber.best, climber.history, climber.to frame A catalog climber that imports a library beyond hillclimb openevolve , gepa names it in a requirements.txt beside its policy.py — pip install -r climbers/gepa/requirements.txt , as climber get says; tuner: optuna is the engine's and needs 'hillclimb optuna ' . climber.start ... opens the same search to drive by hand, one climber.step at a time, and Problem name, score=my function, ... defines a problem from a scoring function. Runnable scripts are in examples/ https://github.com/rebase-energy/hillclimb/tree/main/examples . Compare two head to head: hillclimb climber get openevolve --no-default hillclimb run heilbronn-convex-13 --climber climbers/greedy/policy.py --climber climbers/openevolve/policy.py one search each; --parallel-searches 3 runs three of each hillclimb experiment report <run-id | From first run to following and resuming a search. | Define your own problem and write its verifier. | | The modules a climber is built from. | Compare climbers on the same problem. | | Every example problem and its best known value. | Every hillclimb command and its flags. | | Build and run searches from Python. | Blog posts on hillclimbing. | Questions, results, ideas: join the Discord https://hillclimb.sh/discord?utm medium=readme .