Momentic Mo: QA agents that catch bugs by using your app
Momentic (YC W24) launched Mo, a QA agent that autonomously plans, explores, and bug-bashes web, iOS, and Android apps without scripts, and published QA Bench: 1,396 human-labeled bugs across Gitea, Metabase, Twenty, and Saleor, where Mo found 269 bugs in 60 minutes at 84% precision.
Why it matters
Vendor benchmark claims Mo found 3x the bugs of the next-best coding agent on the same apps and time budget — a recall-first QA agent with a public, reproducible benchmark attached.
What you could build with it
A small startup shipping weekly could point Mo at every deploy preview so an agent bug-bash runs before each release, catching broken flows and regressions that scripted tests miss.
Does it hold up?
Promising for pre-release QA: the benchmark is public and the agent is generally available with a CLI for CI, but the headline numbers are vendor-reported and have not been independently reproduced.
Built with Momentic Mo
- Launch HN: Momentic (YC W24) – Agents that catch bugs by using your apphackernews · Founders' Launch HN post with 158 points and 135 comments, including the QA Bench numbers and $250 in Mo spend for new signups.
- Momentic Launches Mo, Catches 269 of 1,396 QA Bench Bugsarticle · Independent writeup of the QA Bench results, noting the figures are vendor-reported and the benchmark is Momentic's own labeled corpus.
Learn more
First spotted on article: source.
More AI agents
CowAgent: open-source super AI assistant and agent harness with memory that compoundsAn open-source personal AI assistant and agent harness by zhayujie, back on Hacker News' front page this week: it…agents · JEV 0.78Agent Desktop: Vercel Labs' CLI that gives agents reliable desktop control via the accessibility treeVercel Labs' Rust CLI and C library lets AI agents read and operate desktop apps through OS accessibility trees: a…agents · JEV 0.76Open Notebook: self-hosted, multi-model NotebookLM alternative trending againOpen-source research notebook that turns documents, web pages, audio and video into searchable notebooks with chat…agents · JEV 0.75OpenBot: self-hosted AI coworkers, each with its own computer and audit trailCopilotKit's MIT-licensed alpha gives each AI coworker its own container with a browser, files and logins, behind a…agents · JEV 0.73DeepTutor: open-source, agent-native personalized tutor trending againHKUDS/DeepTutor, the University of Hong Kong's open-source personalized learning assistant, is trending on GitHub…agents · JEV 0.72claude-seo: universal SEO skill for Claude Code, trending on GitHubAgrici Daniel's MIT-licensed Claude Code plugin bundles 26 sub-skills and 19 specialist agents that run full SEO…agents · JEV 0.72
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.