OpenAI 2026 hackathon

Lineage

The UX Where Humans and Agents Shape Visual Work Together

Solo project by Jeremy Watt · 0 likes · 0 comments

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 #5,001 place in the like-ranked listing is a tie-break inside that group, not a ranking.

Projects (log scale)

1
10
100
1k
10k
05,592
11,758
2285
3–4132
5–975
10+14

Likes on Devpost. ▲ marks this project's group.

Show the figures
LikesProjectsShare of archive
05,59271.2%
11,75822.4%
22853.6%
3–41321.7%
5–9751.0%
10+140.2%
Devpost like counts for all 7,856 archived projects, captured when this archive was built.

Executive Summary

What the company appears to be: Lineage is a self-reported local-first visual workspace designed for creative teams working with AI agents. The author states it enables humans and agents to collaborate on visual work, maintaining a shared, durable creative state that preserves history and provides precise context for agents.

What changed: This project was submitted as part of the OpenAI 2026 hackathon. It represents an early-stage concept or prototype focused on human-agent collaboration in creative workflows. The description indicates development using Codex/GPT-5.6 Sol, React, Node.js, and SQLite.

Single most important open question: Is there evidence of traction, revenue, or customer adoption beyond the author's own account? The self-reported nature of all information makes it impossible to assess commercial viability or market demand without further data.

Back to contents

What The Product Actually Is

The description states that Lineage is a local-first TypeScript and React application with a Node.js/Express backend and SQLite-backed workspace state. It includes:

  • Visual lineage graphs
  • Re-roll history
  • Target-scoped agent claims
  • Task queues
  • Durable selection packets
  • Isolated stable, preview, and development runtime channels

It is described as a shared visual workspace where humans and agents create, review, and evolve creative assets together.

The author also notes that it was built using Codex with GPT-5.6 Sol, which helped in designing, implementing, testing, and hardening the human-agent workflow.

Confidence: Low — this is entirely self-reported, and no independent verification exists.

Back to contents

Positioning & Claim Evolution

The author states:

  • Creative teams increasingly work with AI agents, but context behind assets gets scattered across chats, folders, prompts, and disconnected iterations.
  • Lineage aims to provide a workspace where creative work stays understandable to people while remaining precise enough for an agent to continue accurately.
  • It allows humans to trace an asset from origin through branches, re-roll attempts, selections, and final formats.
  • Agents can retrieve exact asset, prompt, relationships, selections, and instructions via CLI rather than restarting from vague chat summaries.

Inference: The positioning appears to be a solution for human-agent collaboration in creative workflows, particularly around visual design or content creation. It claims to address fragmentation in current AI-assisted creative processes by offering a structured, shared workspace.

Confidence: Low — this is a claim made by the author, not verified.

Back to contents

Target Customer & ICP

The description states that Lineage targets creative teams working with AI agents, particularly those who need:

  • A durable creative history
  • Precise context for agents
  • Shared visual records of work

It also mentions that humans can trace assets through branches and iterations, while agents access exact context via CLI.

Inference: The ICP likely includes designers, content creators, or creative professionals who collaborate with AI tools in local environments, especially those using generative AI for visual output.

Confidence: Low — no explicit customer segmentation or market data provided.

Back to contents

Business Model & Pricing Evidence

Not evidenced. No mention of pricing, monetization strategy, or business model in the self-reported description.

Back to contents

Technical & Delivery Signals

The author states:

  • Built with Node.js/Express, React, SQLite, TypeScript
  • Uses Codex with GPT-5.6 Sol for development
  • Includes features like:
    • Visual lineage graphs
    • Re-roll history
    • Task queues
    • Durable selection packets
    • Isolated runtime channels

The project is described as a local-first application, suggesting it does not rely on cloud infrastructure or SaaS delivery.

Inference: The technical stack and architecture suggest a developer-focused, local-first tool with potential for integration into creative workflows involving AI agents.

Confidence: Low — this is self-reported, and no independent validation of the tech stack or delivery model exists.

Back to contents

Traction & Maturity Signals

Not evidenced. No data on:

  • Revenue
  • Customers
  • Usage metrics
  • Product adoption
  • Market traction

The project was submitted to a hackathon, indicating early-stage development.

Confidence: Very low — no evidence of traction or maturity beyond the author's own account.

Back to contents

Competitive Context

Not evidenced. No mention of competitors, market positioning, or competitive landscape in the self-reported description.

Back to contents

Key Risks & Red Flags

  • Self-reported only: All information is unverified and lacks third-party corroboration.
  • No traction or revenue data: The project appears to be a prototype or hackathon submission with no evidence of commercial adoption.
  • Limited team size: Only one member (Jeremy Watt) is listed, raising questions about execution capacity or scalability.
  • Unproven market demand: No indication that the described need for such a tool has been validated by users or customers.
  • Unclear monetization path: No business model or pricing structure provided.

Confidence: Medium — based on the lack of evidence and limited scope of the project, these are likely real risks, but they cannot be confirmed without further data.

Back to contents

Diligence Questions To Ask The Founders

  1. What specific creative workflows does Lineage aim to improve? Can you describe a typical user journey?
  2. How do you plan to validate market demand for this tool?
  3. Are there any early adopters or pilot users of the product?
  4. What is your roadmap for moving from prototype to scalable product?
  5. How do you intend to monetize Lineage, if at all?
  6. What are the key technical challenges that remain unresolved in the current version?
  7. What are the main differences between Lineage and existing tools in this space?

Back to contents

Investment/Partnership Verdict

Not evidenced.

The self-reported description indicates a concept or prototype submitted to a hackathon, with no evidence of traction, revenue, or customer adoption. The author’s claims about product functionality and positioning are unverified.

Confidence: Very low — this is not a commercial entity or product with demonstrated market fit or viability. It may be an idea in early development, but there is no basis to assess its potential for investment or partnership at this stage.

Back to contents

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.