{"categories":[{"label":"Monitoring","url":"https://skillfed.io/packages/category/system-monitoring/3"}],"enrichment":{"capability":"AgentOps provides observability and monitoring for AI agents, capturing execution traces, LLM costs, and session replays with minimal code integration.","skillfed_tags":["ai-agent-observability","llm-monitoring","opentelemetry-based"],"use_cases":["Debug multi-step agent workflows by replaying execution traces and inspecting LLM calls step-by-step.","Track and optimize LLM costs across different foundation model providers in production agent systems.","Monitor CrewAI or AG2 agents with automatic telemetry by setting AGENTOPS_API_KEY and calling init().","Instrument custom agent code with decorators to capture operation boundaries and exception handling.","Self-host the AgentOps dashboard and API backend on your own cloud for air-gapped or compliance-sensitive deployments."],"what_it_does":"AgentOps is an observability platform designed to instrument AI agent applications with minimal code overhead. It captures execution traces, LLM API calls, costs, and errors, then replays them in a web dashboard for debugging and analysis. The package provides decorators (@session, @agent, @operation, @task, @workflow) to mark code boundaries and automatically record inputs, outputs, and exceptions. It integrates natively with popular agent frameworks (CrewAI, AG2, LangGraph, Camel, Langchain, Cohere, OpenAI Agents SDK) and can be self-hosted on your own infrastructure.\n\nThe core use case is reducing the time to debug and optimize AI agents by providing step-by-step execution graphs, LLM spend tracking across foundation model providers, and session replay. It depends on OpenTelemetry for instrumentation, httpx and requests for HTTP communication, and pyyaml for configuration. The package supports Python 3.9 through 3.13 and has no known security vulnerabilities.","worth_installing":"Yes. AgentOps is actively maintained, has no security vulnerabilities, and installs with low friction. The MIT license poses no restrictions. Install it if you are building or debugging AI agents and want production observability without writing custom instrumentation\u2014the decorator-based API is lightweight and the framework integrations are well-established. Skip it only if you have no need for agent monitoring or prefer a fully offline debugging workflow."},"id":"agentops","links":{"html":"https://skillfed.io/packages/agentops","md":"https://skillfed.io/packages/agentops.md","pypi":"https://pypi.org/project/agentops/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2025-08-29","license_spdx":null,"license_treatment":"permissive","name":"agentops","python_support":"supports_current","summary":"Observability and DevTool Platform for AI Agents"},"popularity":{"monthly_downloads":299803,"position":7851,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"0.4.21"}