Larch

The description states that Larch is a visual story studio for building branching, playable narratives. It allows creators to:

• Author dialogue, choices, variables, player input, AI dialogue, mini-games, and Unity Events on a readable canvas.
• Keep character personality, speaking style, portraits, expressions, and voice direction beside the story.
• Organize reusable art, audio, video, and documents in a dedicated media library.
• Preview branches immediately in the browser.
• Export the same project to versionable Larch JSON, a self-contained web player, or a Unity package with runtime code, media, and event hooks.

The core editor, preview, JSON normalization, and exports remain available without a model call. AI is described as an optional assistance layer, not the owner of the story.

Inference Larch appears to be a narrative design tool aimed at interactive storytelling teams, integrating AI for content generation while preserving deterministic outputs for engine use.

The author states that Larch was built around the question: “What if the story could remain the source of truth from the first line of dialogue to the playable build?” This suggests a positioning around single-source-of-truth storytelling and cross-platform narrative delivery.

It claims to reduce friction in workflows where teams translate ideas between documents, spreadsheets, asset folders, prompt histories, and engine scripts. It also positions itself as a tool that supports both writers and developers by offering:

• A readable canvas for story creation.
• AI-assisted generation within bounded contexts.
• Deterministic export paths across platforms (web and Unity).

Inference Larch is positioned as a hybrid creative-engineering tool, aiming to bridge the gap between narrative design and technical implementation.

The description states that Larch targets interactive-story teams who lose time translating ideas between documents, spreadsheets, asset folders, prompt histories, and engine scripts. It also mentions that it supports creators working with:

• Dialogue, choices, variables, player input, AI dialogue, mini-games, and Unity Events.
• Character personality, speaking style, portraits, expressions, and voice direction.

It is implied to be used by writers, designers, artists, and Unity developers involved in interactive storytelling projects.

Inference The ICP likely includes small to mid-sized teams working on narrative-driven games or interactive media, where cross-functional collaboration and deterministic output are critical.

No explicit business model or pricing information is provided in the description. The author states that:

• Core editor, preview, JSON normalization, and exports remain available without a model call.
• AI is an optional assistance layer.
• A server-side OpenAI key can be configured for AI features.

There is no mention of monetization, subscriptions, usage fees, or pricing tiers.

Inference The business model may be based on optional AI features, but the description does not confirm whether Larch intends to charge for access or use.

The author describes how Larch was built using:

• Frontend: React 19, TypeScript, React Flow, Zustand, Framer Motion, PixiJS, Three.js.
• Backend: Express 5 service providing sessions, ownership, versioning, uploads, billing, AI-provider adapters, Unity pairing, scoped MCP access, and export jobs.

Key technical signals include:

• One graph of nodes, edges, variables, localized content, characters, and media drives three deterministic outputs:
  • Re-importable Larch authoring JSON file.
  • Standalone HTML player with local saves, language selection, and sandboxed mini-game messaging.
  • Unity package with runtime-safe story data, media assets, a sample scene, editor tooling, and Unity Event callbacks.

Public web and Unity runtime payloads strip character secrets, system prompts, authoring prompts, account data, and Live/API keys.

Inference Larch appears to be built on modern frontend/backend stacks with strong emphasis on deterministic outputs, security boundaries, and cross-platform compatibility.

The project is described as a hackathon submission (OpenAI 2026). No evidence of revenue, customers, or adoption beyond the author’s own account is provided. The description mentions:

• A recorded demo.
• A public URL: larch.yapiflow.com.
• Plans for future features like collaborative review, analytics, and a Unity SDK.

There are no metrics on usage, retention, or user feedback.

Inference No traction or maturity signals are evident beyond the initial prototype and self-reported development process.

The author does not reference any direct competitors. However, the described functionality overlaps with:

• Tools for interactive storytelling (e.g., Twine, Choose Your Own Adventure systems).
• Game engine tools (Unity, Unreal) that support branching narratives.
• AI-assisted writing tools (e.g., Notion, ChatGPT plugins).
• Narrative design platforms for visual scripting and branching.

It is unclear whether Larch competes directly with any existing product or if it fills a niche in the intersection of narrative design and game development.

Inference Larch may be positioned as a narrative design tool with AI integration, but its competitive landscape is not defined.

• No revenue, customers, or traction data: The project is described only as a hackathon submission.
• Unproven market demand: No evidence of real-world usage or adoption.
• AI dependency risk: While AI is optional, its inclusion raises questions about scalability and control over content.
• Limited team size: Only one member listed (Yayapipi ZHI YANG), which may limit execution capacity.
• Self-reported only: All claims are unverified; no third-party validation or external sources.

Inference The lack of traction, revenue, and customer data makes it difficult to assess commercial viability. The tool’s success hinges on future development and market fit.

1. What is the current status of Larch beyond the hackathon prototype?
2. Are there any early adopters or pilot users?
3. How does Larch plan to monetize its AI features?
4. Has the team validated demand for this tool in the market?
5. What are the key assumptions about user behavior and workflow that underpin Larch’s design?
6. Is there a roadmap beyond the current MVP, and how is it prioritized?
7. How does Larch handle data privacy and security in its export workflows?