AgentEval 0.1.1-alpha

This is a prerelease version of AgentEval.
There is a newer prerelease version of this package available.
See the version list below for details.
dotnet add package AgentEval --version 0.1.1-alpha
                    
NuGet\Install-Package AgentEval -Version 0.1.1-alpha
                    
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package.
<PackageReference Include="AgentEval" Version="0.1.1-alpha" />
                    
For projects that support PackageReference, copy this XML node into the project file to reference the package.
<PackageVersion Include="AgentEval" Version="0.1.1-alpha" />
                    
Directory.Packages.props
<PackageReference Include="AgentEval" />
                    
Project file
For projects that support Central Package Management (CPM), copy this XML node into the solution Directory.Packages.props file to version the package.
paket add AgentEval --version 0.1.1-alpha
                    
#r "nuget: AgentEval, 0.1.1-alpha"
                    
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package.
#:package AgentEval@0.1.1-alpha
                    
#:package directive can be used in C# file-based apps starting in .NET 10 preview 4. Copy this into a .cs file before any lines of code to reference the package.
#addin nuget:?package=AgentEval&version=0.1.1-alpha&prerelease
                    
Install as a Cake Addin
#tool nuget:?package=AgentEval&version=0.1.1-alpha&prerelease
                    
Install as a Cake Tool

AgentEval

The first .NET-native AI agent testing, evaluation, and benchmarking framework

Features

  • 🎯 Tool Tracking - Monitor tool/function calls with timing and arguments
  • 📊 Performance Metrics - TTFT, latency, tokens, cost estimation
  • Fluent Assertions - Expressive test assertions for tools and performance
  • 🔬 RAG Metrics - Faithfulness, relevance, context precision
  • 📈 Benchmarking - Performance and agentic benchmarks
  • 🔌 Extensible - Adapter pattern for multiple agent frameworks
  • 📋 Trace-First Failure Reporting - Structured failure reports with tool timelines
  • 🔧 Testing Infrastructure - FakeChatClient for mocking LLM responses

Quick Start

using AgentEval;
using AgentEval.MAF;

// Create test harness
var harness = new MAFTestHarness(evaluatorClient);

// Run test with tool tracking
var result = await harness.RunTestAsync(agent, new TestCase
{
    Name = "Feature Planning Test",
    Input = "Plan a user authentication feature",
    EvaluationCriteria = ["Should include security considerations"]
});

// Assert tool usage
result.ToolUsage!
    .Should()
    .HaveCalledTool("SecurityTool")
        .BeforeTool("FeatureTool")
        .WithoutError()
    .And()
    .HaveNoErrors();

// Assert performance
result.Performance!
    .Should()
    .HaveTotalDurationUnder(TimeSpan.FromSeconds(10))
    .HaveEstimatedCostUnder(0.10m);

// Check failure details
if (!result.Passed && result.Failure != null)
{
    Console.WriteLine($"Failure: {result.Failure.Summary}");
    Console.WriteLine($"Tool Timeline: {result.Timeline?.TotalToolCalls} calls");
}

Test Coverage

  • 210 unit tests covering all core functionality
  • Tests for all assertions, metrics, models, and adapters
  • All tests passing ✅

Installation

dotnet add package AgentEval

Documentation

See the AgentEval Design Document for full documentation.

License

MIT License - See LICENSE file for details.

Product Compatible and additional computed target framework versions.
.NET net8.0 is compatible.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed.  net9.0 is compatible.  net9.0-android was computed.  net9.0-browser was computed.  net9.0-ios was computed.  net9.0-maccatalyst was computed.  net9.0-macos was computed.  net9.0-tvos was computed.  net9.0-windows was computed.  net10.0 is compatible.  net10.0-android was computed.  net10.0-browser was computed.  net10.0-ios was computed.  net10.0-maccatalyst was computed.  net10.0-macos was computed.  net10.0-tvos was computed.  net10.0-windows was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages

This package is not used by any NuGet packages.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last Updated
0.6.0-beta 77 3/5/2026
0.5.4-beta 76 3/3/2026
0.5.3-beta 97 3/1/2026
0.5.2-beta 72 2/28/2026
0.5.1-beta 61 2/28/2026
0.4.0-beta 81 2/22/2026
0.3.0-beta 118 1/25/2026
0.2.1-beta 62 1/24/2026
0.2.0-beta 57 1/18/2026
0.1.1-alpha 69 1/3/2026
0.1.0-alpha 58 1/3/2026