AcademyMCP serversDevelopment

EvalView

Engineering teams use it to check that changes to an AI agent do not silently alter how it behaves.

  • Recommendedour rating
  • 137gitHub stars
  • Apache-2.0licence
  • 36 days agolast update
git clone https://github.com/hidai25/eval-view.git
README.md

Loading the file...

What it does

Regression testing for AI agents. You record what an agent does today as a golden baseline, then EvalView detects behavioral drift on later runs and can block regressions in CI. It is also available as an MCP server.

Use cases

  1. 01Save a baseline of your agent's current behavior
  2. 02Catch behavioral drift after a prompt or model change
  3. 03Block regressions in your CI pipeline

Questions about
EvalView.

What is EvalView used for?

Engineering teams use it to check that changes to an AI agent do not silently alter how it behaves. Regression testing for AI agents. You record what an agent does today as a golden baseline, then EvalView detects behavioral drift on later runs and can block regressions in CI. It is also available as an MCP server.

How do I install EvalView?

Run this in your terminal: git clone https://github.com/hidai25/eval-view.git

Is EvalView open source?

Yes. The code is on GitHub (hidai25/eval-view) under the Apache-2.0 licence.

Is EvalView safe to use?

It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.