.dockerignore
.env.keys.example
.gitignore
AGENTS.md
CLAUDE.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
Dockerfile
INSTALL.md
LICENSE
Makefile
NOTICE
README.md
ROADMAP.md
THIRD_PARTY
architecture-diagram.drawio
buildspec-deploy.yml
buildspec.yml
deploy.sh
destroy.sh
manage-users.sh
package-lock.json
package.json
pyproject.toml
uv.lock
.claude/skills/ship-it/SKILL.md
.github/workflows/publish.yml
backend/__init__.py
backend/api/__init__.py
backend/api/compare.py
backend/api/main.py
backend/api/optimizations.py
backend/core/__init__.py
backend/core/agent.py
backend/core/bedrock_pricing.json
backend/core/chat.py
backend/core/database.py
backend/core/inspect_viewer.py
backend/core/judge_prompt_builder.py
backend/core/judge_tools.py
backend/core/jury_scoring.py
backend/core/mcp_client.py
backend/judge_prompts/reference_comparison.md
buildspec-scripts/deploy.sh
buildspec-scripts/destroy-data.sh
buildspec-scripts/destroy.sh
design/agentcore-architecture.md
docker/backend.Dockerfile
docker/frontend.Dockerfile
docs/DEVELOPMENT.md
docs/SELF_HOSTING.md
docs/evaluation-platform-onepager.md
docs/image.png
eval_mcp/INSTALL.md
eval_mcp/__init__.py
eval_mcp/__main__.py
eval_mcp/_agent_launcher.py
eval_mcp/agent_detect.py
eval_mcp/bedrock_capture.py
eval_mcp/canary.py
eval_mcp/cli.py
eval_mcp/config.py
eval_mcp/judge_config.py
eval_mcp/otlp_receiver.py
eval_mcp/pricing.py
eval_mcp/provider_pricing.json
eval_mcp/s3_sync.py
eval_mcp/server.py
eval_mcp/storage.py
eval_mcp/subprocess_runner.py
eval_mcp/viewer.py
eval_mcp/core/__init__.py
eval_mcp/core/bedrock_client.py
eval_mcp/core/document_chunking.py
eval_mcp/core/eval_results.py
eval_mcp/core/judge_config.py
eval_mcp/core/logging_utils.py
eval_mcp/core/pdf_report.py
eval_mcp/core/pipeline_stages.py
eval_mcp/core/pricing.py
eval_mcp/core/provider_pricing.json
eval_mcp/core/s3_client.py
eval_mcp/core/user_storage.py
eval_mcp/installers/__init__.py
eval_mcp/installers/_json_merge.py
eval_mcp/installers/_toml_merge.py
eval_mcp/installers/base.py
eval_mcp/installers/claude_code.py
eval_mcp/installers/codex.py
eval_mcp/installers/cursor.py
eval_mcp/installers/detect.py
eval_mcp/installers/kiro.py
eval_mcp/installers/vscode.py
eval_mcp/tools/__init__.py
eval_mcp/tools/agent.py
eval_mcp/tools/analyze_agent_image.py
eval_mcp/tools/analyze_agent_path.py
eval_mcp/tools/analyze_dataset.py
eval_mcp/tools/bedrock_models.py
eval_mcp/tools/create_agent_eval_config.py
eval_mcp/tools/create_config.py
eval_mcp/tools/create_pipeline_eval_config.py
eval_mcp/tools/external_providers.py
eval_mcp/tools/generate_judge.py
eval_mcp/tools/generate_qa.py
eval_mcp/tools/generate_report.py
eval_mcp/tools/get_evaluation_details.py
eval_mcp/tools/get_optimization_details.py
eval_mcp/tools/list_datasets.py
eval_mcp/tools/list_eval_configs.py
eval_mcp/tools/list_evaluations.py
eval_mcp/tools/list_judges.py
eval_mcp/tools/list_optimizations.py
eval_mcp/tools/optimize_prompt.py
eval_mcp/tools/run_eval.py
eval_mcp/tools/save_dataset.py
eval_mcp/viewer_static/404.html
eval_mcp/viewer_static/__next.__PAGE__.txt
eval_mcp/viewer_static/__next._full.txt
eval_mcp/viewer_static/__next._head.txt
eval_mcp/viewer_static/__next._index.txt
eval_mcp/viewer_static/__next._tree.txt
eval_mcp/viewer_static/_not-found.html
eval_mcp/viewer_static/_not-found.txt
eval_mcp/viewer_static/chat.html
eval_mcp/viewer_static/chat.txt
eval_mcp/viewer_static/data.html
eval_mcp/viewer_static/data.txt
eval_mcp/viewer_static/history.html
eval_mcp/viewer_static/history.txt
eval_mcp/viewer_static/index.html
eval_mcp/viewer_static/index.txt
eval_mcp/viewer_static/optimizations.html
eval_mcp/viewer_static/optimizations.txt
eval_mcp/viewer_static/results.html
eval_mcp/viewer_static/results.txt
eval_mcp/viewer_static/_next/static/aoQ96MhkAMWr0HWFeuVlw/_buildManifest.js
eval_mcp/viewer_static/_next/static/aoQ96MhkAMWr0HWFeuVlw/_clientMiddlewareManifest.js
eval_mcp/viewer_static/_next/static/aoQ96MhkAMWr0HWFeuVlw/_ssgManifest.js
eval_mcp/viewer_static/_next/static/chunks/000ce62-8w~jc.js
eval_mcp/viewer_static/_next/static/chunks/004~5-orepc~t.js
eval_mcp/viewer_static/_next/static/chunks/03~yq9q893hmn.js
eval_mcp/viewer_static/_next/static/chunks/06pe-8hdrilbo.js
eval_mcp/viewer_static/_next/static/chunks/0_i._.xrvczva.js
eval_mcp/viewer_static/_next/static/chunks/0focprf_lnj6v.js
eval_mcp/viewer_static/_next/static/chunks/0f~jjbm_h75jz.js
eval_mcp/viewer_static/_next/static/chunks/0g~mtccp2uacq.js
eval_mcp/viewer_static/_next/static/chunks/0k492loyc8imh.js
eval_mcp/viewer_static/_next/static/chunks/0r8qmxiij0uer.js
eval_mcp/viewer_static/_next/static/chunks/0rjbzh0_.xz_w.js
eval_mcp/viewer_static/_next/static/chunks/0uz71x3mgy~vh.js
eval_mcp/viewer_static/_next/static/chunks/0wuw6-bd8b87f.css
eval_mcp/viewer_static/_next/static/chunks/14k2l__1oqybo.js
eval_mcp/viewer_static/_next/static/chunks/17vjdk0jajkb0.js
eval_mcp/viewer_static/_next/static/chunks/turbopack-0nxelb148g7~q.js
eval_mcp/viewer_static/_next/static/media/GeistMono_Variable-s.p.17jn9btb_52pq.woff2
eval_mcp/viewer_static/_next/static/media/Geist_Variable-s.p.0-te~ja_gpvcf.woff2
eval_mcp/viewer_static/_next/static/media/InstrumentSerif_Italic-s.p.0ercad8pami3_.woff2
eval_mcp/viewer_static/_next/static/media/InstrumentSerif_Regular-s.p.17mszrlkn-yu..woff2
eval_mcp/viewer_static/_not-found/__next._full.txt
eval_mcp/viewer_static/_not-found/__next._head.txt
eval_mcp/viewer_static/_not-found/__next._index.txt
eval_mcp/viewer_static/_not-found/__next._not-found.__PAGE__.txt
eval_mcp/viewer_static/_not-found/__next._not-found.txt
eval_mcp/viewer_static/_not-found/__next._tree.txt
eval_mcp/viewer_static/api/health
eval_mcp/viewer_static/chat/__next._full.txt
eval_mcp/viewer_static/chat/__next._head.txt
eval_mcp/viewer_static/chat/__next._index.txt
eval_mcp/viewer_static/chat/__next._tree.txt
eval_mcp/viewer_static/chat/__next.chat.__PAGE__.txt
eval_mcp/viewer_static/chat/__next.chat.txt
eval_mcp/viewer_static/data/__next._full.txt
eval_mcp/viewer_static/data/__next._head.txt
eval_mcp/viewer_static/data/__next._index.txt
eval_mcp/viewer_static/data/__next._tree.txt
eval_mcp/viewer_static/data/__next.data.__PAGE__.txt
eval_mcp/viewer_static/data/__next.data.txt
eval_mcp/viewer_static/history/__next._full.txt
eval_mcp/viewer_static/history/__next._head.txt
eval_mcp/viewer_static/history/__next._index.txt
eval_mcp/viewer_static/history/__next._tree.txt
eval_mcp/viewer_static/history/__next.history.__PAGE__.txt
eval_mcp/viewer_static/history/__next.history.txt
eval_mcp/viewer_static/optimizations/__next._full.txt
eval_mcp/viewer_static/optimizations/__next._head.txt
eval_mcp/viewer_static/optimizations/__next._index.txt
eval_mcp/viewer_static/optimizations/__next._tree.txt
eval_mcp/viewer_static/optimizations/__next.optimizations.__PAGE__.txt
eval_mcp/viewer_static/optimizations/__next.optimizations.txt
eval_mcp/viewer_static/results/__next._full.txt
eval_mcp/viewer_static/results/__next._head.txt
eval_mcp/viewer_static/results/__next._index.txt
eval_mcp/viewer_static/results/__next._tree.txt
eval_mcp/viewer_static/results/__next.results.__PAGE__.txt
eval_mcp/viewer_static/results/__next.results.txt
examples/run_all_tests.sh
examples/configs/bedrock-eval.yaml
examples/configs/demo-questions.yaml
examples/configs/healthcare_eval_full.yaml
examples/configs/promptfooconfig-simple.yaml
examples/configs/simple_config.yaml
examples/datasets/simple_healthcare_config.yaml
examples/langchain_bedrock_agent/agent.py
examples/langchain_bedrock_agent/requirements.txt
examples/local_agent/agent.py
examples/local_agent/requirements.txt
examples/local_agent/task.py
examples/strands_agent/agent-as-tools.ipynb
examples/strands_agent/agent.py
examples/strands_agent/requirements.txt
examples/test_agent/Dockerfile
examples/test_agent/agent.py
examples/test_agent/compose.yaml
examples/test_agent/task.py
frontend/.gitignore
frontend/next-env.d.ts
frontend/next.config.ts
frontend/package-lock.json
frontend/package.json
frontend/postcss.config.mjs
frontend/tailwind.config.ts
frontend/tsconfig.json
frontend/app/globals.css
frontend/app/layout.tsx
frontend/app/page.tsx
frontend/app/providers.tsx
frontend/app/api/health/route.ts
frontend/app/chat/page.tsx
frontend/app/data/page.tsx
frontend/app/fonts/Geist-Variable.woff2
frontend/app/fonts/GeistMono-Variable.woff2
frontend/app/fonts/InstrumentSerif-Italic.woff2
frontend/app/fonts/InstrumentSerif-Regular.woff2
frontend/app/fonts/OFL.txt
frontend/app/fonts/SHA256SUMS
frontend/app/history/page.tsx
frontend/app/optimizations/page.tsx
frontend/app/results/page.tsx
frontend/components/ChatInterface.tsx
frontend/components/Header.tsx
frontend/components/MessageInput.tsx
frontend/components/MessageList.tsx
frontend/components/data/DatasetDetail.tsx
frontend/components/data/DatasetList.tsx
frontend/components/data/DocumentsView.tsx
frontend/components/data/JudgesView.tsx
frontend/components/data/SubToggle.tsx
frontend/components/optimizations/OptimizationDetail.tsx
frontend/components/optimizations/OptimizationRail.tsx
frontend/components/results/AggregateMetrics.tsx
frontend/components/results/ComparisonGrid.tsx
frontend/components/results/ComparisonView.tsx
frontend/components/results/ResultsHeader.tsx
frontend/components/results/RunRail.tsx
frontend/components/results/SampleDetailPanel.tsx
frontend/contexts/AuthContext.tsx
frontend/contexts/ChatContext.tsx
frontend/lib/data-api.ts
frontend/lib/data-types.ts
helm/eval/Chart.lock
helm/eval/Chart.yaml
helm/eval/values-aws.yaml
helm/eval/values.yaml
helm/eval/charts/oauth2-proxy-7.18.0.tgz
helm/eval/templates/deployment.yaml
helm/eval/templates/hpa.yaml
helm/eval/templates/pdb.yaml
helm/eval/templates/pvc.yaml
helm/eval/templates/rbac.yaml
helm/eval/templates/service.yaml
helm/external-secrets-config/Chart.yaml
helm/external-secrets-config/values.yaml
helm/external-secrets-config/templates/external-secrets.yaml
helm/external-secrets-config/templates/secret-store.yaml
infra/.gitignore
infra/.terraform.lock.hcl
infra/terraform.tfvars.example
infra/data/.terraform.lock.hcl
infra/data/main.tf
infra/data/outputs.tf
infra/data/rds.tf
infra/data/storage.tf
infra/data/variables.tf
infra/data/vpc.tf
infra/modules/eval-logs-bucket/.terraform.lock.hcl
infra/modules/eval-logs-bucket/main.tf
infra/modules/eval-logs-bucket/outputs.tf
infra/modules/eval-logs-bucket/variables.tf
infra/platform/.terraform.lock.hcl
infra/platform/alb.tf
infra/platform/cicd.tf
infra/platform/cloudfront.tf
infra/platform/cognito.tf
infra/platform/eks.tf
infra/platform/kubernetes.tf
infra/platform/main.tf
infra/platform/outputs.tf
infra/platform/sandbox-security.tf
infra/platform/storage.tf
infra/platform/variables.tf
llm_evaluation_system.egg-info/PKG-INFO
llm_evaluation_system.egg-info/SOURCES.txt
llm_evaluation_system.egg-info/dependency_links.txt
llm_evaluation_system.egg-info/entry_points.txt
llm_evaluation_system.egg-info/requires.txt
llm_evaluation_system.egg-info/top_level.txt
local/Dockerfile.frontend
local/Dockerfile.python
local/README.md
local/compose.yaml
local/entrypoint.py
local/nginx-compose.conf
scripts/populate-pricing.py
scripts/verify_optimizer_improves.py
tests/test_agent_cancel_recovery.py
tests/test_agent_cancellation_timing.py
tests/test_agent_detect.py
tests/test_bedrock_capture_adapter.py
tests/test_bedrock_models.py
tests/test_canary.py
tests/test_chat_cancel_eks.py
tests/test_data_api.py
tests/test_generate_judge_iter.py
tests/test_http_server.py
tests/test_install_claude_code.py
tests/test_install_codex.py
tests/test_install_cursor.py
tests/test_install_dispatcher.py
tests/test_install_json_merge.py
tests/test_install_kiro.py
tests/test_install_toml_merge.py
tests/test_install_vscode.py
tests/test_langchain_subprocess_e2e.py
tests/test_mcp_eval.py
tests/test_mcp_schema.py
tests/test_model_usage_dedupe.py
tests/test_optimize_prompt.py
tests/test_otlp_receiver.py
tests/test_qa_allocation.py
tests/test_raw_otel_persistence.py
tests/test_run_eval_fail_loud.py
tests/test_subprocess_mode_wiring.py
tests/test_subprocess_otlp_integration.py
tests/test_subprocess_runner.py
tests/mcp_eval/__init__.py
tests/mcp_eval/questions.xml
tests/mcp_eval/runner.py