Archive position — measured, not model output
0 likes on Devpost
2,264 of the 7,856 archived projects have more likes, and 5,592 share exactly 0 — so this project's #3,524 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 | 5,592 | 71.2% |
| 1 | 1,758 | 22.4% |
| 2 | 285 | 3.6% |
| 3–4 | 132 | 1.7% |
| 5–9 | 75 | 1.0% |
| 10+ | 14 | 0.2% |
Executive Summary
What the company appears to be
COPYCAT is a self-reported multilingual social-deduction party game built as a ChatGPT App, designed for 3–10 players. It allows users to play with humans or AI-controlled players (CPUs), with no API key required and no need for separate login or installation.
What changed
The project was submitted as part of the OpenAI 2026 hackathon. The author describes a shift from a local bridge prototype to a true ChatGPT App architecture, where ChatGPT acts as both host and identity boundary, while the game server functions only as a referee.
Single most important open question
Is there any evidence of user engagement or adoption beyond the hackathon submission? The description does not indicate whether the app has been used by anyone outside of its creators or if it has moved past prototype stage.
What The Product Actually Is
The description states that COPYCAT is a 3–10 player social-deduction game. It uses a 16-word grid where one secret Copycat does not know the chosen word. Players give one-word hints, vote for the faker, and a caught Copycat gets one final comeback guess.
It supports:
- Global human matchmaking
- Private rooms
- Instant rule-based CPU practice
- ChatGPT-controlled CPU players
The game is described as being built using ChatGPT Apps SDK, with a backend that exposes tools via MCP (Model Communication Protocol) and uses Cloudflare Workers for serving endpoints and managing WebSocket state machines.
Not evidenced No information about actual gameplay mechanics beyond the description, no evidence of real users or usage data, no details on how the game is hosted or accessed outside of the hackathon submission.
Positioning & Claim Evolution
The author claims that COPYCAT:
- Is a multilingual social-deduction game inside ChatGPT
- Eliminates language barriers through automatic translation
- Allows players to use either human opponents or AI-controlled CPUs without requiring an API key
- Operates with no bridge, install, or login required
It positions itself as a low-friction, accessible party game that leverages ChatGPT’s infrastructure for identity and communication.
Inference The positioning suggests a focus on ease-of-use and accessibility in multiplayer gaming environments, especially within AI-native platforms like ChatGPT. However, this is based on the author's self-description and not validated by external metrics or user feedback.
Target Customer & ICP
The description states that COPYCAT targets:
- Users who enjoy party games
- People looking for low-friction multiplayer experiences
- Individuals interested in social-deduction gameplay
It is designed for 3–10 players and supports both human and AI opponents, suggesting an audience that values casual, accessible gaming.
Not evidenced No specific customer segments or personas are defined. No evidence of target market size, behavior patterns, or competitive positioning beyond the hackathon context.
Business Model & Pricing Evidence
The description states:
- There is no API key required
- No operator inference bills
- No need for separate login or installation
- The backend never calls an LLM
It also mentions that players can use ChatGPT-controlled CPUs without incurring costs, implying a model-free operation.
Inference This suggests the project may be built as a freemium or no-cost experience, possibly with monetization through optional features or future expansion. However, there is no explicit mention of pricing models or revenue streams.
Technical & Delivery Signals
The system is built using:
- ChatGPT Apps SDK
- MCP (Model Communication Protocol) tools
- Cloudflare Workers
- Durable Objects for WebSocket state management
Key technical claims include:
- The backend never calls an LLM
- Translation happens within the UI, not in the server
- CPU players reason privately and submit only final actions
- The system supports deterministic fallbacks and sandboxed networking
Not evidenced No evidence of production deployment beyond the hackathon submission. No information on scalability, performance, or long-term maintenance plans.
Traction & Maturity Signals
The description states:
- It was submitted to the OpenAI 2026 hackathon
- The project includes a permanent Cloudflare deployment
- It has end-to-end testing coverage
- It supports four complete play paths
However, there is no evidence of:
- Real-world usage or adoption
- Customer feedback or engagement metrics
- Any form of monetization or growth beyond the prototype stage
Absence of evidence
No data on user retention, active users, or product maturity beyond the hackathon submission.
Competitive Context
The description does not mention any competitors directly. It positions itself as a new type of party game within ChatGPT, leveraging AI-native architecture to reduce friction and cost.
Not evidenced No competitive analysis, no comparison with existing games or platforms, no indication of market saturation or differentiation strategy.
Key Risks & Red Flags
- Unverified claims: All features are self-reported without independent validation.
- Prototype-only status: No evidence of real-world usage or product-market fit beyond the hackathon.
- No revenue model: No indication of how the project might scale into a business.
- Limited scope: The game is described as a single-use experience within ChatGPT, with no clear path to broader adoption.
- Dependency on ChatGPT App ecosystem: If ChatGPT changes its APIs or policies, this could impact viability.
Diligence Questions To Ask The Founders
- What is the current status of the app beyond the hackathon submission? Has it been used by others?
- How does the team plan to scale beyond a single-user prototype?
- Are there any plans for monetization or user acquisition strategies?
- What are the limitations of the ChatGPT App architecture that might affect long-term viability?
- Can you provide evidence of user engagement or feedback from early adopters?
Investment/Partnership Verdict
This is a self-reported hackathon project with no verified traction, revenue, or customer data. The description indicates a working prototype built using ChatGPT Apps, but there is no evidence of real-world usage or business development.
Confidence level Low The project appears to be an experimental idea with potential for further development, but lacks commercial due-diligence signals such as user engagement, product-market fit, or scalability indicators. Any investment or partnership decision should be contingent on deeper validation and proof-of-concept beyond the hackathon submission.
Source
Submitted to the OpenAI 2026 hackathon on Devpost. Project home on DevPost.
The analysis above was generated by a language model from the project's own one-line description. It is not independent research and contains no verified traction, revenue or customer data.

