Skip to content
Hot eventDeveloping

Open-source agentest grades AI agents from OpenTelemetry traces offline

1 reports1 reporting sourcesUpdated 5 h ago

Start here

AI digest

AiEnsured CTO Srinivas Padmanabhuni released agentest, an open-source tool that evaluates AI agents by reading their existing OpenTelemetry GenAI traces rather than re-running them. It applies 165 tests to what the agent actually did, flagging behaviors such as claiming unearned success, acting before verifying, following a hidden instruction, calling a disallowed tool or leaking personal data. The tool runs offline with no API key, network or LLM judge, so the same traces always produce the same pass, fail or n/a verdicts, according to the release. It works with any framework that records OpenTelemetry GenAI traces and ships native-log importers for LangGraph, OpenAI Agents SDK, AutoGen, smolagents and n8n. It installs via pip install agentest-ai (version 3.5.0) and offers a --strict CI gate with JUnit, SARIF, JSON, HTML, Markdown and CSV output. A browser report card and Colab demo allow use without installation.

Generated from reports · updated 5 h ago

Report timeline

Follow the reports to see the event from different sides.

November 19
  1. Hacker News · AI
    Agentest launches as an offline test suite that grades AI agents from OpenTelemetry traces

    AiEnsured CTO Srinivas Padmanabhuni released agentest, an open-source tool that reads an agent's existing OpenTelemetry GenAI traces and runs 165 tests on what the agent actually did, such as claiming success it did not earn, acting before verifying, following a hidden instruction, calling a disallowed tool or leaking personal data. It runs offline with no API key, network or LLM judge, so the same traces always produce the same pass, fail or n/a verdicts, and it ships native-log importers for LangGraph, OpenAI Agents SDK, AutoGen, smolagents and n8n. Installable via pip install agentest-ai (version 3.5.0), it offers a --strict CI gate with JUnit, SARIF, JSON, HTML, Markdown and CSV output, plus a no-install browser report card and Colab demo.

Heat for this event

Current, comparable range
9
Peak, comparable range
10November 19 23:00
Change in 24 hours
–

The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.