whatisgithub

What is agenteval?

nishanttyagi28/agenteval — explained in plain English

Analysis updated 2026-05-18

1PythonAudience · developerComplexity · 3/5LicenseSetup · moderate

In one sentence

A CI testing framework for AI agents that scores correctness, hallucination, tool use, latency, and cost against a versioned baseline in GitHub Actions.

Mindmap

mindmap
  root((repo))
    What it does
      Runs agents against golden YAML cases
      Scores five reliability metrics
      Gates regressions in CI
    Tech stack
      Python
      GitHub Actions
      Streamlit
    Use cases
      Catch AI agent regressions
      Detect flaky agent answers
      Check tool call accuracy
    Audience
      Developers
      AI agent builders
    Setup
      Install from PyPI
      Write YAML golden cases

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Run a suite of golden test cases against an AI agent and score five reliability metrics.

USE CASE 2

Fail a GitHub Actions CI check when an agent's quality regresses from a saved baseline.

USE CASE 3

Detect flaky agents that give inconsistent answers to the same repeated prompt.

USE CASE 4

Check whether an agent called the expected tools in the expected order.

What is it built with?

PythonGitHub ActionsStreamlitYAML

How does it compare?

nishanttyagi28/agenteval0xustaz/streamgatea-bissell/unleash-lite
Stars111
LanguagePythonPythonPython
Setup difficultymoderatehardhard
Complexity3/54/54/5
Audiencedeveloperdeveloperresearcher

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires writing YAML golden test cases and wiring an adapter for the agent under test.

So what is it?

AgentEval is a testing framework built specifically for AI agents, the kind of software that uses a large language model to answer questions or carry out tasks. Where normal automated tests check that code always gives the exact same result, AI agents can behave differently each time even with the same input, so ordinary testing tools do not catch every kind of failure. AgentEval fills that gap. The tool works by running an agent against a set of golden test cases written in YAML, a simple text format for structured data. Each case describes a prompt, the expected correct answer, which tools the agent should use, and how much tolerance is allowed. AgentEval then scores the results on five measures: whether the answer is correct, whether the agent made up unsupported facts or numbers, whether it called the right tools, how fast it responded, and how much the run cost. These scores get compared against a saved baseline from an earlier run, and if quality drops too much the tool can fail a check in GitHub Actions, the automation system many software projects use to test code before it is merged. AgentEval also separates true answer failures from infrastructure problems like a provider outage or a broken evaluator, so those do not unfairly count against the agent's quality score. It includes an opt-in mode for detecting flaky behavior, meaning cases where an agent gives a different answer each time it is asked the same question, and can optionally check whether the agent took the expected sequence of steps to reach its answer, not just whether the final answer was right. Results can be viewed in a Streamlit dashboard, a web based interface for browsing data, showing pass and fail rates at both the whole suite level and for individual test cases. This tool is meant for developers building AI agents who want a repeatable way to catch regressions before shipping changes to production, similar to how automated tests are used for regular code.

Copy-paste prompts

Prompt 1
Help me write YAML golden test cases for AgentEval to evaluate my LLM agent.
Prompt 2
Set up AgentEval in GitHub Actions to gate regressions before merging.
Prompt 3
Explain the difference between agent_error, evaluator_error, and a failed correctness case in AgentEval.
Prompt 4
Show me how to use AgentEval's repeat mode to detect flaky agent answers.
Prompt 5
Help me interpret AgentEval's Streamlit dashboard results for my test suite.

Frequently asked questions

What is agenteval?

A CI testing framework for AI agents that scores correctness, hallucination, tool use, latency, and cost against a versioned baseline in GitHub Actions.

What language is agenteval written in?

Mainly Python. The stack also includes Python, GitHub Actions, Streamlit.

How hard is agenteval to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is agenteval for?

Mainly developer.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.