Tag: llm-observability
Agent Execution Tracing CLI
A local development tool for recording and inspecting agent execution snapshots, including LLM calls, tool usage, and context engine data. It provides a CLI to analyse traces, messages, and user memory for debugging agentic workflows.
Iris MCP Server for Agent Evaluation
An MCP server for evaluating AI agent outputs for quality, safety, and cost using deterministic rules. It enables PII detection, trace logging, and execution cost monitoring without the need for LLM-as-judge.
Opik Python SDK Patterns
Provides architectural patterns and implementation strategies for the Opik Python SDK, covering async tracing, integration techniques, and efficient message batching.
Langfuse LLM Observability Debugging Skill
This skill enables agents to debug LLM applications using Langfuse observability. It provides structured playbooks for investigating traces, exceptions, and latency, alongside managing prompts and datasets.