agents-last-exam
Agents' Last Exam
파일 탐색기
최종 버전 다운로드 (.zip)- cua-client.js
- index.js
- package-lock.json
- package.json
- README.md
- index.js
- vm-client.js
- package-lock.json
- package.json
- README.md
- __init__.py
- image_retention.py
- trajectory_saver.py
- __init__.py
- canonical.py
- canonical_sanitize.py
- canonical_types.py
- __init__.py
- compaction.py
- context.py
- README.md
- replay.py
- token_estimation.py
- transcript.py
- __init__.py
- memory.py
- memory_flush.py
- memory_flush_policy.py
- README.md
- __init__.py
- _message_shapes.py
- cache_policy.py
- helper_runtime.py
- image_sanitization.py
- model_config.py
- thinking.py
- unified_loop.py
- __init__.py
- README.md
- subagent_general.py
- subagent_gui.py
- subagent_gui_protocol.py
- subagent_registry.py
- subagent_session.py
- subagent_tools.py
- __init__.py
- _paths.py
- _tool_utils.py
- analyze_image.py
- computer_handler.py
- fs_backends.py
- mcp_runtime.py
- README.md
- tools.py
- tools_fs.py
- tools_shell.py
- tools_web.py
- __init__.py
- agent_loop.py
- agent_loop_helpers.py
- AGENTS.md
- AUDIT.md
- prompt.py
- session.py
- __init__.py
- config.py
- deployer.py
- pyproject.toml
- README.md
- transcript_to_trajectory.py
- __init__.py
- config.py
- deployer.py
- pyproject.toml
- telemetry.py
- __init__.py
- AGENTS.md
- config.py
- deployer.py
- pyproject.toml
- README.md
- telemetry.py
- upstream
- __init__.py
- AGENTS.md
- config.py
- deployer.py
- pyproject.toml
- README.md
- __init__.py
- AGENTS.md
- config.py
- deployer.py
- pyproject.toml
- README.md
- __init__.py
- config.py
- deployer.py
- pathscan.py
- pyproject.toml
- __init__.py
- AGENTS.md
- config.py
- deployer.py
- pyproject.toml
- README.md
- __init__.py
- AGENTS.md
- config.py
- deployer.py
- pyproject.toml
- README.md
- upstream
- __init__.py
- config.py
- deployer.py
- otel.py
- pyproject.toml
- README.md
- telemetry.py
- __init__.py
- AGENTS.md
- config.py
- deployer.py
- pyproject.toml
- README.md
- upstream
- __init__.py
- AGENTS.md
- config.py
- deployer.py
- pyproject.toml
- README.md
- upstream
- __init__.py
- config.py
- deployer.py
- pyproject.toml
- telemetry.py
- __init__.py
- AGENTS.md
- config.py
- deployer.py
- pyproject.toml
- README.md
- upstream
- vision.py
- __init__.py
- AGENTS.md
- config.py
- deployer.py
- pyproject.toml
- README.md
- __init__.py
- AGENTS.md
- config.py
- deployer.py
- pyproject.toml
- README.md
- _bootstrap.py
- __init__.py
- agent_deployer.py
- executor.py
- sandbox.py
- task_data.py
- trajectory.py
- custom_startup.sh
- firefox.desktop
- install_firefox.sh
- Dockerfile
- Dockerfile
- entrypoint.sh
- healthcheck.sh
- README.md
- bake_nested_images.sh
- build.sh
- cleanup.sh
- entrypoint.sh
- export_rootfs.sh
- README.md
- __init__.py
- ale_kasm.py
- ale_ubuntu22.py
- ale_ubuntu22_docker.py
- ale_win10.py
- ale_win_server.py
- __init__.py
- aliyun.py
- aws.py
- docker.py
- gcloud.py
- qemu.py
- static.py
- __init__.py
- baked_in_sandbox.py
- gsbucket.py
- huggingface.py
- local_host.py
- ossbucket.py
- s3bucket.py
- __init__.py
- env.py
- output_pull.py
- __init__.py
- _docker_entry.py
- _sandbox_entry.py
- _secrets.py
- docker.py
- Dockerfile.native_base
- local.py
- sandbox.py
- __init__.py
- config_loader.py
- experiment_spec.py
- factory.py
- lifecycle.py
- run_writer.py
- runner.py
- termination.py
- __init__.py
- driver.py
- loader.py
- __main__.py
- cli.py
- logo.png
- teaser.pdf
- teaser.png
- ale_claw.yaml
- claude_code.yaml
- codex.yaml
- cursor_cli.yaml
- droid.yaml
- dummy.yaml
- forgecode.yaml
- gemini_cli.yaml
- grok_build.yaml
- grok_cli.yaml
- hermes.yaml
- kimi_code.yaml
- openclaw_cli.yaml
- openhands_cli.yaml
- terminus_2.yaml
- docker.yaml
- environment_aliyun.yaml
- environment_aws.yaml
- environment_gcloud.yaml
- qemu.yaml
- static_win_dev.yaml
- app.js
- nav.js
- style.css
- add-agent.html
- add-environment.html
- add-task.html
- agents.html
- aliyun.html
- aws.html
- build-image.html
- configure.html
- google-cloud.html
- local-docker.html
- local.html
- mcp-tools.html
- providers.html
- run.html
- sandbox.html
- static.html
- tasks.html
- trajectories.html
- trajectory-schema.html
- index.html
- README.md
- serve.py
- local-qemu.md
- quickstart.md
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- leap_filter_sequence.py
- leap_preprocessing_algorithms.py
- leapctype.py
- leaptorch.py
- libleapct.so
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.sh
- meta.json
- install.ps1
- meta.json
- meta.json
- README.md
- meta.json
- README.md
- install.ps1
- meta.json
- install.ps1
- meta.json
- install.ps1
- meta.json
- install.ps1
- meta.json
- install.ps1
- meta.json
- install.ps1
- meta.json
- install.ps1
- meta.json
- install.ps1
- meta.json
- install.ps1
- meta.json
- install.ps1
- meta.json
- meta.json
- README.md
- meta.json
- README.md
- meta.json
- README.md
- install.ps1
- meta.json
- meta.json
- README.md
- meta.json
- README.md
- install.ps1
- meta.json
- install.ps1
- meta.json
- install.ps1
- meta.json
- install_task_deps.sh
- README.md
- verify_task_env.sh
- import_images.sh
- sync_task_data.sh
- import_images.sh
- sync_task_data.sh
- fetch_task_data.sh
- publish_qemu_images.py
- openai.env.example
- .env.example
- full-spectrum.txt
- last-exam.txt
- near-term.txt
- overall.txt
- full-spectrum.txt
- last-exam.txt
- near-term.txt
- overall.txt
- ale_cli.txt
- cpu_unlicensed.txt
- docker_support.txt
- full.txt
- hello_both.txt
- licensed.txt
- tool_smoke_both.txt
- unlicensed.txt
- score_outputs.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- __init__.py
- __init__.py
- ar_task_shared.py
- finance_evaluation.py
- generate_alt_references.py
- __init__.py
- score_american_option_outputs.py
- main.py
- task_card.json
- main.py
- task_card.json
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- evaluate_L3.py
- run_tests.py
- score_output_bundle.py
- main.py
- task_card.json
- evaluate.py
- evaluate_L2.py
- evaluate_L3.py
- score_output_bundle.py
- main.py
- task_card.json
- verify_ab_test_outputs.py
- main.py
- task_card.json
- __init__.py
- evaluate_segmentation.py
- main.py
- task_card.json
- score_workbook.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- run_hidden_suite.py
- main.py
- task_card.json
- score_audit_report.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- evaluate_metrics.py
- main.py
- task_card.json
- main.py
- shared.py
- task_card.json
- score_screening_memo.py
- main.py
- task_card.json
- score_onepager_output.py
- score_onepager_v2.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_research_answers.py
- main.py
- task_card.json
- score_taxform_outputs.py
- main.py
- task_card.json
- __init__.py
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_logical_error_rates.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- run_judge_wrapper.sh
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- main.py
- task_card.json
- verify_sgf.py
- main.py
- task_card.json
- score_outputs.py
- variant_specs.py
- main.py
- task_card.json
- oracle.py
- verify_outputs.py
- main.py
- task_card.json
- verify_k8s_migration.py
- main.py
- task_card.json
- score_root_cause_analysis.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- main.py
- task_card.json
- score_os_log_permissions.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_particle_filter_outputs.py
- main.py
- task_card.json
- main.py
- task_card.json
- prepare_workspace.py
- verify_safe_recover.py
- main.py
- task_card.json
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- main.py
- task_card.json
- __init__.py
- main.py
- task_card.json
- main.py
- task_card.json
- main.py
- task_card.json
- main.py
- task_card.json
- main.py
- task_card.json
- main.py
- task_card.json
- main.py
- task_card.json
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- evaluate_submission.py
- main.py
- task_card.json
- bundle_lib.py
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- __init__.py
- detect_floors.py
- render_human_views.py
- score_outputs.py
- main.py
- task_card.json
- detect_floors.py
- render_human_views.py
- score_outputs.py
- main.py
- task_card.json
- score_submission_urdf.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- eval.py
- main.py
- task_card.json
- verify_alignment.py
- main.py
- task_card.json
- main.py
- task_card.json
- check_collision.py
- generate_ref_stls.py
- setup_test_dirs.py
- simulate_agent.py
- verify_stl.py
- main.py
- task_card.json
- score_humanoid_velocity_policy.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- verify_process.py
- verify_results.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- verify_submission.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- verify_reliability_indices.py
- main.py
- task_card.json
- extract_scene_metrics.py
- main.py
- task_card.json
- verify_sanding_scores.py
- main.py
- task_card.json
- verify_submission.py
- main.py
- task_card.json
- __init__.py
- score_outputs.py
- main.py
- task_card.json
- main.py
- task_card.json
- score_crf_sdtm_mapping.py
- test_score_crf_sdtm_mapping.py
- main.py
- task_card.json
- score_crf_sdtm_mapping.py
- main.py
- task_card.json
- main.py
- task_card.json
- score_predictions.py
- main.py
- task_card.json
- score_predictions.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- test_score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- verify_hidden_smoke.py
- main.py
- task_card.json
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- evaluate.py
- replay.m
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- score_hidden_summary.py
- main.py
- task_card.json
- main.py
- task_card.json
- __init__.py
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- __init__.py
- verify_submission.py
- main.py
- task_card.json
- verify_submission.py
- main.py
- task_card.json
- eval.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- verify_output.py
- main.py
- task_card.json
- score_merfish.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- score_output.py
- main.py
- task_card.json
- score_spatial_domains.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- eval.py
- main.py
- task_card.json
- score_svg.py
- main.py
- task_card.json
- EVALUATOR_DATA.md
- main.py
- scoring.py
- task_card.json
- score_colonies.py
- main.py
- task_card.json
- score_zdock_interface.py
- main.py
- task_card.json
- __init__.py
- verify_outputs.py
- main.py
- task_card.json
- main.py
- task_card.json
- __init__.py
- __init__.py
- _common.py
- __init__.py
- score_outputs.py
- main.py
- task_card.json
- verify_climate.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- verify_submission.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- verify_smiles.py
- main.py
- task_card.json
- verify_submission.py
- main.py
- task_card.json
- score_molecular_structure_plausibility.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- verify.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- __init__.py
- __init__.py
- neuro_common.py
- neuro_runtime.py
- __init__.py
- main.py
- task_card.json
- score_annotation_workbook.py
- main.py
- task_card.json
- verify_outputs.py
- main.py
- task_card.json
- __init__.py
- score_outputs.py
- main.py
- task_card.json
- __init__.py
- score_outputs.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- evaluate_submission_safe.py
- main.py
- task_card.json
- __init__.py
- __init__.py
- evaluation.py
- remote_score.py
- main.py
- task_card.json
- blender_eval_submission.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- local_soft_eval.py
- remote_hard_eval.py
- _shared_eval.py
- main.py
- task_card.json
- score_outputs.py
- main.py
- task_card.json
- render_parts_dataset.py
- run_lowpoly_evaluation.py
- main.py
- task_card.json
- variant_catalog.json
- main.py
- task_card.json
- main.py
- task_card.json
- main.py
- task_card.json
- main.py
- task_card.json
- blender_render_object_views.py
- local_soft_eval.py
- remote_hard_eval.py
- main.py
- task_card.json
- variant_catalog.json
- __init__.py
- score_audio_remote.py
- main.py
- task_card.json
- build_camera_sequences.py
- local_render_eval.py
- render_candidate_views.ps1
- runtime_executor.py
- runtime_init_unreal.py
- main.py
- task_card.json
- variant_catalog.json
- blender_render_submission.py
- local_soft_eval.py
- remote_render_eval.py
- _shared_eval.py
- main.py
- task_card.json
- blender_render_material_views.py
- blender_render_multipart_material_views.py
- local_soft_eval.py
- remote_hard_eval.py
- main.py
- task_card.json
- evaluate_storyboard.py
- main.py
- task_card.json
- __init__.py
- common_config.py
- common_setup.py
- linux_runtime.py
- published_tasks.json
- pyproject.toml
- test_agent_loop_logging.py
- test_analyze_image_tool.py
- test_cache_policy.py
- test_canonical_format.py
- test_coordinate_scaling.py
- test_exec_tool.py
- test_fs_backends.py
- test_fs_tools.py
- test_image_retention.py
- test_image_retention_modes.py
- test_image_sanitization.py
- test_message_ordering.py
- test_model_config.py
- test_openclaw_compaction.py
- test_openclaw_context.py
- test_openclaw_memory_flush.py
- test_openclaw_memory_store.py
- test_openclaw_memory_tools.py
- test_openclaw_replay.py
- test_openclaw_session.py
- test_openclaw_tools.py
- test_openclaw_transcript_format.py
- test_post_compaction_context.py
- test_prompt_builder.py
- test_sanitize_items.py
- test_subagent_tools.py
- test_ale_claw_cost_accounting.py
- test_auto_resume.py
- test_baked_in_sandbox.py
- test_claude_code_telemetry.py
- test_codex_telemetry.py
- test_executor_secrets.py
- test_grok_build.py
- test_grok_build_telemetry.py
- test_kimi_code.py
- test_kimi_code_telemetry.py
- test_openclaw_cli.py
- test_openclaw_cli_completion.py
- test_qemu_provider.py
- test_task_driver_detached.py
- test_cfr_game_theory_equilibrium.py
- test_clustered_cyclic_code_circuit_level_simulation.py
- test_digital_marketing_ab_test_verifier.py
- test_grader_failure_handling.py
- test_mpc_control_building.py
- test_pcb_layout_kicad_evaluator.py
- test_rgi_mcr1_colistin_v2.py
- test_scene2_resample_verifier.py
- test_wgs_variant_calling.py
- conftest.py
- test_range_cmd.py
- test_sse_read.py
- test_tail_reconcile.py
- .dockerignore
- .gitignore
- .gitmodules
- AGENTS.md
- example_exp.yaml
- LICENSE
- LICENSE-DATA
- pyproject.toml
- README.md
# 설치 가이드
1. 코드 내려받기
git clone https://github.com/rdi-berkeley/agents-last-exam
깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.
cd agents-last-exam
방금 내려받은 프로젝트 폴더 안으로 이동합니다.
2. Docker
쉬움 추천사전 준비물
- Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
- Docker Desktop 컨테이너를 빌드하고 실행하려면 필요합니다. 설치 후 실행해서 백그라운드에 켜두세요.
⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.
docker build -f ale_run/environments/images/ale_kasm/Dockerfile -t agents-last-exam .
Dockerfile을 기반으로 실행 가능한 이미지를 빌드합니다.
docker run -p 8080:80 agents-last-exam
빌드된 이미지를 실제 컨테이너로 실행합니다.
터미널에 docker compose ps 를 입력해 컨테이너들이 Up 상태인지 확인하세요. README에 포트 번호가 적혀있다면 브라우저에서 http://localhost:포트번호 로 접속해보세요.
3. Node.js
쉬움사전 준비물
⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.
cd ale_run/agents/_assets/cua_mcp_server
이 프로젝트의 관련 파일이 하위 폴더 안에 있어서, 먼저 그 폴더로 이동합니다.
npm install
package.json에 명시된 라이브러리들을 내려받아 설치합니다.
npm start
개발/실행 서버를 켭니다.
명령어 실행 후 터미널에 나타나는 주소(보통 http://localhost:3000 형태)를 브라우저에서 열어보세요.
4. Python
쉬움사전 준비물
⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.
pip install .
PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.
python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요
파이썬 스크립트(또는 모듈)를 실행합니다.
에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.
// repository documentation
Was this content helpful?
(0 ratings)
