RunThru

Developer Tools

Freemium

Added on Nov 11,2026

thumbnail

Description

RunThru is an AI-powered GitHub app that checks whether a pull request actually works by using the feature on a deploy preview and filming a narrated video walkthrough of it.

You comment /runthru on any pull request that has a deploy preview. An agent reads the diff, opens the preview in a real browser, clicks through the flow the change affects, then writes and voices one line of script per step. You can add direction in plain English when you want a different take.

A second model grades the finished video, so the agent that films the walkthrough never marks its own work. Before a feature doesn't work verdict is posted, another model re-checks the claim against the captured page. Every line of narration comes from a screenshot and is checked against the picture.

Key features include a single pull request comment with the video, chapters and a verdict with a QA score, timestamped issues with suggested fixes, and a judge.json file with the score, verdict and each issue that CI can read. A RunThru check can sit next to your CI and be required before merging, and the same comment updates when you comment again after a push.

It finds deploy previews from Vercel, Netlify, Render, Cloudflare Pages or any URL, and works on pull requests written by Claude Code, Cursor, Codex and Copilot. Videos can be shared through a share page or sent to Slack, and come in 16:9, 1:1 and 9:16 formats. The app never pushes code or runs your repository's code.

Pricing: the Free plan includes 5 videos a month at 720p with a RunThru end card. Pro costs $29 per month for 30 videos, then $1 per video, with 1080p60 or 4K output, no watermark, custom colours, a choice of narrator and music. Team costs $99 per month for 100 videos, then $0.90 per video. Enterprise lets you run the pipeline on your own runners with your own model keys. Prices are in USD.

It is suited to engineering teams, code reviewers, product managers and designers who want to see a feature working before merging, especially when coding agents open pull requests faster than people can check them.

By the PowerfulAI.tools Editorial Team · Updated 11 November 2026 · Researched with AI assistance and checked against the official RunThru website · How we review tools

RunThru Key Features

  • Comment /runthru on a GitHub pull request to film a narrated walkthrough
  • Browser agent clicks through the changed flow on Vercel, Netlify, Render or Cloudflare Pages previews
  • Second model, Gemini 3.1 Pro, grades the video with a verdict and QA score
  • Timestamped issues with suggested fixes, plus a judge.json file usable in CI
  • Required RunThru merge check and Slack notifications through /runthru notify
  • Exports 16:9 for PRs, with 1:1 and 9:16 cuts on Pro and above
  • iOS Simulator support, showing taps as touches inside a device frame

RunThru Pricing

Free plan covers 5 videos a month at 720p; Pro costs $29 per month for 30 videos and Team $99 per month for 100 videos, with extra videos billed per video.

Pricing checked against the official RunThru website in November 2026. Prices can change, so confirm before you buy.

Who is RunThru best for?

Engineering teams on GitHub who want every pull request demoed and QA-checked on its deploy preview before merging.

Things to know before using RunThru

  • Free plan is limited to 5 videos a month at 720p with a RunThru end card
  • Only runs when a repository owner, member or collaborator comments /runthru

RunThru FAQs

Does RunThru run or change my repository's code?

The site says RunThru cannot push code and never runs the repository's code; it works against the deploy preview, and videos are hosted by RunThru rather than committed to the repo.

Can RunThru test apps behind login or Vercel Deployment Protection?

Yes. A .runthru.yml file can hold demo credentials in test_data, a vercel_bypass setting and preview URL patterns.

Can I self-host RunThru?

Self-hosting is available via runthru login, and the Enterprise plan runs the same pipeline on your own runners and model keys, including localhost and VPN staging.

RunThru Alternatives

Popular alternatives to RunThru include Pollinations, NemoClaw and Agnes AI. Compare their pricing and what each is best for below.

ToolPricingBest for
Pollinations Freemium Developers and hobby builders who want a single API for adding AI images, audio and text to their websites, bots and app...
NemoClaw Free Developers and platform teams who want to run always-on AI agents on NVIDIA hardware under policy-based security control...
Agnes AI Freemium Developers building AI-powered apps who want access to several models through one API.
OrcaRouter Freemium Developers and teams who want to balance AI quality and cost across many models.
DiagramGPT Free Developers and students who need to sketch system designs and workflows quickly by describing them in words.
  • ai
  • tool
  • tools
  • pull request
  • code review
  • qa testing
  • github app
  • video walkthrough
  • deploy preview
  • ai agent
  • automated testing
  • narrated video
  • developer tools
  • ci
  • vercel
  • netlify
  • cloudflare pages
  • render
  • claude code
  • cursor
  • codex
  • copilot
  • slack
  • engineering teams
  • product managers
  • bug detection
  • browser automation
  • changelog videos

RunThru Reviews

What do you think about RunThru?

Leave a review for the community

No Review Found

Alternative Tools

Scalekit AgentKit
Scalekit AgentKit logo
Scalekit AgentKit
DEVELOPER TOOLS

Freemium

Scalekit AgentKit is an MCP gateway that connects AI agents to more than 600 connectors and over 30,000 tools behind a s...
FlyRouter
FlyRouter logo
FlyRouter
DEVELOPER TOOLS

Paid

FlyRouter is an LLM router and unified API gateway that gives developers one key and one endpoint for models from Claude...
ForAgent
ForAgent logo
ForAgent
DEVELOPER TOOLS

Freemium

ForAgent is a tool that gives AI agents private numbers so they can call and talk to each other, across your own devices...
Seldon Wren
Seldon Wren logo
Seldon Wren
DEVELOPER TOOLS

Free Trial

Wren by Seldon is an AI-powered QA testing tool that runs end to end browser tests from plain-English descriptions using...
Operum
Operum logo
Operum
DEVELOPER TOOLS

Freemium

Operum is an AI-powered desktop app that gives founders, developers and teams a coordinated AI product team that plans, ...
API Stock
API Stock logo
API Stock
DEVELOPER TOOLS

Paid

API Stock is a unified AI API that gives developers and businesses access to video, image, music and chat models through...
Arize AX
Arize AX logo
Arize AX
DEVELOPER TOOLS

Freemium

Arize AX is an AI engineering platform from Arize AI that gives teams observability and evaluation tools to understand a...
Pydantic Logfire
Pydantic Logfire logo
Pydantic Logfire
DEVELOPER TOOLS

Freemium

Pydantic Logfire is an AI observability and evaluation platform from the team behind Pydantic Validation, built to help ...
LangChain
LangChain logo
LangChain
DEVELOPER TOOLS

Freemium

LangChain is an agent engineering platform and set of open-source frameworks for building, testing, deploying and monito...
Self-Hosted AI Stack

Free

Self-Hosted AI Stack is an open-source project by Lin Song for running a private AI platform on infrastructure you contr...