Arize Ai Provider Integration

This handles CRUD operations for LLM provider credentials in Arize AI, so evaluators and other features can call models on your behalf without you hardcoding keys everywhere. It wraps the `ax ai-integrations` CLI and supports the usual suspects: OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM, plus custom OpenAI-compatible endpoints. The integrations are account-scoped, not workspace-scoped, which is worth knowing upfront. You'll want this when setting up judge models for evals or connecting any LLM provider to Arize. The skill is thorough about listing existing integrations before creating new ones, which saves you from credential sprawl.

skills.sh installs: 1.1K
GitHub stars: 41K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add github/awesome-copilot --skill arize-ai-provider-integration --agent claude-code

Installs into .claude/skills of the current project.

Files

Arize AI Integration Skill

SPACE — Most --space flags and the ARIZE_SPACE env var accept a space name (e.g., my-workspace) or a base64 space ID (e.g., U3BhY2U6...). Find yours with ax spaces list. Note: ai-integrations create does not accept --space — AI integrations are account-scoped. Use --space only with list, get, update, and delete.

Concepts

AI Integration = stored LLM provider credentials registered in Arize; used by evaluators to call a judge model and by other Arize features that need to invoke an LLM on your behalf
Provider = the LLM service backing the integration (e.g., openAI, anthropic, awsBedrock)
Integration ID = a base64-encoded global identifier for an integration (e.g., TGxtSW50ZWdyYXRpb246MTI6YUJjRA==); required for evaluator creation and other downstream operations
Scoping = visibility rules controlling which spaces or users can use an integration
Auth type = how Arize authenticates with the provider: default (provider API key), proxy_with_headers (proxy via custom headers), or bearer_token (bearer token auth)