Back to browse
Ito – Code reviews that run code

Ito – Code reviews that run code

by evanmarshall·Jun 16, 2026·10 points·6 comments

AI Analysis

●●SolidSlickSolve My Problem

Runs actual code in sandboxes instead of static analysis or URL-clicking agents.

Strengths
  • Devcontainer sandboxes wire up full application environment for realistic testing
  • Scriptless setup maps application logic without manual test configuration
  • Provides screenshots, videos, and run logs as runtime evidence of bugs
Weaknesses
  • Agentic QA category becoming crowded with similar funded competitors
  • Requires providing credentials for authenticated flows - security concerns for some teams
Target Audience

Engineering teams, QA leads, senior developers

Similar To

Cursor bugbot · Greptile · Coderabbit

Post Description

I'm Evan and I made Ito.ai

It's code review that actually runs your code. The result is that it finds more bugs with a smaller false positive rate. You get screenshots, videos, and run logs. I built Ito because manual verification sucks and I thought I could automate it. I've been a professional developer for 15 years and now more than ever, I'm just spending time making sure things work.

I looked into all of the other agentic testing tools that click around a url you give them and frankly, they sucked. They just didn't work. I figured to be able to actually testing things you need to run the full environment so you can seed data, bypass gates, mock external dependencies. They also can't get runtime evidence about changes that aren't frontend. Ito does.

Under the hood, Ito is creating a devcontainer for your application. All of your services are wired up and then a team of agents goes and tests your PR. We rolled out our own sandboxes and our own agentic coding loops.

I built Ito to be another useful signal in development. It shouldn't annoy you when it's not perfect and it saves you a bunch of time testing.

A few open source examples:

- n8n https://app.ito.ai/share/bb7d73aa-fd08-482d-9938-87938e2a232...

- lobehub https://app.ito.ai/share/1d76f15a-9998-4154-85b4-b177924cba8...

- excalidraw https://app.ito.ai/share/d1cb1475-fbe5-4c71-901b-409ba2aa6d6...

Similar Projects

Security●●●Banger

OpenClaw skills degrade agent safety

Behavioral safety testing reveals 45 regressions static analysis misses—guardrails provided.

Big BrainWizardryZero to One
shadab_nazar
123mo ago