OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Evaluation & Observability

Agentops — AgentOps-AI

AgentOps is a Python SDK and open-source observability app for monitoring AI-agent sessions, reviewing executions, and tracking LLM-provider costs. Its dashboard includes session replays and step-by-step execution graphs, and the project also describes benchmarking and evaluation workflows.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agentops — AgentOps-AI — OpenViST project profile in Agent Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use AgentOps when you need to examine agent executions or track LLM costs, particularly in an application built with one of its named integrations.

Who it is for

  • Developers building or operating AI-agent applications in Python.
  • Teams using supported agent frameworks who want session-level debugging and cost visibility.

Documented uses

  • Inspect an agent run through session replay and execution graphs.
  • Track LLM-provider spend across agent sessions.
  • Add monitoring data collection to an application using a named agent framework.
  • Develop benchmarking and evaluation workflows for agent behavior.
Before you choose

Requirements & limits

The repository identifies the app as open source under the MIT license. Its quick start requires an AgentOps API key; the repository also documents a self-hosted dashboard and API backend.

  • The documented SDK setup uses Python and an API key.
  • The repository names multiple agent-framework integrations, but does not supply tested setup details for each one.
  • The project documents both a dashboard service and a self-hosting path for the full app and API backend.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Add AgentOps session analytics to a Python program

Initialize AgentOps in a Python application and make its session analytics viewable from the dashboard.

Before you start

  • Python application
  • AgentOps package installed with pip
  • AgentOps API key

Steps

  1. Install the package with the command below.

    Documented command
    pip install agentops

  2. At the beginning of the program, import agentops and call agentops.init() with your API key.

  3. At the end of the program, call agentops.end_session('Success').

  4. View the session in the AgentOps dashboard.

Expected outcome

Session analytics for LLM calls can be viewed in the AgentOps dashboard.

Guide limitations

  • The repository does not provide framework-specific configuration in this quick-start example.
  • The documented steps do not specify handling for unsuccessful or interrupted sessions.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
AgentOps-AI/agentops · Official homepage title · retained in its source language
How we review sourcesSuggest a correction