Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Morph

Videos of AI testing your PR, embedded in GitHub

Details

External ID
46891827
Source
HN
Company
—
Product
Morph
Website domain
morphllm.com
Launched
Feb. 4, 2026
Cohort
—
Upvotes
35
Upvotes percentile
0.7634770889487871
Tags
—
Fetched at
Sept. 7, 2026, 9:26 p.m.
Updated at
Sept. 7, 2026, 9:26 p.m.

Description

I review PRs all day and I've basically stopped reading them. Someone opens a 2000-line PR, I scroll, see it's mostly AI-generated React components, leave a comment, merge. I felt bad about it until I realized everyone on my team does the same thing.The problem is diffs are the wrong format. A PR might change how three buttons behave. Staring at green and red lines to understand that is crazy.The core reason we built this is that we feel that products today are built with assumptions from the past. 100x code with the same review systems means 100x human attention. Human attention cannot scale to fit that need, so we built something different. Humans are provably more engaged with video content than text.So we RL trained and built an agent that watches your preview deployment when you open a PR, clicks around the stuff that changed, and posts a video in the PR itself.Hardest part was figuring out where changed code actually lives in the running app. A diff could say Button.tsx line 47 changed, but that doesn't tell you how to find that button. We walk React's Fiber tree where each node maps back to source files, so we can trace changes to bounding boxes for the DOM elements. We then reward the model for showing and interacting within it.This obviously only works with React so we have to get more clever when generalizing to all languages.We trained an RL agent to interact with those components. Simple reward: points for getting modified stuff into viewport, double for clicking/typing. About 30% of what it does is weird, partial form submits, hitting escape mid-modal, because real users do that stuff and polite AI models won't test it on their own.This catches things unit tests miss completely: z-index bugs where something renders but you can't click it, scroll containers that trap you, handlers that fail silently.What's janky right now: feature flags, storing different user states, and anything that requires context not provided.Free to try: https://morphllm.com/dashboard/integrations/githubDemo: https://www.youtube.com/watch?v=Tc66RMA0nCY

Enrichment

Theme
browser automation and scraping for AI
Vertical
—
Function
Workflow automation
Audience
Developer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
ai tests your pull requests embedded in github
Manually corrected
False

Could you build this?

Partial The GitHub App webhook and video embedding are straightforward, but building an autonomous browser agent that intelligently discovers and exercises arbitrary UI changes from a PR diff requires advanced agentic orchestration.

What it would actually take: The system requires a GitHub App backend listening to PR events, a preview environment deployment orchestrator, and a headless browser engine (Playwright) driven by a vision-language agent model (VLM). The hard part is reliably parsing code diffs to infer intended user interactions, autonomously driving dynamic web SPAs without brittle failures, and capturing smooth screen recordings with automated bug/assertion reporting.

Discussion

13 comments analyzed.

Competitors mentioned: Loom (screen recording for PR context), Antigravity

Concerns raised: Only works on proprietary forge, not vendor-agnostic, Enables shipping large LLM-generated diffs without proper code review, Reduces human code review from already-insufficient ~150 lines baseline, Lack of transparency in landing page signup flow, Risk of normalizing professional corner-cutting with AI-generated code

Feature requests: Make manual review requirement configurable with educational best practices content, Support multiple git forges beyond proprietary platform, Require explicit opt-in to disable review safeguards

Competitors

Other products that read as similar to this one — 98 launches clear the similarity bar, closest 8 shown.

Attention rank: #24 of 99 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 84 days after the earliest competitor.

Other launches for this product