Archive position — measured, not model output
1 like on Devpost
505 of the 7,850 archived projects have more likes, and 1,758 share exactly 1 — so this project's #2,253 place in the like-ranked listing is a tie-break inside that group, not a ranking.
Projects (log scale)
Likes on Devpost. ▲ marks this project's group.
Show the figures
| Likes | Projects | Share of archive |
|---|---|---|
| 0 | 5,587 | 71.2% |
| 1 | 1,758 | 22.4% |
| 2 | 284 | 3.6% |
| 3–4 | 132 | 1.7% |
| 5–9 | 75 | 1.0% |
| 10+ | 14 | 0.2% |
User Stories BotA demo video on every pull request
Get a demo video on every new feature
GitHub App that watches your pull requests and records a narrated, captioned demo.
Save time on demo prep and make informed decisions faster with a video walkthrough of every new feature.
Executive Summary
What the company appears to be
Yorio is a self-reported web-based AI personal trainer that uses live camera input and voice coaching to guide users through workouts. The product is built using an orchestration platform called Jinn, which employs AI agents (primarily Codex) to perform development tasks. The core functionality includes pose tracking for rep counting, real-time voice coaching via the Gemini Live API, and a browser-based UI with optional camera input.
What changed
The project was submitted as part of an OpenAI 2026 hackathon, indicating it is in early-stage development or prototyping. It does not appear to have launched publicly beyond a demo or prototype stage. The author describes the product as “the shipping product running a scripted two-exercise session,” suggesting that this is a minimal viable version.
Single most important open question
Is there any evidence of user adoption, revenue, or traction beyond the self-reported demo and hackathon submission?
What The Product Actually Is
The description states that Yorio is an AI personal trainer as a web app with no installation required. It uses:
- A live voice coach powered by the Gemini Live API
- Camera-based pose tracking via MediaPipe for rep counting
- A green-orb avatar that greets users and guides them through workouts
- Optional camera input; voice-only mode is also supported
The demo includes a two-exercise session: squats and jumping jacks. The system counts reps out loud using classical pose state machines, which are explained in the code.
Inference The product appears to be a browser-based workout app that leverages AI for coaching and real-time feedback, but it is not yet a full-fledged commercial offering.
Positioning & Claim Evolution
The author positions Yorio as:
- An AI personal trainer that sees you move
- A replacement for expensive trainers or intimidating gyms
- A solution to the problem of skipping reps because workout videos don’t observe users
Claim
Yorio aims to be a low-cost, accessible alternative to traditional personal training.
Inference The positioning is rooted in accessibility and convenience, but no evidence exists that this has been validated with real users or markets.
Target Customer & ICP
The description states:
- The product targets people who struggle with motivation during workouts
- It aims to replace expensive trainers or gym intimidation
- Users can use it without installing anything (browser-based)
Inference The target customer is likely someone looking for a low-cost, self-guided workout solution. However, no evidence of actual user personas, segmentation, or market research is provided.
Business Model & Pricing Evidence
There is no evidence in the description of:
- Revenue model
- Pricing strategy
- Monetization plan
- Customer acquisition costs
- Any paid features or subscriptions
Inference The business model remains undefined. The demo is described as free and login-free, but there is no indication of how monetization will be implemented.
Technical & Delivery Signals
Key technical components mentioned:
- Built using Codex, Docker, Firebase Auth, Gemini Live API, Google Cloud Run, MediaPipe, Next.js, PostHog, React, React Three Fiber, Stripe, TailwindCSS, Three.js, TypeScript, Web Audio API, WebRTC, and WebSockets
- The build process was orchestrated by a platform called Jinn, an open-source AI orchestration tool
- Codex employees (AI agents) were used to implement, review, and verify code
- Rep counting uses classical pose state machines
- Real-time voice coaching is integrated with the workout loop
Inference The technical stack suggests a modern, browser-based SaaS product built using AI-assisted development. However, no evidence of scalability, performance metrics, or production deployment beyond the demo.
Traction & Maturity Signals
The description states:
- The demo is the shipping product
- It runs a scripted two-exercise session (squats and jumping jacks)
- The project was submitted to a hackathon
- No mention of users, customers, revenue, or usage data
Inference There is no evidence of traction or user adoption beyond the prototype. The product is described as “the shipping product” but lacks any commercial or market validation.
Competitive Context
No direct competitors are named in the description. However, the author implies a competitive space that includes:
- Traditional personal trainers
- Gym memberships
- Workout apps with video instruction (e.g., YouTube, Peloton, Fitbit)
Inference The competitive landscape is implied but not clearly defined or analyzed.
Open Questions & Risks
- Unproven market demand: No evidence of users or adoption beyond the demo
- AI-driven development model: Reliance on AI agents for development introduces uncertainty in quality control and scalability
- No monetization strategy: No indication of how the product will generate revenue
- Limited functionality: Only two exercises are demonstrated, with no clear roadmap to expansion
- Hackathon prototype: The project is not yet a commercial product
Questions the description leaves open
- What is the current stage of development beyond the demo?
- Have you tested Yorio with real users or in a controlled environment?
- How do you plan to scale the AI orchestration model for broader use cases?
- Is there any evidence of user engagement, retention, or feedback?
- What are your plans for monetization and customer acquisition?
- Can you provide more details on how the AI agents interact with each other and ensure quality control?
Overall Assessment
Not evidenced
There is no evidence of revenue, customers, traction, or a clear path to monetization. The project appears to be a hackathon prototype built using an experimental AI development framework. While the concept is interesting, there is insufficient commercial due-diligence evidence to assess viability or investment potential.
The author states that the demo is the shipping product, but this does not constitute traction or market validation. The lack of any user data, financials, or business model details makes it impossible to evaluate the project’s readiness for investment or partnership.
User Stories BotA demo video on every pull request
Get a demo video on every new feature
GitHub App that watches your pull requests and records a narrated, captioned demo.
Save time on demo prep and make informed decisions faster with a video walkthrough of every new feature.
Source
Submitted to the OpenAI 2026 hackathon on Devpost. Project home on Devpost. Back to the full gallery on Devpost.
This competitive analysis was produced by
top-founders.com (opens in a new tab)
Generated by a language model from this project's public Devpost page — its tagline, the author's own write-up and any built-with tags listed there — as captured in August 2026. Short quotations are the author's words. It is an opinion on the idea as a business, not on the people behind it, and it reflects the description as published then. If the project has moved on, request a correction below. The analysis is not independent research and contains no verified traction, revenue or customer data.
An independent guide by KFG International LLC — not affiliated with, endorsed by, or connected to Devpost or OpenAI.