RunThru
Narrated video proof that a pull request works
What is RunThru?
RunThru is a GitHub app that records a narrated walkthrough video of a pull request and checks whether the changed feature works. A repository owner, member or collaborator comments /runthru on a pull request that has a deploy preview. An AI agent reads the diff, opens the preview in a real browser, uses the affected feature and records a captioned walkthrough with chapters, then a second model grades the video and posts a verdict with timestamped issues and suggested fixes back to the pull request, usually within 5 to 8 minutes. According to its site, Claude Opus 5.5 explores the feature and writes the narration, ElevenLabs provides the voice and Gemini 3.1 Pro reviews the result.
It detects previews from Vercel, Netlify, Render and Cloudflare Pages, and can also use a URL you pass, a pattern in a .runthru.yml file or a static folder. Each run posts a RunThru check on the pull request that can be made a required status check, and results can be sent to a Slack channel. RunThru cannot push code or run repository code, and it works on pull requests from coding agents such as Claude Code, Cursor, Codex and GitHub Copilot as well as from people. Every video gets a share page with the verdict, chapters, transcript and an MP4 download, and paid plans add square and vertical cuts for social posts and changelogs.
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 and no watermark, and Team costs $99 per month for 100 videos, then $0.90 per video, with priority rendering and a Slack channel for each repository. Enterprise runs the same pipeline on your own runners with your own model keys, including localhost, staging behind a VPN and the iOS Simulator.
Score breakdown (out of 5)
What you would use it for
- →Checking that a coding agent's pull request works before human review
- →Giving reviewers a short video instead of pulling a branch locally
- →Producing changelog and social clips of shipped features
Pros & Cons
👍 Pros
- ✓Free plan with 5 videos a month and no card or API keys
- ✓A separate model grades the video, so the recording agent does not mark its own work
- ✓Cannot push code or run repository code
👎 Cons
- ✗Needs a deploy preview or a reachable URL for each pull request
- ✗Runs only when someone comments /runthru, so a required check waits for that comment
- ✗Testing localhost or VPN staging needs an Enterprise self-hosted license
Key Features
- ✓ Narrated, captioned walkthrough video for a pull request with a deploy preview
- ✓ Second-model verdict with timestamped issues and suggested fixes
- ✓ RunThru status check that can be required before merging
- ✓ Automatic preview detection for Vercel, Netlify, Render and Cloudflare Pages
- ✓ Share page with chapters, transcript and MP4 download
- ✓ Slack notifications for every video or only those needing attention
- ✓ Square and vertical cuts on paid plans
Available on
Integrates with
RunThru Pricing
✅ RunThru has a free plan - no credit card required to start.
Free
- ✓5 videos a month
- ✓720p, RunThru end card
- ✓The verdict on every video
- ✓Share page, chapters and transcript
- ✓Slack notifications
Pro
- ✓30 videos a month, then $1 per video
- ✓1080p60 or 4K, no watermark
- ✓Square and vertical cuts
- ✓Your colors, a choice of narrator, music
Team
- ✓100 videos a month, then $0.90 per video
- ✓Everything in Pro
- ✓Priority rendering
- ✓A Slack channel for each repository
Enterprise
- ✓Runs the same pipeline on your own runners with your own model keys
- ✓Localhost, VPN staging and the iOS Simulator
- ✓Self-hosted CLI and GitHub Action license
Developer resources
Related Tools
Claude is the best AI assistant for long-document work and research where accuracy matters. Its context window of up to 1M tokens and resistance to sycophancy make it the honest choice when you need a thinking partner rather than an agreeable assistant. Start on the free tier; the Pro plan at $20/month is worth it if you regularly hit the free usage limits, and Max ($100/month) or Ultra ($200/month) suit heavier daily use.
ChatGPT is the most capable all-in-one AI assistant available. Its combination of image generation, voice mode, code execution, web browsing, and a large custom GPT ecosystem makes it the default choice for users who want one tool that handles everything. The tradeoff is that it is rarely the deepest tool on any single task.
Cursor is the most powerful AI code editor available. Its multi-file editing is ahead of plugin-based alternatives, making large-scale refactors practical in ways GitHub Copilot cannot match. At $30/month for Premium (Grok models included, other models billed at API rates) it is a meaningful upgrade for any developer doing more than small isolated changes.
GitHub Copilot is the right starting point for developers adopting AI-assisted coding. It integrates into whatever editor you already use, requires no workflow change, and has a usable free tier. The Pro plan at $10/month is the lowest-cost path to unlimited AI completions, though chat and agent work now draw from a monthly credit allowance; heavy agent users should look at Pro+ ($39) or Max ($100).
This page contains affiliate links. We may earn a commission at no extra cost to you. Learn more.