Archive position — measured, not model output
0 likes on Devpost
2,263 of the 7,850 archived projects have more likes, and 5,587 share exactly 0 — so this project's #6,646 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
Shared Margin is a self-reported Codex-native tool that enables humans and AI models to co-consume books and films together, capturing shared moments with annotations, observations, and questions. It is described as a plugin for OpenAI's Codex platform, built during a hackathon, and designed to support "a durable mixed-media trail that never merges the human and model voices."
What changed
The project evolved from two prior tools — co-reading-mcp and film-matinee — into a unified plugin. The author states that this new version introduces a common schema for moments in books and films, a local-first viewer, and a shared session workflow.
Single most important open question
Is there any evidence of user adoption or engagement beyond the author’s own project posts?
Note: This analysis is based entirely on self-reported information from the project description. No third-party verification, traction data, revenue, or customer information is available.
What The Product Actually Is
The description states that Shared Margin is a Codex-native plugin built for co-consuming media with an AI model. It supports:
- A common schema for anchoring moments in books and films
- A five-tool MCP server for managing shared sessions (beginning, capturing, revisiting, finishing, exporting)
- A local-first viewer and Markdown export functionality
- A spoiler-safe Codex skill that keeps the experience linear
- A mixed-media trail where human and model voices are preserved separately
It is built using technologies including Codex, GPT-5.6, Node.js, Python, HTML, CSS, JavaScript, and FFmpeg.
Inference: The tool appears to be a prototype or proof-of-concept, not a commercial product. It is described as installable locally and designed for personal use during shared reading or viewing sessions.
Positioning & Claim Evolution
The author claims that Shared Margin was built from two prior tools — co-reading-mcp and film-matinee — which were separate but related. The evolution into Shared Margin represents an effort to unify these experiences into a single plugin.
Key positioning elements:
- It is not about summary generation, but rather about capturing specific moments.
- It emphasizes preserving the voices of both human and model without flattening them into one interpretation.
- The tool aims to support "company" with an AI, not just analysis or commentary.
Claim: The author positions Shared Margin as a way to make "accidental behavior deliberate, durable, and portable across media."
Inference: This is a conceptual positioning statement, not evidence of traction or adoption.
Target Customer & ICP
The description does not name specific customer segments. However, the author implies that the tool targets:
- People who enjoy reading or watching films with AI models
- Users interested in co-consuming media and annotating moments together
- Developers or creators working with Codex and AI tools for creative collaboration
Inference: The target audience is likely early adopters of AI tools, particularly those using Codex or similar platforms. No explicit ICP is stated.
Business Model & Pricing Evidence
There is no evidence in the description of a business model or pricing structure. The tool is described as:
- A local-first plugin
- An installable repository with setup scripts
- A prototype or hackathon project
Not evidenced: No revenue, monetization, or pricing information.
Technical & Delivery Signals
The author states that Shared Margin was built using:
- Codex and GPT-5.6
- Technologies: Node.js, Python, HTML, CSS, JavaScript, FFmpeg
- A five-tool MCP server
- A local viewer and Markdown export
- A setup script, smoke test, and demo
It is described as a plugin for Codex, and the repository is available on GitHub with submodules.
Inference: The tool is technically functional but likely not production-ready. It is presented as a prototype or proof-of-concept.
Traction & Maturity Signals
The author references:
- Views, likes, saves, and comments on prior project posts (8,273 views, 1,081 likes, 1,184 saves, 133 comments)
- A user comment indicating that someone used the tool to watch a film with an AI model for about 40 minutes across two sessions
Not evidenced: No revenue, customer base, or usage metrics beyond self-reported engagement on prior posts.
Competitive Context
The description does not mention direct competitors. However, it references:
- Two previous tools: co-reading-mcp and film-matinee
- The author’s intent to unify these into a single plugin
- A focus on AI-assisted co-consumption of media
Inference: This tool may be part of a broader trend in AI-assisted reading or viewing experiences, but no competitive landscape is described.
Open Questions & Risks
- The project is self-reported and unverified, with no third-party evidence.
- It is described as a hackathon prototype, not a commercial product.
- No evidence of user adoption, revenue, or customer traction.
- The tool is local-first and not scalable beyond individual use.
- The author states that the project was built during a single week-long hackathon — no indication of long-term development or iteration.
Inference: This is a proof-of-concept with limited commercial viability unless further developed and validated.
Questions the description leaves open
- What is the intended path from prototype to product?
- Are there any users beyond the author’s own engagement?
- How does this tool differ from existing AI co-reading or co-viewing tools (if any)?
- Is there a plan for monetization or commercial use?
- What are the technical limitations of the local-first approach, and how might they be overcome?
Overall Assessment
Not evidenced: No data on valuation, funding, traction, or business model.
Assessment: This is a self-reported hackathon project with no evidence of commercial viability or user adoption. It appears to be an early-stage idea or prototype, not a product ready for investment or partnership. The author’s claims about engagement and utility are based on prior project posts, which do not constitute verified traction.
Confidence: Low — based entirely on self-reported information with no external validation or data points.
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.