agentops
Observability and DevTool Platform for AI Agents
Decision gist · record as of 2026-08-14
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—the 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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires an API key from the AgentOps dashboard (https://app.agentops.ai/settings/projects) to send telemetry; local-only usage without an API key is not supported by the basic integration.
- Low friction installation with a pure Python wheel.
- Actively maintained with recent releases; last commit 2026-06-25 and 5775 GitHub stars indicate ongoing development and community adoption.
License · maintenance · safety
permissive license (permissive) — MIT license (permissive) means you can use, modify, and distribute this package freely in commercial and private projects with minimal restrictions.
last release 2025-08-29 (350 days) · last repo commit 2026-06-25 · 5,775 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 299,803 downloads/mo, #7,851 on PyPI
Alternatives
Verify before relying
pip install agentops
import agentops
agentops.init("<YOUR_API_KEY>")
# ... your agent code ...
agentops.end_session('Success')- Whether the package can operate in offline mode or with a self-hosted backend without requiring the cloud API key
- Performance overhead of instrumentation on agent execution speed and latency
- Data retention and privacy policies for telemetry sent to AgentOps servers
What it is and 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.
The 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.
Use it for
- 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.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
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—the 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.
Install
agentops on PyPI
Before you install
Low friction installation with a pure Python wheel. Actively maintained with recent releases; last commit 2026-06-25 and 5775 GitHub stars indicate ongoing development and community adoption.
Requires an API key from the AgentOps dashboard (https://app.agentops.ai/settings/projects) to send telemetry; local-only usage without an API key is not supported by the basic integration.
License in practice
MIT license (permissive) means you can use, modify, and distribute this package freely in commercial and private projects with minimal restrictions.
Quickstart
pip install agentops
import agentops
agentops.init("<YOUR_API_KEY>")
# ... your agent code ...
agentops.end_session('Success')Verify before relying
- Whether the package can operate in offline mode or with a self-hosted backend without requiring the cloud API key
- Performance overhead of instrumentation on agent execution speed and latency
- Data retention and privacy policies for telemetry sent to AgentOps servers
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 14 packagesaiohttphttpxopentelemetry-apiopentelemetry-exporter-otlp-proto-httpopentelemetry-instrumentationopentelemetry-sdkopentelemetry-semantic-conventionsordered-setpackagingpsutilpyyamlrequeststermcolorwrapt |
| Maintenance | Actively maintained 350 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 299,803 / month, #7,851 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.9 |
Evidence: agentops-0.4.21-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “session replay for agents”
- agentopsAgentOps provides observability and monitoring for AI agents,…
- agent-framework-azurefunctionsHosts Microsoft Agent Framework agents on Azure Durable Functions,…
- asciinemaRecords and replays terminal sessions, saving them as timestamped…
Give your agent the search over MCP, or paste the wish link into any chat.
More Monitoring packages
Wraps any iterable to display a real-time progress bar in the terminal or Jupyter notebook, showing iteration count, elapsed time, and estimated time remaining.
Provides generated Python code for OpenTelemetry semantic conventions, enabling standardized attribute naming and constant definitions for instrumentation and telemetry collection.
Install it if you are using OpenTelemetry and want to follow semantic conventions correctly.
Provides the reference implementation of the OpenTelemetry API for collecting and exporting traces, metrics, and logs from Python applications.
Provides the abstract API and interfaces for OpenTelemetry instrumentation in Python, defining how to emit traces, metrics, and logs without tying code to a specific SDK implementation.
Exports OpenTelemetry observability data to an OpenTelemetry Collector using Protobuf-encoded messages over HTTP.
Install it if you are using OpenTelemetry in Python and need to send data to a Collector over HTTP.
Provides automatic instrumentation commands and programmatic APIs to inject distributed tracing into Python applications without code changes, detecting and instrumenting packages used by your program.
Install it if you need distributed tracing without code changes and have compatible instrumented packages in your environment.
See also clawmetry · mlflow · opentelemetry-instrumentation-openai-agents · microsoft-agents-a365-observability-core · judgeval · openlit · smolagents · opik · tokencost · opentelemetry-instrumentation-crewai