sentry-setup-ai-monitoring

Configure Sentry tracing for LLM calls and agent executions.

Updated Mar 5, 2026
One-click install
npx skills add https://github.com/Himanshu040604/codex-skills-setup --skill sentry-setup-ai-monitoring-himanshu040604
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sentry-setup-ai-monitoring
Source: https://github.com/Himanshu040604/codex-skills-setup/tree/main/assets/codex/skills/claude-import/skills/plugins/sentry%40claude-plugins-official/skills/sentry-setup-ai-monitoring
Command: npx skills add https://github.com/Himanshu040604/codex-skills-setup --skill sentry-setup-ai-monitoring-himanshu040604

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill simplifies the process of setting up Sentry for AI monitoring, allowing you to track LLM calls, agent executions, and token consumption within your projects.

Core Features & Use Cases

  • Automated SDK Detection: Automatically identifies installed AI SDKs (OpenAI, Anthropic, LangChain, etc.) to configure appropriate integrations.
  • AI Observability: Provides insights into LLM usage, latency, and costs.
  • Use Case: When a user asks to "monitor LLM calls" or "track AI agent performance," this skill guides them through configuring Sentry to capture and analyze these interactions.

Quick Start

Use the sentry-setup-ai-monitoring skill to set up AI monitoring for your project.

Frequently Asked Questions about sentry-setup-ai-monitoring

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up Sentry for LLM observability and AI agent monitoring?

Sentry AI monitoring setup involves detecting installed AI SDKs like OpenAI or LangChain and configuring tracing to capture LLM calls, agent executions, and token consumption. This skill automates SDK detection and integration configuration for Python and JavaScript environments.

Can I monitor LLM calls and token usage in both Python and JavaScript projects?

Yes, LLM call monitoring supports both Python and JavaScript environments. The setup detects installed SDKs and configures integrations for OpenAI, Anthropic, LangChain, Google GenAI, and Vercel AI SDK to trace AI interactions and token consumption across these languages.

What AI SDKs are supported for tracing agent executions and tool usage?

Supported AI SDKs for tracing agent executions and tool usage include OpenAI, Anthropic, LangChain, Google GenAI, and Vercel AI SDK. The setup automatically identifies installed SDKs to configure the appropriate Sentry integrations.

How does Sentry AI monitoring track token consumption and latency?

Sentry AI monitoring tracks token consumption and latency by configuring tracing for LLM calls and agent executions. It provides observability into AI interactions by identifying installed SDKs and setting up integrations to capture usage metrics.

Do I need to manually configure Sentry integrations for each AI SDK I use?

No, manual configuration is not required for each AI SDK. The setup automatically detects installed AI SDKs like OpenAI, Anthropic, and LangChain, then applies the appropriate Sentry integrations to monitor LLM calls and agent executions.

What is the best way to track AI agent performance and LLM call latency in Sentry?

The best way to track AI agent performance is configuring Sentry with automated SDK detection for OpenAI, Anthropic, LangChain, Google GenAI, or Vercel AI SDK. This enables tracing for agent executions, LLM calls, and token consumption to provide latency and usage insights.