{"id":"apple-coremltools","name":"coremltools","homepage":"https://coremltools.readme.io","repo_url":"https://github.com/apple/coremltools","category":"ai-ml","subcategories":[],"tags":["ai-ml","model-conversion","coreml","python","pytorch","tensorflow","xgboost","scikit-learn","libsvm"],"what_it_does":"coremltools is a Python library that converts and manipulates machine-learning models into Apple Core ML format, including reading/writing/optimizing Core ML models and (on macOS) verifying conversions via prediction.","use_cases":["Convert trained TensorFlow/PyTorch/scikit-learn/XGBoost/LibSVM models to Core ML for deployment in Apple apps","Inspect and optimize Core ML models (format/model tooling)","Validate model conversion by running predictions using Core ML (macOS)"],"not_for":["Serving models over a network (it is not an online inference API)","Training or fine-tuning models on the server side","Mobile/off-device conversion without an Apple/Core ML toolchain"],"best_when":"You need to package existing ML models into Core ML for on-device inference in iOS/macOS apps, using a Python conversion pipeline.","avoid_when":"You require a standalone REST/GraphQL/SDK web service interface, or you need an HTTP-authenticated API for remote inference.","alternatives":["Apple MLModel tools (Core ML model tooling via Xcode)","ONNX Runtime + ONNX tooling for cross-platform deployment","Vendor-specific conversion pipelines to other runtimes (e.g., TensorFlow Lite tools, TFLite/Android tooling)","Other model conversion frameworks (e.g., ONNX-based conversion chains)"],"af_score":53.8,"security_score":54.5,"reliability_score":41.2,"package_type":"skill","discovery_source":["openclaw"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-29T14:58:32.892466+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":false,"mcp_server_url":null,"has_sdk":true,"sdk_languages":["Python"],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["None (local/offline Python library usage)"],"oauth":false,"scopes":false,"notes":"No network API/auth described; typical usage is local conversion tooling in a developer environment."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Open-source Python package (no pricing information in provided data)."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":53.8,"security_score":54.5,"reliability_score":41.2,"mcp_server_quality":0.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":100.0,"rate_limit_clarity":0.0,"tls_enforcement":50.0,"auth_strength":100.0,"scope_granularity":0.0,"dependency_hygiene":50.0,"secret_handling":60.0,"security_notes":"No network transport or auth is implied by the provided content (reduces risk of credential exposure). However, as with any Python conversion tool, security depends on the integrity of installed dependencies and the safety of processing untrusted model artifacts (not covered in provided data).","uptime_documented":0.0,"version_stability":65.0,"breaking_changes_history":55.0,"error_recovery":45.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["This is a local Python conversion library rather than a network service; agent integration relies on correct Python environments and supported model formats/framework versions.","Conversion behavior can depend on platform/toolchain and model specifics; agents should validate outputs rather than assume universal conversion success.","No API-rate-limit or HTTP error-code semantics apply (tooling errors are library/exception-based)."]}}