Solcraft: Crypto Venture Architect

A cyberpunk-themed, AI-powered "Founder in a Box" for Solana: generate ideas, verify uniqueness, craft blueprints, and move from DAPP prompt to pump token mint in one flow.

🧠 Project Logic & Core Features

The application operates on a three-stage pipeline: Forge (Ideation) -> Oracle (Verification) -> Architect (Blueprinting), plus a builder flow: DAPP -> MINT_TOKEN.

1. The Forge: Idea Generation

Users can configure the "Forge" to generate project ideas based on specific parameters:

• Modes:
  • Targeted: precise control over target ecosystems and sectors.
  • Random: chaotic, high-variance "wildcard" ideas.
• Parameters:
  • Ecosystem: Solana only.
  • Sectors: PUMP, DeFi, SocialFi, GameFi, Infra, DePin, NFT, DAO.
  • Degen Level (0-100): Controls the "risk/innovation" temperature.
    • Low Level: Focuses on Real World Assets (RWA), infrastructure, and institutional DeFi.
    • High Level: Focuses on meme mechanics, high-yield experiments, and "ponzi-nomics".
  • AI Model: Uses gpt-5.2-ca / ChatGPT API with structured JSON schemas to ensure consistent output formats (Title, Tagline, Description, Features).

2. The Oracle: Verification System

Once an idea is generated, it can be verified for uniqueness:

• Collision Detection: The AI queries the OpenAI completion API to reason about similar protocols and flag potential conflicts proactively.
• Pivot Suggestions: If a collision is found, the AI suggests specific pivots (e.g., "Add a privacy layer", "Rebrand to X").
• Verification Statuses:
  • VERIFIED: Unique idea, confirmed safe to proceed.
  • WARNING: Similar projects exist (listed with URLs).
  • FAILED: Verification process error.

3. The Architect: Blueprint Generation

For any generated idea, the user can "View Blueprint" to generate a full technical whitepaper on the fly:

• Executive Summary & Vision
• Tokenomics: Allocation, vesting schedules, and utility.
• Roadmap: 4-phase execution plan.
• Technical Architecture: Smart contract structure, frontend requirements, and indexing needs.
• Builder Flow: DAPP prompt generation for vibe coding IDEs, then pump token minting with auto-generated logos and prefilled metadata.

🛠 Tech Stack

• Frontend Framework: React 19 + Vite
• Language: TypeScript
• Styling:
  • Tailwind CSS (Utility classes)
  • Custom CSS (Cyber-grid backgrounds, Scanlines, Neon glows) via index.html
• AI Integration: OpenAI Chat Completions (gpt-5.2-ca) via fetch/custom wrapper
• Icons: Lucide React
• Animation: Framer Motion
• Internationalization: Fully localized support for English (en), Chinese (zh-CN, zh-TW), and Russian (ru).

🚀 Getting Started

Prerequisites

• Node.js (v18 or higher)
• An OpenAI API Key (ChatGPT GPT-5.2 compatibility)

Installation

1. Clone and Install

npm install

2. Configure Environment Create a .env.local file in the root directory:

OPENAI_BASE_URL=https://api.chatanywhere.org/v1/
OPENAI_MODEL=gpt-5.2-ca
OPENAI_API_KEY=sk-xxxx

Alternatively, you can enter your API key directly in the application Settings UI.

3. Run Locally

   npm run dev

   Access the app at http://localhost:5173

📂 Project Structure

• App.tsx: Main application controller. Handles state for ideas, logs, and UI layout.
• services/ai.ts: Core AI logic. Contains the generateIdeas, verifyIdea, and generateBlueprint functions with specific prompt engineering.
• types.ts: TypeScript definitions for Idea, ForgeConfig, Blueprint, etc.
• locales.ts: Translation strings for all supported languages.
• components/: Reusable UI components (IdeaCard, TerminalOutput, ConfigPanel, etc.).
• index.html: Contains the "Cyberpunk" global styles (.cyber-grid, .scanline, .neon-text).