agentos-api-traces

List and retrieve AgentOS Traces API execution data via Python SDK.

4|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/ajshedivy/agno-cookbook --skill agentos-api-traces
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agentos-api-traces
Source: https://github.com/ajshedivy/agno-cookbook/tree/main/plugins/agno-agentos-api/skills/agentos-api-traces
Command: npx skills add https://github.com/ajshedivy/agno-cookbook --skill agentos-api-traces

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agno[os], and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides tools to inspect and understand the execution flow, performance, and resource usage of agents running on an AgentOS instance, enabling debugging and performance analysis.

Core Features & Use Cases

  • Trace Inspection: View detailed information about agent runs, including model calls, token usage, tool interactions, and errors.
  • Session Statistics: Aggregate performance metrics across multiple agent runs within a session.
  • Use Case: Debug a complex agent workflow by examining the trace of a failed run to pinpoint where the error occurred and why.

Quick Start

Use the agentos-api-traces skill to list the last 5 traces from your AgentOS instance running at http://localhost:7777.

Frequently Asked Questions about agentos-api-traces

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I inspect AgentOS execution traces for debugging agent runs?

Inspect AgentOS execution traces by querying the Traces API endpoints via a Python SDK, which retrieves model calls, token usage, and tool interactions to pinpoint agent run failures.

How can I view session statistics for agent workflows running on AgentOS?

View session statistics for agent workflows by aggregating performance metrics across multiple execution runs within a single session using the provided CLI script and Python SDK.

Can I list and filter traces from a local AgentOS instance?

List and filter traces from a local AgentOS instance by interacting with the Traces API, enabling custom filtering of execution data for integration testing and debugging workflows.

Do I need the agno package to retrieve trace details and execution data?

Yes, you need the agno package installed to use this Skill, as it provides the necessary Python SDK and CLI scripts to retrieve trace details and analyze agent execution data.

What is the best way to debug a failed agent workflow using execution traces?

Debug a failed agent workflow by examining its execution trace to identify model calls, token usage, and tool interactions, pinpointing exactly where the error occurred and why.

Why does my agent run fail without showing errors in the standard logs?

Agent runs may hide specific errors in standard logs, but querying the AgentOS Traces API reveals detailed execution flow and resource usage, exposing the exact tool interactions and model call failures.