Your Dashboard

Discord

Build your next agent with evals, observability, and replays

Start using AgentOps with just 2 lines of code

An in-depth exploration of the foundational elements and operational dynamics of AgentOps, highlighting its architecture and constituent components.

Seemingly magic tools that can be added to functions and classes for easier instrumenting.

Detailed breakdown of initializing AgentOps and managing sessions.

AgentOps currently supports four event types: ActionEvent, LLMEvent, ToolEvent, and ErrorEvent.

Tags are a fantastic way to organize your Sessions based on data known by the developer but not by AgentOps. Ex: `paid-user`, `v3`, `recruiter-agent`

All functions and classes exposed in the top layer of the SDK

Tracking LLM Calls using the AgentOps SDK

Use the `@track_agent()` decorator to tag your agents

Log events such as agent actions, LLM calls, tool calls, and errors. _See [Event Class](./events)_.

[CrewAI](https://crewai.io) is a framework for easily building multi-agent applications.

AgentOps provides first class support for Autogen

AgentOps provides first class support for Lanchain applications

AgentOps provides first class support for Cohere

Call the latest models using the OpenAI format including:   Llama, Mistral, Claude, Gemini, Gemma, Dall-E, Whisper

AgentOps provides first class support for MultiOn agents