openevolve
Open-source implementation of AlphaEvolve
File Explorer
Download Latest Version (.zip)- sidebar-node-logic.instructions.md
- claude.yml
- python-test.yml
- release.yml
- security-scan.yml
- default_config.yaml
- early_stopping_example.yaml
- island_config_example.yaml
- island_examples.yaml
- README.md
- best_program.py
- best_program_info.json
- config.yaml
- evaluator.py
- initial_program.py
- best_program.py
- best_program_info.json
- config.yaml
- evaluator.py
- initial_program.py
- best_program.py
- best_program_info.json
- config.yaml
- evaluator.py
- initial_program.py
- best_program.py
- best_program_info.json
- config.yaml
- evaluator.py
- initial_program.py
- best_program.py
- best_program_info.json
- config.yaml
- evaluator.py
- initial_program.py
- best_program.py
- best_program_info.json
- config.yaml
- evaluator.py
- initial_program.py
- best_program.py
- best_program_info.json
- config.yaml
- evaluator.py
- initial_program.py
- best_program.py
- best_program_info.json
- config.yaml
- evaluator.py
- initial_program.py
- create_task.py
- generate_all_tasks.py
- README.md
- requirements.txt
- run_benchmark.py
- task_adapter.py
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- requirements.txt
- README.md
- Evolved task.png
- example.png
- best_program.py
- best_program_info.json
- post_evolution_evaluation_result.json
- 90c2a0c2-e3bd-4aa4-9bdc-1ab1b9326f97.json
- ce48590c-4448-45b9-83f4-9e0a85424033.json
- best_program.py
- best_program_info.json
- metadata.json
- base_config.yaml
- config.yaml
- evaluator.py
- generate_config.py
- initial_program.py
- post_evolution_eval.py
- README.md
- run_evolution.sh
- failing_config.yaml
- prev_sim__works_evaluator.py
- attn.mlir
- attn_template.mlir
- baseline_attention.mlir
- baseline_attention_v0.mlir
- export_mlir.mlir
- self_attention_torch_mlir_gen.mlir
- self_attention_with_consts_torch_dialect.mlir
- self_attn_with_consts_linalg_dialect.mlir
- self_attn_with_consts_linalg_dialect.mlir.backup
- debug_real_execution.py
- fix_tensor_shapes.py
- mlir_lowering_pipeline.py
- mlir_syntax_test.py
- to_real_mlir.sh
- test_evaluator.py
- test_results.py
- config.yaml
- evaluator.py
- initial_program.py
- README.md
- config.yaml
- evaluator.py
- fixtures.py
- initial_program.py
- README.md
- test_gaming.py
- best_program.py
- best_program_info.json
- circle_packing_1.png
- circle_packing_10.png
- circle_packing_190.png
- circle_packing_460.png
- config_phase_1.yaml
- config_phase_1_anthropic.yaml
- config_phase_2.yaml
- config_phase_2_anthropic.yaml
- evaluator.py
- initial_program.py
- README.md
- requirements.txt
- config.yaml
- config_phase_1.yaml
- config_phase_2.yaml
- evaluator.py
- evolution_plot.png
- initial_program.py
- README.md
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- README.md
- config.yaml
- evaluator.py
- initial_program.py
- README.md
- requirements.txt
- compare_results.py
- config.yaml
- evaluator.py
- initial_program.py
- iterative_agent.py
- README.md
- run_iterative.sh
- run_iterative_trials.py
- run_openevolve.sh
- run_openevolve_trials.py
- run_random_baseline.py
- evaluation.txt
- evaluator_system_message.txt
- full_rewrite_user.txt
- config.yaml
- config_qwen3_baseline.yaml
- config_qwen3_evolution.yaml
- dataset_settings.yaml
- emotion_prompt.txt
- emotion_prompt_dataset.yaml
- evaluate_prompts.py
- evaluation_results_baseline_20250809_070942.json
- evaluation_results_evolved_20250809_103002.json
- evaluator.py
- gsm8k_prompt.txt
- gsm8k_prompt_dataset.yaml
- hotpotqa_prompt.txt
- hotpotqa_prompt_dataset.yaml
- hover_prompt.txt
- hover_prompt_dataset.yaml
- ifeval_prompt.txt
- ifeval_prompt_dataset.yaml
- initial_prompt.txt
- initial_prompt_dataset.yaml
- README.md
- requirements.txt
- run_evolution.sh
- diff_user.txt
- evaluation.txt
- evolution_history.txt
- full_rewrite_user.txt
- previous_attempt.txt
- top_program.txt
- config.yml
- evaluator_stub.py
- initial_content_stub.txt
- lm-eval.py
- README.md
- requirements.txt
- best_program.py
- best_program_info.json
- config.yaml
- evaluator.py
- EVOLUTION_ANALYSIS.md
- initial_program.py
- mlx_lm_generate_with_hook.py
- quick_benchmark_test.py
- quick_demo.py
- qwen3_benchmark_suite.py
- README.md
- requirements.txt
- run_benchmarks.py
- run_evolve_experiment.sh
- test_optimized_attention.py
- config.yaml
- evaluator.py
- example.kattisrc
- initial_program.py
- README.md
- requirements.txt
- submit.py
- config.yaml
- evaluator.py
- initial_program.r
- README.md
- requirements.txt
- lib.rs
- main.rs
- .gitignore
- Cargo.lock
- Cargo.toml
- config.yaml
- evaluator.py
- initial_program.rs
- README.md
- requirements.txt
- config.yaml
- evaluator.py
- initial_program.py
- README.md
- requirements.txt
- data_constrained_scaling_law.yaml
- domain_mixture_scaling_law.yaml
- easy_question_scaling_law.yaml
- lr_bsz_scaling_law.yaml
- moe_scaling_law.yaml
- parallel_scaling_law.yaml
- sft_scaling_law.yaml
- vocab_scaling_law.yaml
- data_loader.py
- evaluator.py
- init_program.py
- README.md
- run.sh
- dataclasses.py
- datamodules.py
- data_api.py
- eval.py
- README.md
- scripts.sh
- additional.hpp
- context.hpp
- json.hpp
- local_2_opt_search.hpp
- local_k_opt_search.hpp
- random_solution.hpp
- utils.hpp
- config.json
- heat_map_inference.py
- heat_map_train.py
- TSP.cpp
- additional.hpp
- context.hpp
- json.hpp
- local_2_opt_search.hpp
- local_k_opt_search.hpp
- random_solution.hpp
- utils.hpp
- config.json
- heat_map_inference.py
- heat_map_train.py
- TSP.cpp
- metric_improvement_through_evolution_process.png
- code_to_query.py
- heat_map_runner.py
- load_data.py
- runner.py
- tsp_runner.py
- utils.py
- .gitignore
- config.yaml
- evaluator.py
- README.md
- requirements.txt
- start_evolution.py
- config.yaml
- evaluator.py
- initial_program.py
- README.md
- requirements.txt
- README.md
- __init__.py
- base.py
- claude_code.py
- ensemble.py
- openai.py
- __init__.py
- sampler.py
- templates.py
- diff_user.txt
- evaluation.txt
- evaluator_system_message.txt
- evolution_history.txt
- fragments.json
- full_rewrite_user.txt
- inspiration_program.txt
- inspirations_section.txt
- previous_attempt.txt
- system_message.txt
- system_message_changes_description.txt
- system_message_with_changes_description.txt
- top_program.txt
- user_message_with_changes_description.txt
- __init__.py
- async_utils.py
- code_utils.py
- format_utils.py
- metrics_utils.py
- trace_export_utils.py
- __init__.py
- _version.py
- api.py
- cli.py
- config.py
- controller.py
- database.py
- embedding.py
- evaluation_result.py
- evaluator.py
- evolution_trace.py
- novelty_judge.py
- process_parallel.py
- test_regional_endpoint.py
- main.css
- manual.css
- graph.js
- list.js
- main.js
- mainUI.js
- manual.js
- performance.js
- sidebar.js
- state.js
- index.html
- manual_page.html
- program_page.html
- manual.py
- requirements.txt
- visualizer.py
- __init__.py
- conftest.py
- README.md
- test_checkpoint_with_llm.py
- test_evolution_pipeline.py
- test_examples_validation.py
- test_iteration_counting_with_llm.py
- test_library_api.py
- test_migration_with_llm.py
- test_smoke.py
- test_api.py
- test_api_key_from_env.py
- test_artifacts.py
- test_artifacts_integration.py
- test_boolean_metrics.py
- test_cascade_validation.py
- test_changes_description.py
- test_checkpoint_resume.py
- test_claude_code_llm.py
- test_cli_model_override.py
- test_code_utils.py
- test_concurrent_island_access.py
- test_database.py
- test_database_cleanup.py
- test_early_stopping_config.py
- test_embedding.py
- test_evaluator_timeout.py
- test_evolution_trace.py
- test_feature_stats_persistence.py
- test_file_extension_preservation.py
- test_format_utils.py
- test_grid_stability.py
- test_initial_program_artifacts.py
- test_island_child_placement.py
- test_island_isolation.py
- test_island_map_elites.py
- test_island_migration.py
- test_island_parent_consistency.py
- test_island_tracking.py
- test_iteration_counting.py
- test_llm_config_optional_params.py
- test_llm_ensemble.py
- test_map_elites_features.py
- test_migration_no_duplicates.py
- test_model_parameter_demo.py
- test_novelty_asyncio_issue.py
- test_openai_model_detection.py
- test_orphan_program_removal.py
- test_population_elite_protection.py
- test_process_parallel.py
- test_process_parallel_fix.py
- test_prompt_inspiration_dedup.py
- test_prompt_sampler.py
- test_prompt_sampler_comprehensive.py
- test_provider_propagation.py
- test_reasoning_effort_config.py
- test_regional_endpoint.py
- test_sample_from_island_inspirations.py
- test_sample_from_island_ratios.py
- test_snapshot_artifacts_limit.py
- test_template_dir_resolution.py
- test_utils.py
- test_valid_configs.py
- test_visualization_sanitization.py
- .gitignore
- .pre-commit-config.yaml
- CLAUDE.md
- CONTRIBUTING.md
- Dockerfile
- LICENSE
- Makefile
- MANIFEST.in
- openevolve-architecture.png
- openevolve-logo.png
- openevolve-run.py
- openevolve-visualizer.png
- pyproject.toml
- README.md
- setup.py
# Installation Guide
git clone https://github.com/algorithmicsuperintelligence/openevolve
Downloads the entire project code from GitHub to your computer.
cd openevolve
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommendedpip install openevolve
Installs the package published on PyPI directly โ no need to clone the source.
pip install optillm
Installs the package published on PyPI directly โ no need to clone the source.
npm install -g @anthropic-ai/claude-code
Installs the package published on the npm registry globally โ no need to clone the source.
Pulled directly from this repo's README.
3. Docker
Easy- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker pull ghcr.io/algorithmicsuperintelligence/openevolve:latest
Type this command into your terminal and run it.
docker run --rm -v $(pwd):/app ghcr.io/algorithmicsuperintelligence/openevolve:latest \
Runs the built image as an actual container.
Pulled directly from this repo's README.
4. Python
Easypip install openevolve
Installs the package published on PyPI directly โ no need to clone the source.
pip install -e ".[dev]"
Installs the Python libraries listed in requirements.txt (or similar).
pip install optillm
Installs the package published on PyPI directly โ no need to clone the source.
pip install -r scripts/requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
Pulled directly from this repo's README.
5. Make
Medium- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
make
Compiles the code based on the generated build configuration to produce an executable.
