Kashikoi

ActiveAI-native

Simulation Engine for Benchmarking AI Products

What it does

Kashikoi is a simulation engine to benchmark AI agents. We generate CPU friendly world models that autonomously interview agents and generate deep behavioral assessments. We built a similar technology at Moveworks which was used to ship 250+ enterprise agents to customers daily.

Its site says now · captured 2026-08-23

The simulation engine for AI | Kashikoi

Kashikoi is an all in one simulation platform that allows you to build, evaluate and truly test your AI agent so you can fix bugs before your customers ever see them.

Next to it in Agent infrastructure · AI agent benchmarking and evaluation

  • BluejayY Combinator X25

    Test, monitor, and improve your voice and chat AI agents

  • CovalY Combinator S24

    Simulation & Evaluation that scales voice and chat AI agents

  • Ressl AIY Combinator W26

    Train, eval and build autonomous agents

  • RoarkY Combinator W25

    Test, monitor, and improve your voice agents

  • OpenbenchmarksY Combinator F24

    Openbenchmarks helps Agents pick the right vendors via Benchmarking

  • nao LabsY Combinator X25

    Open Source Analytics Agent

  • PrismY Combinator X25

    Deploy AI Agents with a Single API Call

  • SimY Combinator X25

    Open source platform to build AI agent workflows